Tootfinder

Cross-lingual Transfer or Machine Translation? On Data Augmentation for Monolingual Semantic Textual Similarity
Sho Hoshino, Akihiko Kato, Soichiro Murakami, Peinan Zhang
https://arxiv.org/abs/2403.05257

Cross-lingual Transfer or Machine Translation? On Data Augmentation for Monolingual Semantic Textual Similarity
Learning better sentence embeddings leads to improved performance for natural language understanding tasks including semantic textual similarity (STS) and natural language inference (NLI). As prior studies leverage large-scale labeled NLI datasets for fine-tuning masked language models to yield sentence embeddings, task performance for languages other than English is often left behind. In this study, we directly compared two data augmentation techniques as potential solutions for monolingual ST…

A Data Augmentation Pipeline to Generate Synthetic Labeled Datasets of 3D Echocardiography Images using a GAN
Cristiana Tiago, Andrew Gilbert, Ahmed S. Beela, Svein Arne Aase, Sten Roar Snare, Jurica Sprem
https://arxiv.org/abs/2403.05384

A Data Augmentation Pipeline to Generate Synthetic Labeled Datasets of 3D Echocardiography Images using a GAN
Due to privacy issues and limited amount of publicly available labeled datasets in the domain of medical imaging, we propose an image generation pipeline to synthesize 3D echocardiographic images with corresponding ground truth labels, to alleviate the need for data collection and for laborious and error-prone human labeling of images for subsequent Deep Learning (DL) tasks. The proposed method utilizes detailed anatomical segmentations of the heart as ground truth label sources. This initial d…

Cross-lingual Transfer or Machine Translation? On Data Augmentation for Monolingual Semantic Textual Similarity
Sho Hoshino, Akihiko Kato, Soichiro Murakami, Peinan Zhang
https://arxiv.org/abs/2403.05257

Cross-lingual Transfer or Machine Translation? On Data Augmentation for Monolingual Semantic Textual Similarity
Learning better sentence embeddings leads to improved performance for natural language understanding tasks including semantic textual similarity (STS) and natural language inference (NLI). As prior studies leverage large-scale labeled NLI datasets for fine-tuning masked language models to yield sentence embeddings, task performance for languages other than English is often left behind. In this study, we directly compared two data augmentation techniques as potential solutions for monolingual ST…

Resolution enhancement of SOHO/MDI Magnetograms
Ying Qin, Kai-Fan Ji, Hui Liu, Xiao-Guang Yu
https://arxiv.org/abs/2404.05968 https://

Resolution enhancement of SOHO/MDI Magnetograms
Research on the solar magnetic field and its effects on solar dynamo mechanisms and space weather events has benefited from the continual improvements in instrument resolution and measurement frequency. The augmentation and assimilation of historical observational data timelines also play a significant role in understanding the patterns of solar magnetic field variation. Within the realm of astronomical data processing, superresolution reconstruction refers to the process of using a substantial…

WixUp: A General Data Augmentation Framework for Wireless Perception in Tracking of Humans
Yin Li, Rajalakshmi Nandakumar
https://arxiv.org/abs/2405.04804 …

WixUp: A General Data Augmentation Framework for Wireless Perception in Tracking of Humans
Recent advancements in wireless perception technologies, including mmWave, WiFi, and acoustics, have expanded their application in human motion tracking and health monitoring. They are promising alternatives to traditional camera-based perception systems, thanks to their efficacy under diverse conditions or occlusions, and enhanced privacy. However, the integration of deep learning within this field introduces new challenges such as the need for extensive training data and poor model generaliza…

This https://arxiv.org/abs/2311.16909 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_sta…

Multinomial belief networks for healthcare data
Healthcare data from patient or population cohorts are often characterized by sparsity, high missingness and relatively small sample sizes. In addition, being able to quantify uncertainty is often important in a medical context. To address these analytical requirements we propose a deep generative Bayesian model for multinomial count data. We develop a collapsed Gibbs sampling procedure that takes advantage of a series of augmentation relations, inspired by the Zhou$\unicode{x2013}$Cong$\unicod…

Towards Effective Next POI Prediction: Spatial and Semantic Augmentation with Remote Sensing Data
Nan Jiang, Haitao Yuan, Jianing Si, Minxiao Chen, Shangguang Wang
https://arxiv.org/abs/2404.04271

Towards Effective Next POI Prediction: Spatial and Semantic Augmentation with Remote Sensing Data
The next point-of-interest (POI) prediction is a significant task in location-based services, yet its complexity arises from the consolidation of spatial and semantic intent. This fusion is subject to the influences of historical preferences, prevailing location, and environmental factors, thereby posing significant challenges. In addition, the uneven POI distribution further complicates the next POI prediction procedure. To address these challenges, we enrich input features and propose an effe…

This https://arxiv.org/abs/2403.02639 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csCV_…

False Positive Sampling-based Data Augmentation for Enhanced 3D Object Detection Accuracy
Recent studies have focused on enhancing the performance of 3D object detection models. Among various approaches, ground-truth sampling has been proposed as an augmentation technique to address the challenges posed by limited ground-truth data. However, an inherent issue with ground-truth sampling is its tendency to increase false positives. Therefore, this study aims to overcome the limitations of ground-truth sampling and improve the performance of 3D object detection models by developing a n…

This https://arxiv.org/abs/2303.02408 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_ees…

Data Augmentation for Generating Synthetic Electrogastrogram Time Series
To address an emerging need for large number of diverse datasets for rigor evaluation of signal processing techniques, we developed and evaluated a new method for generating synthetic electrogastrogram time series. We used electrogastrography (EGG) data from an open database to set model parameters and statistical tests to evaluate synthesized data. Additionally, we illustrated method customization for generating artificial EGG time series alterations caused by the simulator sickness. Proposed …

This https://arxiv.org/abs/2306.04527 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_ees…

ContriMix: Scalable stain color augmentation for domain generalization without domain labels in digital pathology
Differences in staining and imaging procedures can cause significant color variations in histopathology images, leading to poor generalization when deploying deep-learning models trained from a different data source. Various color augmentation methods have been proposed to generate synthetic images during training to make models more robust, eliminating the need for stain normalization during test time. Many color augmentation methods leverage domain labels to generate synthetic images. This ap…

Data Augmentation Policy Search for Long-Term Forecasting
Liran Nochumsohn, Omri Azencot
https://arxiv.org/abs/2405.00319 https://arx…

Data Augmentation Policy Search for Long-Term Forecasting
Data augmentation serves as a popular regularization technique to combat overfitting challenges in neural networks. While automatic augmentation has demonstrated success in image classification tasks, its application to time-series problems, particularly in long-term forecasting, has received comparatively less attention. To address this gap, we introduce a time-series automatic augmentation approach named TSAA, which is both efficient and easy to implement. The solution involves tackling the a…

This https://arxiv.org/abs/2403.00890 has been replaced.
link: https://scholar.google.com/scholar?q=a

Improving Android Malware Detection Through Data Augmentation Using Wasserstein Generative Adversarial Networks
Generative Adversarial Networks (GANs) have demonstrated their versatility across various applications, including data augmentation and malware detection. This research explores the effectiveness of utilizing GAN-generated data to train a model for the detection of Android malware. Given the considerable storage requirements of Android applications, the study proposes a method to synthetically represent data using GANs, thereby reducing storage demands. The proposed methodology involves creatin…

WixUp: A General Data Augmentation Framework for Wireless Perception in Tracking of Humans
Yin Li, Rajalakshmi Nandakumar
https://arxiv.org/abs/2405.04804 …

WixUp: A General Data Augmentation Framework for Wireless Perception in Tracking of Humans
Recent advancements in wireless perception technologies, including mmWave, WiFi, and acoustics, have expanded their application in human motion tracking and health monitoring. They are promising alternatives to traditional camera-based perception systems, thanks to their efficacy under diverse conditions or occlusions, and enhanced privacy. However, the integration of deep learning within this field introduces new challenges such as the need for extensive training data and poor model generaliza…

Data Augmentation with In-Context Learning and Comparative Evaluation in Math Word Problem Solving
Gulsum Yigit, Mehmet Fatih Amasyali
https://arxiv.org/abs/2404.03938

Data Augmentation with In-Context Learning and Comparative Evaluation in Math Word Problem Solving
Math Word Problem (MWP) solving presents a challenging task in Natural Language Processing (NLP). This study aims to provide MWP solvers with a more diverse training set, ultimately improving their ability to solve various math problems. We propose several methods for data augmentation by modifying the problem texts and equations, such as synonym replacement, rule-based: question replacement, and rule based: reversing question methodologies over two English MWP datasets. This study extends by i…

This https://arxiv.org/abs/2310.19041 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_sta…

On Linear Separation Capacity of Self-Supervised Representation Learning
Recent advances in self-supervised learning have highlighted the efficacy of data augmentation in learning data representation from unlabeled data. Training a linear model atop these enhanced representations can yield an adept classifier. Despite the remarkable empirical performance, the underlying mechanisms that enable data augmentation to unravel nonlinear data structures into linearly separable representations remain elusive. This paper seeks to bridge this gap by investigating under what c…

Importance Guided Data Augmentation for Neural-Based Code Understanding
Zeming Dong, Qiang Hu, Xiaofei Xie, Maxime Cordy, Mike Papadakis, Jianjun Zhao
https://arxiv.org/abs/2402.15769

Importance Guided Data Augmentation for Neural-Based Code Understanding
Pre-trained code models lead the era of code intelligence. Many models have been designed with impressive performance recently. However, one important problem, data augmentation for code data that automatically helps developers prepare training data lacks study in the field of code learning. In this paper, we introduce a general data augmentation framework, GenCode, to enhance the training of code understanding models. GenCode follows a generation-and-selection paradigm to prepare useful traini…

This https://arxiv.org/abs/2403.01944 has been replaced.
link: https://scholar.google.com/scholar?q=a

Fourier-basis Functions to Bridge Augmentation Gap: Rethinking Frequency Augmentation in Image Classification
Computer vision models normally witness degraded performance when deployed in real-world scenarios, due to unexpected changes in inputs that were not accounted for during training. Data augmentation is commonly used to address this issue, as it aims to increase data variety and reduce the distribution gap between training and test data. However, common visual augmentations might not guarantee extensive robustness of computer vision models. In this paper, we propose Auxiliary Fourier-basis Augme…

This https://arxiv.org/abs/2309.09371 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_sta…

Gibbs Sampling using Anti-correlation Gaussian Data Augmentation, with Applications to L1-ball-type Models
L1-ball-type priors are a recent generalization of the spike-and-slab priors. By transforming a continuous precursor distribution to the L1-ball boundary, it induces exact zeros with positive prior and posterior probabilities. With great flexibility in choosing the precursor and threshold distributions, we can easily specify models under structured sparsity, such as those with dependent probability for zeros and smoothness among the non-zeros. Motivated to significantly accelerate the posterior…

Predicting UAV Type: An Exploration of Sampling and Data Augmentation for Time Series Classification
Tarik Crnovrsanin, Calvin Yu, Dane Hankamer, Cody Dunne
https://arxiv.org/abs/2403.00565

Predicting UAV Type: An Exploration of Sampling and Data Augmentation for Time Series Classification
Unmanned aerial vehicles are becoming common and have many productive uses. However, their increased prevalence raises safety concerns -- how can we protect restricted airspace? Knowing the type of unmanned aerial vehicle can go a long way in determining any potential risks it carries. For instance, fixed-wing craft can carry more weight over longer distances, thus potentially posing a more significant threat. This paper presents a machine learning model for classifying unmanned aerial vehicles…

This https://arxiv.org/abs/2401.05871 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csCL_…

Enhancing Personality Recognition in Dialogue by Data Augmentation and Heterogeneous Conversational Graph Networks
Personality recognition is useful for enhancing robots' ability to tailor user-adaptive responses, thus fostering rich human-robot interactions. One of the challenges in this task is a limited number of speakers in existing dialogue corpora, which hampers the development of robust, speaker-independent personality recognition models. Additionally, accurately modeling both the interdependencies among interlocutors and the intra-dependencies within the speaker in dialogues remains a significant is…

Data Augmentation Policy Search for Long-Term Forecasting
Liran Nochumsohn, Omri Azencot
https://arxiv.org/abs/2405.00319 https://arx…

Data Augmentation Policy Search for Long-Term Forecasting
Data augmentation serves as a popular regularization technique to combat overfitting challenges in neural networks. While automatic augmentation has demonstrated success in image classification tasks, its application to time-series problems, particularly in long-term forecasting, has received comparatively less attention. To address this gap, we introduce a time-series automatic augmentation approach named TSAA, which is both efficient and easy to implement. The solution involves tackling the a…

Human-in-the-Loop Synthetic Text Data Inspection with Provenance Tracking
Hong Jin Kang, Fabrice Harel-Canada, Muhammad Ali Gulzar, Violet Peng, Miryung Kim
https://arxiv.org/abs/2404.18881

Human-in-the-Loop Synthetic Text Data Inspection with Provenance Tracking
Data augmentation techniques apply transformations to existing texts to generate additional data. The transformations may produce low-quality texts, where the meaning of the text is changed and the text may even be mangled beyond human comprehension. Analyzing the synthetically generated texts and their corresponding labels is slow and demanding. To winnow out texts with incorrect labels, we develop INSPECTOR, a human-in-the-loop data inspection technique. INSPECTOR combines the strengths of pr…

AnatoMix: Anatomy-aware Data Augmentation for Multi-organ Segmentation
Chang Liu, Fuxin Fan, Annette Schwarz, Andreas Maier
https://arxiv.org/abs/2403.03326

AnatoMix: Anatomy-aware Data Augmentation for Multi-organ Segmentation
Multi-organ segmentation in medical images is a widely researched task and can save much manual efforts of clinicians in daily routines. Automating the organ segmentation process using deep learning (DL) is a promising solution and state-of-the-art segmentation models are achieving promising accuracy. In this work, We proposed a novel data augmentation strategy for increasing the generalizibility of multi-organ segmentation datasets, namely AnatoMix. By object-level matching and manipulation, o…

This https://arxiv.org/abs/2306.06945 has been replaced.
link: https://scholar.google.com/scholar?q=a

Underwater Acoustic Target Recognition based on Smoothness-inducing Regularization and Spectrogram-based Data Augmentation
Underwater acoustic target recognition is a challenging task owing to the intricate underwater environments and limited data availability. Insufficient data can hinder the ability of recognition systems to support complex modeling, thus impeding their advancement. To improve the generalization capacity of recognition models, techniques such as data augmentation have been employed to simulate underwater signals and diversify data distribution. However, the complexity of underwater environments c…

A Comparative Study on Enhancing Prediction in Social Network Advertisement through Data Augmentation
Qikai Yang, Panfeng Li, Xinyu Shen, Zhicheng Ding, Wenjing Zhou, Yi Nian, Xinhe Xu
https://arxiv.org/abs/2404.13812

A Comparative Study on Enhancing Prediction in Social Network Advertisement through Data Augmentation
In the ever-evolving landscape of social network advertising, the volume and accuracy of data play a critical role in the performance of predictive models. However, the development of robust predictive algorithms is often hampered by the limited size and potential bias present in real-world datasets. This study presents and explores a generative augmentation framework of social network advertising data. Our framework explores three generative models for data augmentation - Generative Adversaria…

Learning-based model augmentation with LFRs
Jan H. Hoekstra, Chris Verhoek, Roland T\'oth, Maarten Schoukens
https://arxiv.org/abs/2404.01901 https://<…

Learning-based model augmentation with LFRs
Artificial neural networks (ANN) have proven to be effective in dealing with the identification nonlinear models for highly complex systems. To still make use of the prior information available from baseline models derived from, e.g., first-principles (FP), methods have been developed that integrate the prior knowledge into the identification algorithm for the ANN in a variety of methods. These methods have shown better estimation speeds and/or accuracy on unseen data. Among these methods are m…

Improving Topic Relevance Model by Mix-structured Summarization and LLM-based Data Augmentation
Yizhu Liu, Ran Tao, Shengyu Guo, Yifan Yang
https://arxiv.org/abs/2404.02616

Improving Topic Relevance Model by Mix-structured Summarization and LLM-based Data Augmentation
Topic relevance between query and document is a very important part of social search, which can evaluate the degree of matching between document and user's requirement. In most social search scenarios such as Dianping, modeling search relevance always faces two challenges. One is that many documents in social search are very long and have much redundant information. The other is that the training data for search relevance model is difficult to get, especially for multi-classification relevance …

Retrieve, Merge, Predict: Augmenting Tables with Data Lakes
Riccardo CappuzzoSODA Team - Inria Saclay, Gael VaroquauxSODA Team - Inria Saclay, Aimee CoelhoDataiku, Paolo PapottiEURECOM
https://arxiv.org/abs/2402.06282

Retrieve, Merge, Predict: Augmenting Tables with Data Lakes
We present an in-depth analysis of data discovery in data lakes, focusing on table augmentation for given machine learning tasks. We analyze alternative methods used in the three main steps: retrieving joinable tables, merging information, and predicting with the resultant table. As data lakes, the paper uses YADL (Yet Another Data Lake) -- a novel dataset we developed as a tool for benchmarking this data discovery task -- and Open Data US, a well-referenced real data lake. Through systematic e…

Label-Free Topic-Focused Summarization Using Query Augmentation
Wenchuan Mu, Kwan Hui Lim
https://arxiv.org/abs/2404.16411 https://ar…

Label-Free Topic-Focused Summarization Using Query Augmentation
In today's data and information-rich world, summarization techniques are essential in harnessing vast text to extract key information and enhance decision-making and efficiency. In particular, topic-focused summarization is important due to its ability to tailor content to specific aspects of an extended text. However, this usually requires extensive labelled datasets and considerable computational power. This study introduces a novel method, Augmented-Query Summarization (AQS), for topic-focus…

This https://arxiv.org/abs/2404.01921 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csCL_…

A Rationale-centric Counterfactual Data Augmentation Method for Cross-Document Event Coreference Resolution
Based on Pre-trained Language Models (PLMs), event coreference resolution (ECR) systems have demonstrated outstanding performance in clustering coreferential events across documents. However, the existing system exhibits an excessive reliance on the `triggers lexical matching' spurious pattern in the input mention pair text. We formalize the decision-making process of the baseline ECR system using a Structural Causal Model (SCM), aiming to identify spurious and causal associations (i.e., ration…

Data is all you need: Finetuning LLMs for Chip Design via an Automated design-data augmentation framework
Kaiyan Chang, Kun Wang, Nan Yang, Ying Wang, Dantong Jin, Wenlong Zhu, Zhirong Chen, Cangyuan Li, Hao Yan, Yunhao Zhou, Zhuoliang Zhao, Yuan Cheng, Yudong Pan, Yiqi Liu, Mengdi Wang, Shengwen Liang, yinhe han, Huawei Li, Xiaowei Li
https://

Data is all you need: Finetuning LLMs for Chip Design via an Automated design-data augmentation framework
Recent advances in large language models have demonstrated their potential for automated generation of hardware description language (HDL) code from high-level prompts. Researchers have utilized fine-tuning to enhance the ability of these large language models (LLMs) in the field of Chip Design. However, the lack of Verilog data hinders further improvement in the quality of Verilog generation by LLMs. Additionally, the absence of a Verilog and Electronic Design Automation (EDA) script data augm…

NaNa and MiGu: Semantic Data Augmentation Techniques to Enhance Protein Classification in Graph Neural Networks
Yi-Shan Lan, Pin-Yu Chen, Tsung-Yi Ho
https://arxiv.org/abs/2403.14736

NaNa and MiGu: Semantic Data Augmentation Techniques to Enhance Protein Classification in Graph Neural Networks
Protein classification tasks are essential in drug discovery. Real-world protein structures are dynamic, which will determine the properties of proteins. However, the existing machine learning methods, like ProNet (Wang et al., 2022a), only access limited conformational characteristics and protein side-chain features, leading to impractical protein structure and inaccuracy of protein classes in their predictions. In this paper, we propose novel semantic data augmentation methods, Novel Augmenta…

Curious about NLP beyond the startup hype? Join Emanuele Lapponi and Murhaf Fares at this year's #bbuzz and explore NLP in a 'traditional' setting. Tackle challenges such as data scarcity and domain specificity using e.g. data augmentation and zero-shot classification, and learn some tips and tricks to tackle concrete and relatable NLP problems.

A consistent test of spherical symmetry for multivariate and high-dimensional data via data augmentation
Bilol Banerjee, Anil K. Ghosh
https://arxiv.org/abs/2403.12491

A consistent test of spherical symmetry for multivariate and high-dimensional data via data augmentation
We develop a test for spherical symmetry of a multivariate distribution $P$ that works even when the dimension of the data $d$ is larger than the sample size $n$. We propose a non-negative measure $ζ(P)$ such that $ζ(P)=0$ if and only if $P$ is spherically symmetric. We construct a consistent estimator of $ζ(P)$ using the data augmentation method and investigate its large sample properties. The proposed test based on this estimator is calibrated using a novel resampling algorithm. Our test c…

ChildAugment: Data Augmentation Methods for Zero-Resource Children's Speaker Verification
Vishwanath Pratap Singh, Md Sahidullah, Tomi Kinnunen
https://arxiv.org/abs/2402.15214

ChildAugment: Data Augmentation Methods for Zero-Resource Children's Speaker Verification
The accuracy of modern automatic speaker verification (ASV) systems, when trained exclusively on adult data, drops substantially when applied to children's speech. The scarcity of children's speech corpora hinders fine-tuning ASV systems for children's speech. Hence, there is a timely need to explore more effective ways of reusing adults' speech data. One promising approach is to align vocal-tract parameters between adults and children through children-specific data augmentation, referred here …

Living-off-The-Land Reverse-Shell Detection by Informed Data Augmentation
Dmitrijs Trizna, Luca Demetrio, Battista Biggio, Fabio Roli
https://arxiv.org/abs/2402.18329

Living-off-The-Land Reverse-Shell Detection by Informed Data Augmentation
The living-off-the-land (LOTL) offensive methodologies rely on the perpetration of malicious actions through chains of commands executed by legitimate applications, identifiable exclusively by analysis of system logs. LOTL techniques are well hidden inside the stream of events generated by common legitimate activities, moreover threat actors often camouflage activity through obfuscation, making them particularly difficult to detect without incurring in plenty of false alarms, even using machine…

This https://arxiv.org/abs/2303.00510 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csSD_…

A Comparison of Speech Data Augmentation Methods Using S3PRL Toolkit
Data augmentations are known to improve robustness in speech-processing tasks. In this study, we summarize and compare different data augmentation strategies using S3PRL toolkit. We explore how HuBERT and wav2vec perform using different augmentation techniques (SpecAugment, Gaussian Noise, Speed Perturbation) for Phoneme Recognition (PR) and Automatic Speech Recognition (ASR) tasks. We evaluate model performance in terms of phoneme error rate (PER) and word error rate (WER). From the experiment…

Fidelitous Augmentation of Human Accelerometric Data for Deep Learning
Tracey K. M. Lee, H. W. Chan, K. H. Leo, Effie Chew, L. Zhao, Saeid Sanei
https://arxiv.org/abs/2404.14211 <…

Fidelitous Augmentation of Human Accelerometric Data for Deep Learning
Time series (TS) data have consistently been in short supply, yet their demand remains high for training systems in prediction, modeling, classification, and various other applications. Synthesis can serve to expand the sample population, yet it is crucial to maintain the statistical characteristics between the synthesized and the original TS : this ensures consistent sampling of data for both training and testing purposes. However the time domain features of the data may not be maintained. Thi…

This https://arxiv.org/abs/2402.01542 has been replaced.
link: https://scholar.google.com/scholar?q=a

Learning Collective Variables with Synthetic Data Augmentation through Physics-inspired Geodesic Interpolation
In molecular dynamics simulations, rare events, such as protein folding, are typically studied using enhanced sampling techniques, most of which are based on the definition of a collective variable (CV) along which acceleration occurs. Obtaining an expressive CV is crucial, but often hindered by the lack of information about the particular event, e.g., the transition from unfolded to folded conformation. We propose a simulation-free data augmentation strategy using physics-inspired metrics to g…

Emergent Equivariance in Deep Ensembles
Jan E. Gerken, Pan Kessel
https://arxiv.org/abs/2403.03103 https://arxiv.org/pdf/2403.03103…

Emergent Equivariance in Deep Ensembles
We demonstrate that deep ensembles are secretly equivariant models. More precisely, we show that deep ensembles become equivariant for all inputs and at all training times by simply using data augmentation. Crucially, equivariance holds off-manifold and for any architecture in the infinite width limit. The equivariance is emergent in the sense that predictions of individual ensemble members are not equivariant but their collective prediction is. Neural tangent kernel theory is used to derive th…

This https://arxiv.org/abs/2311.14153 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csRO_…

Tube-NeRF: Efficient Imitation Learning of Visuomotor Policies from MPC using Tube-Guided Data Augmentation and NeRFs
Imitation learning (IL) can train computationally-efficient sensorimotor policies from a resource-intensive Model Predictive Controller (MPC), but it often requires many samples, leading to long training times or limited robustness. To address these issues, we combine IL with a variant of robust MPC that accounts for process and sensing uncertainties, and we design a data augmentation (DA) strategy that enables efficient learning of vision-based policies. The proposed DA method, named Tube-NeRF…

This https://arxiv.org/abs/2402.06282 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csDB_…

Retrieve, Merge, Predict: Augmenting Tables with Data Lakes
We present an in-depth analysis of data discovery in data lakes, focusing on table augmentation for given machine learning tasks. We analyze alternative methods used in the three main steps: retrieving joinable tables, merging information, and predicting with the resultant table. As data lakes, the paper uses YADL (Yet Another Data Lake) -- a novel dataset we developed as a tool for benchmarking this data discovery task -- and Open Data US, a well-referenced real data lake. Through systematic e…

Improving Socratic Question Generation using Data Augmentation and Preference Optimization
Nischal Ashok Kumar, Andrew Lan
https://arxiv.org/abs/2403.00199

Improving Socratic Question Generation using Data Augmentation and Preference Optimization
The Socratic method is a way of guiding students toward solving a problem independently without directly revealing the solution to the problem. Although this method has been shown to significantly improve student learning outcomes, it remains a complex labor-intensive task for instructors. Large language models (LLMs) can be used to augment human effort by automatically generating Socratic questions for students. However, existing methods that involve prompting these LLMs sometimes produce inva…

How we won BraTS 2023 Adult Glioma challenge? Just faking it! Enhanced Synthetic Data Augmentation and Model Ensemble for brain tumour segmentation
Andr\'e Ferreira, Naida Solak, Jianning Li, Philipp Dammann, Jens Kleesiek, Victor Alves, Jan Egger
https://arxiv.org/abs/2402.17317

How we won BraTS 2023 Adult Glioma challenge? Just faking it! Enhanced Synthetic Data Augmentation and Model Ensemble for brain tumour segmentation
Deep Learning is the state-of-the-art technology for segmenting brain tumours. However, this requires a lot of high-quality data, which is difficult to obtain, especially in the medical field. Therefore, our solutions address this problem by using unconventional mechanisms for data augmentation. Generative adversarial networks and registration are used to massively increase the amount of available samples for training three different deep learning models for brain tumour segmentation, the first…

Is Contrastive Learning Necessary? A Study of Data Augmentation vs Contrastive Learning in Sequential Recommendation
Peilin Zhou, You-Liang Huang, Yueqi Xie, Jingqi Gao, Shoujin Wang, Jae Boum Kim, Sunghun Kim
https://arxiv.org/abs/2403.11136

Is Contrastive Learning Necessary? A Study of Data Augmentation vs Contrastive Learning in Sequential Recommendation
Sequential recommender systems (SRS) are designed to predict users' future behaviors based on their historical interaction data. Recent research has increasingly utilized contrastive learning (CL) to leverage unsupervised signals to alleviate the data sparsity issue in SRS. In general, CL-based SRS first augments the raw sequential interaction data by using data augmentation strategies and employs a contrastive training scheme to enforce the representations of those sequences from the same raw …

Training Generative Adversarial Network-Based Vocoder with Limited Data Using Augmentation-Conditional Discriminator
Takuhiro Kaneko, Hirokazu Kameoka, Kou Tanaka
https://arxiv.org/abs/2403.16464

Training Generative Adversarial Network-Based Vocoder with Limited Data Using Augmentation-Conditional Discriminator
A generative adversarial network (GAN)-based vocoder trained with an adversarial discriminator is commonly used for speech synthesis because of its fast, lightweight, and high-quality characteristics. However, this data-driven model requires a large amount of training data incurring high data-collection costs. This fact motivates us to train a GAN-based vocoder on limited data. A promising solution is to augment the training data to avoid overfitting. However, a standard discriminator is uncond…

This https://arxiv.org/abs/2403.14736 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_qbi…

NaNa and MiGu: Semantic Data Augmentation Techniques to Enhance Protein Classification in Graph Neural Networks
Protein classification tasks are essential in drug discovery. Real-world protein structures are dynamic, which will determine the properties of proteins. However, the existing machine learning methods, like ProNet (Wang et al., 2022a), only access limited conformational characteristics and protein side-chain features, leading to impractical protein structure and inaccuracy of protein classes in their predictions. In this paper, we propose novel semantic data augmentation methods, Novel Augmenta…

UIClip: A Data-driven Model for Assessing User Interface Design
Jason Wu, Yi-Hao Peng, Amanda Li, Amanda Swearngin, Jeffrey P. Bigham, Jeffrey Nichols
https://arxiv.org/abs/2404.12500

UIClip: A Data-driven Model for Assessing User Interface Design
User interface (UI) design is a difficult yet important task for ensuring the usability, accessibility, and aesthetic qualities of applications. In our paper, we develop a machine-learned model, UIClip, for assessing the design quality and visual relevance of a UI given its screenshot and natural language description. To train UIClip, we used a combination of automated crawling, synthetic augmentation, and human ratings to construct a large-scale dataset of UIs, collated by description and rank…

This https://arxiv.org/abs/2402.01542 has been replaced.
link: https://scholar.google.com/scholar?q=a

Learning Collective Variables with Synthetic Data Augmentation through Physics-inspired Geodesic Interpolation
In molecular dynamics simulations, rare events, such as protein folding, are typically studied using enhanced sampling techniques, most of which are based on the definition of a collective variable (CV) along which acceleration occurs. Obtaining an expressive CV is crucial, but often hindered by the lack of information about the particular event, e.g., the transition from unfolded to folded conformation. We propose a simulation-free data augmentation strategy using physics-inspired metrics to g…

Technical report on target classification in SAR track
Haonan Xu, Han Yinan, Haotian Si, Yang Yang
https://arxiv.org/abs/2405.02361 https://

Technical report on target classification in SAR track
This report proposes a robust method for classifying oceanic and atmospheric phenomena using synthetic aperture radar (SAR) imagery. Our proposed method leverages the powerful pre-trained model Swin Transformer v2 Large as the backbone and employs carefully designed data augmentation and exponential moving average during training to enhance the model's generalization capability and stability. In the testing stage, a method called ReAct is utilized to rectify activation values and utilize Energy…

This https://arxiv.org/abs/2402.14494 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csCL_…

Noise-BERT: A Unified Perturbation-Robust Framework with Noise Alignment Pre-training for Noisy Slot Filling Task
In a realistic dialogue system, the input information from users is often subject to various types of input perturbations, which affects the slot-filling task. Although rule-based data augmentation methods have achieved satisfactory results, they fail to exhibit the desired generalization when faced with unknown noise disturbances. In this study, we address the challenges posed by input perturbations in slot filling by proposing Noise-BERT, a unified Perturbation-Robust Framework with Noise Ali…

Is Contrastive Learning Necessary? A Study of Data Augmentation vs Contrastive Learning in Sequential Recommendation
Peilin Zhou, You-Liang Huang, Yueqi Xie, Jingqi Gao, Shoujin Wang, Jae Boum Kim, Sunghun Kim
https://arxiv.org/abs/2403.11136

Is Contrastive Learning Necessary? A Study of Data Augmentation vs Contrastive Learning in Sequential Recommendation
Sequential recommender systems (SRS) are designed to predict users' future behaviors based on their historical interaction data. Recent research has increasingly utilized contrastive learning (CL) to leverage unsupervised signals to alleviate the data sparsity issue in SRS. In general, CL-based SRS first augments the raw sequential interaction data by using data augmentation strategies and employs a contrastive training scheme to enforce the representations of those sequences from the same raw …

Efficiently Estimating Mutual Information Between Attributes Across Tables
A\'ecio Santos, Flip Korn, Juliana Freire
https://arxiv.org/abs/2403.15553 h…

Efficiently Estimating Mutual Information Between Attributes Across Tables
Relational data augmentation is a powerful technique for enhancing data analytics and improving machine learning models by incorporating columns from external datasets. However, it is challenging to efficiently discover relevant external tables to join with a given input table. Existing approaches rely on data discovery systems to identify joinable tables from external sources, typically based on overlap or containment. However, the sheer number of tables obtained from these systems results in …

Sim2Real Transfer for Audio-Visual Navigation with Frequency-Adaptive Acoustic Field Prediction
Changan Chen, Jordi Ramos, Anshul Tomar, Kristen Grauman
https://arxiv.org/abs/2405.02821

Sim2Real Transfer for Audio-Visual Navigation with Frequency-Adaptive Acoustic Field Prediction
Sim2real transfer has received increasing attention lately due to the success of learning robotic tasks in simulation end-to-end. While there has been a lot of progress in transferring vision-based navigation policies, the existing sim2real strategy for audio-visual navigation performs data augmentation empirically without measuring the acoustic gap. The sound differs from light in that it spans across much wider frequencies and thus requires a different solution for sim2real. We propose the fi…

DiffsFormer: A Diffusion Transformer on Stock Factor Augmentation
Yuan Gao, Haokun Chen, Xiang Wang, Zhicai Wang, Xue Wang, Jinyang Gao, Bolin Ding
https://arxiv.org/abs/2402.06656

DiffsFormer: A Diffusion Transformer on Stock Factor Augmentation
Machine learning models have demonstrated remarkable efficacy and efficiency in a wide range of stock forecasting tasks. However, the inherent challenges of data scarcity, including low signal-to-noise ratio (SNR) and data homogeneity, pose significant obstacles to accurate forecasting. To address this issue, we propose a novel approach that utilizes artificial intelligence-generated samples (AIGS) to enhance the training procedures. In our work, we introduce the Diffusion Model to generate sto…

LLM-DA: Data Augmentation via Large Language Models for Few-Shot Named Entity Recognition
Junjie Ye, Nuo Xu, Yikun Wang, Jie Zhou, Qi Zhang, Tao Gui, Xuanjing Huang
https://arxiv.org/abs/2402.14568

LLM-DA: Data Augmentation via Large Language Models for Few-Shot Named Entity Recognition
Despite the impressive capabilities of large language models (LLMs), their performance on information extraction tasks is still not entirely satisfactory. However, their remarkable rewriting capabilities and extensive world knowledge offer valuable insights to improve these tasks. In this paper, we propose $LLM-DA$, a novel data augmentation technique based on LLMs for the few-shot NER task. To overcome the limitations of existing data augmentation methods that compromise semantic integrity and…

StiefelGen: A Simple, Model Agnostic Approach for Time Series Data Augmentation over Riemannian Manifolds
Prasad Cheema, Mahito Sugiyama
https://arxiv.org/abs/2402.19287

Synthetic Data for Robust Stroke Segmentation
Liam Chalcroft, Ioannis Pappas, Cathy J. Price, John Ashburner
https://arxiv.org/abs/2404.01946 https://

Synthetic Data for Robust Stroke Segmentation
Deep learning-based semantic segmentation in neuroimaging currently requires high-resolution scans and extensive annotated datasets, posing significant barriers to clinical applicability. We present a novel synthetic framework for the task of lesion segmentation, extending the capabilities of the established SynthSeg approach to accommodate large heterogeneous pathologies with lesion-specific augmentation strategies. Our method trains deep learning models, demonstrated here with the UNet archit…

This https://arxiv.org/abs/2404.10096 has been replaced.
link: https://scholar.google.com/scholar?q=a

Vision Augmentation Prediction Autoencoder with Attention Design (VAPAAD)
Recent advancements in sequence prediction have significantly improved the accuracy of video data interpretation; however, existing models often overlook the potential of attention-based mechanisms for next-frame prediction. This study introduces the Vision Augmentation Prediction Autoencoder with Attention Design (VAPAAD), an innovative approach that integrates attention mechanisms into sequence prediction, enabling nuanced analysis and understanding of temporal dynamics in video sequences. Ut…

CyberDemo: Augmenting Simulated Human Demonstration for Real-World Dexterous Manipulation
Jun Wang, Yuzhe Qin, Kaiming Kuang, Yigit Korkmaz, Akhilan Gurumoorthy, Hao Su, Xiaolong Wang
https://arxiv.org/abs/2402.14795

CyberDemo: Augmenting Simulated Human Demonstration for Real-World Dexterous Manipulation
We introduce CyberDemo, a novel approach to robotic imitation learning that leverages simulated human demonstrations for real-world tasks. By incorporating extensive data augmentation in a simulated environment, CyberDemo outperforms traditional in-domain real-world demonstrations when transferred to the real world, handling diverse physical and visual conditions. Regardless of its affordability and convenience in data collection, CyberDemo outperforms baseline methods in terms of success rates…

This https://arxiv.org/abs/2112.06460 has been replaced.
link: https://scholar.google.com/scholar?q=a

Improving Sequential Recommendations via Bidirectional Temporal Data Augmentation with Pre-training
Sequential recommendation systems are integral to discerning temporal user preferences. Yet, the task of learning from abbreviated user interaction sequences poses a notable challenge. Data augmentation has been identified as a potent strategy to enhance the informational richness of these sequences. Traditional augmentation techniques, such as item randomization, may disrupt the inherent temporal dynamics. Although recent advancements in reverse chronological pseudo-item generation have shown …

This https://arxiv.org/abs/2304.01705 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_ees…

Cross-modal tumor segmentation using generative blending augmentation and self training
\textit{Objectives}: Data scarcity and domain shifts lead to biased training sets that do not accurately represent deployment conditions. A related practical problem is cross-modal image segmentation, where the objective is to segment unlabelled images using previously labelled datasets from other imaging modalities. \textit{Methods}: We propose a cross-modal segmentation method based on conventional image synthesis boosted by a new data augmentation technique called Generative Blending Augment…

This https://arxiv.org/abs/2401.06788 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_ees…

The NPU-ASLP-LiAuto System Description for Visual Speech Recognition in CNVSRC 2023
This paper delineates the visual speech recognition (VSR) system introduced by the NPU-ASLP-LiAuto (Team 237) in the first Chinese Continuous Visual Speech Recognition Challenge (CNVSRC) 2023, engaging in the fixed and open tracks of Single-Speaker VSR Task, and the open track of Multi-Speaker VSR Task. In terms of data processing, we leverage the lip motion extractor from the baseline1 to produce multi-scale video data. Besides, various augmentation techniques are applied during training, enco…

INSTRAUG: Automatic Instruction Augmentation for Multimodal Instruction Fine-tuning
Wei Han, Hui Chen, Soujanya Poria
https://arxiv.org/abs/2402.14492 http…

INSTRAUG: Automatic Instruction Augmentation for Multimodal Instruction Fine-tuning
Fine-tuning large language models (LLMs) on multi-task instruction-following data has been proven to be a powerful learning paradigm for improving their zero-shot capabilities on new tasks. Recent works about high-quality instruction-following data generation and selection require amounts of human labor to conceive model-understandable instructions for the given tasks and carefully filter the LLM-generated data. In this work, we introduce an automatic instruction augmentation method named INSTR…

This https://arxiv.org/abs/2404.10096 has been replaced.
link: https://scholar.google.com/scholar?q=a

Vision Augmentation Prediction Autoencoder with Attention Design (VAPAAD)
Recent advancements in sequence prediction have significantly improved the accuracy of video data interpretation; however, existing models often overlook the potential of attention-based mechanisms for next-frame prediction. This study introduces the Vision Augmentation Prediction Autoencoder with Attention Design (VAPAAD), an innovative approach that integrates attention mechanisms into sequence prediction, enabling nuanced analysis and understanding of temporal dynamics in video sequences. Ut…

CyberDemo: Augmenting Simulated Human Demonstration for Real-World Dexterous Manipulation
Jun Wang, Yuzhe Qin, Kaiming Kuang, Yigit Korkmaz, Akhilan Gurumoorthy, Hao Su, Xiaolong Wang
https://arxiv.org/abs/2402.14795

CyberDemo: Augmenting Simulated Human Demonstration for Real-World Dexterous Manipulation
We introduce CyberDemo, a novel approach to robotic imitation learning that leverages simulated human demonstrations for real-world tasks. By incorporating extensive data augmentation in a simulated environment, CyberDemo outperforms traditional in-domain real-world demonstrations when transferred to the real world, handling diverse physical and visual conditions. Regardless of its affordability and convenience in data collection, CyberDemo outperforms baseline methods in terms of success rates…

This https://arxiv.org/abs/2304.01705 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_ees…

Cross-modal tumor segmentation using generative blending augmentation and self training
\textit{Objectives}: Data scarcity and domain shifts lead to biased training sets that do not accurately represent deployment conditions. A related practical problem is cross-modal image segmentation, where the objective is to segment unlabelled images using previously labelled datasets from other imaging modalities. \textit{Methods}: We propose a cross-modal segmentation method based on conventional image synthesis boosted by a new data augmentation technique called Generative Blending Augment…

This https://arxiv.org/abs/2309.07289 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csHC_…

User Training with Error Augmentation for Electromyogram-based Gesture Classification
We designed and tested a system for real-time control of a user interface by extracting surface electromyographic (sEMG) activity from eight electrodes in a wrist-band configuration. sEMG data were streamed into a machine-learning algorithm that classified hand gestures in real-time. After an initial model calibration, participants were presented with one of three types of feedback during a human-learning stage: veridical feedback, in which predicted probabilities from the gesture classificatio…

This https://arxiv.org/abs/2306.06945 has been replaced.
link: https://scholar.google.com/scholar?q=a

Underwater Acoustic Target Recognition based on Smoothness-inducing Regularization and Spectrogram-based Data Augmentation
Underwater acoustic target recognition is a challenging task owing to the intricate underwater environments and limited data availability. Insufficient data can hinder the ability of recognition systems to support complex modeling, thus impeding their advancement. To improve the generalization capacity of recognition models, techniques such as data augmentation have been employed to simulate underwater signals and diversify data distribution. However, the complexity of underwater environments c…

Unifying Invariance and Spuriousity for Graph Out-of-Distribution via Probability of Necessity and Sufficiency
Xuexin Chen, Ruichu Cai, Kaitao Zheng, Zhifan Jiang, Zhengting Huang, Zhifeng Hao, Zijian Li
https://arxiv.org/abs/2402.09165

Unifying Invariance and Spuriousity for Graph Out-of-Distribution via Probability of Necessity and Sufficiency
Graph Out-of-Distribution (OOD), requiring that models trained on biased data generalize to the unseen test data, has a massive of real-world applications. One of the most mainstream methods is to extract the invariant subgraph by aligning the original and augmented data with the help of environment augmentation. However, these solutions might lead to the loss or redundancy of semantic subgraph and further result in suboptimal generalization. To address this challenge, we propose a unified fram…

Automatic Cardiac Pathology Recognition in Echocardiography Images Using Higher Order Dynamic Mode Decomposition and a Vision Transformer for Small Datasets
Andr\'es Bell-Navas, Nourelhouda Groun, Mar\'ia Villalba-Orero, Enrique Lara-Pezzi, Jes\'us Garicano-Mena, Soledad Le Clainche
https://arxiv.org/abs/2404.19579 https://arxiv.org/pdf/2404.19579
arXiv:2404.19579v1 Announce Type: new
Abstract: Heart diseases are the main international cause of human defunction. According to the WHO, nearly 18 million people decease each year because of heart diseases. Also considering the increase of medical data, much pressure is put on the health industry to develop systems for early and accurate heart disease recognition. In this work, an automatic cardiac pathology recognition system based on a novel deep learning framework is proposed, which analyses in real-time echocardiography video sequences. The system works in two stages. The first one transforms the data included in a database of echocardiography sequences into a machine-learning-compatible collection of annotated images which can be used in the training stage of any kind of machine learning-based framework, and more specifically with deep learning. This includes the use of the Higher Order Dynamic Mode Decomposition (HODMD) algorithm, for the first time to the authors' knowledge, for both data augmentation and feature extraction in the medical field. The second stage is focused on building and training a Vision Transformer (ViT), barely explored in the related literature. The ViT is adapted for an effective training from scratch, even with small datasets. The designed neural network analyses images from an echocardiography sequence to predict the heart state. The results obtained show the superiority of the proposed system and the efficacy of the HODMD algorithm, even outperforming pretrained Convolutional Neural Networks (CNNs), which are so far the method of choice in the literature.

This https://arxiv.org/abs/2403.07693 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csCL_…

Large, Small or Both: A Novel Data Augmentation Framework Based on Language Models for Debiasing Opinion Summarization
As more than 70$\%$ of reviews in the existing opinion summary data set are positive, current opinion summarization approaches are reluctant to generate negative summaries given the input of negative texts. To address such sentiment bias, a direct approach without the over-reliance on a specific framework is to generate additional data based on large language models to balance the emotional distribution of the dataset. However, data augmentation based on large language models faces two disadvan…

This https://arxiv.org/abs/2403.07693 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csCL_…

Large, Small or Both: A Novel Data Augmentation Framework Based on Language Models for Debiasing Opinion Summarization
As more than 70$\%$ of reviews in the existing opinion summary data set are positive, current opinion summarization approaches are reluctant to generate negative summaries given the input of negative texts. To address such sentiment bias, a direct approach without the over-reliance on a specific framework is to generate additional data based on large language models to balance the emotional distribution of the dataset. However, data augmentation based on large language models faces two disadvan…

Adversarial Curriculum Graph Contrastive Learning with Pair-wise Augmentation
Xinjian Zhao, Liang Zhang, Yang Liu, Ruocheng Guo, Xiangyu Zhao
https://arxiv.org/abs/2402.10468

Adversarial Curriculum Graph Contrastive Learning with Pair-wise Augmentation
Graph contrastive learning (GCL) has emerged as a pivotal technique in the domain of graph representation learning. A crucial aspect of effective GCL is the caliber of generated positive and negative samples, which is intrinsically dictated by their resemblance to the original data. Nevertheless, precise control over similarity during sample generation presents a formidable challenge, often impeding the effective discovery of representative graph patterns. To address this challenge, we propose …

Analyzing Data Augmentation for Medical Images: A Case Study in Ultrasound Images
Adam Tupper, Christian Gagn\'e
https://arxiv.org/abs/2403.09828 https…

Analyzing Data Augmentation for Medical Images: A Case Study in Ultrasound Images
Data augmentation is one of the most effective techniques to improve the generalization performance of deep neural networks. Yet, despite often facing limited data availability in medical image analysis, it is frequently underutilized. This appears to be due to a gap in our collective understanding of the efficacy of different augmentation techniques across medical imaging tasks and modalities. One domain where this is especially true is breast ultrasound images. This work addresses this issue …

The Impact of Frequency Bands on Acoustic Anomaly Detection of Machines using Deep Learning Based Model
Tin Nguyen, Lam Pham, Phat Lam, Dat Ngo, Hieu Tang, Alexander Schindler
https://arxiv.org/abs/2403.00379

The Impact of Frequency Bands on Acoustic Anomaly Detection of Machines using Deep Learning Based Model
In this paper, we propose a deep learning based model for Acoustic Anomaly Detection of Machines, the task for detecting abnormal machines by analysing the machine sound. By conducting extensive experiments, we indicate that multiple techniques of pseudo audios, audio segment, data augmentation, Mahalanobis distance, and narrow frequency bands, which mainly focus on feature engineering, are effective to enhance the system performance. Among the evaluating techniques, the narrow frequency bands …

Large, Small or Both: A Novel Data Augmentation Framework Based on Language Models for Debiasing Opinion Summarization
Yanyue Zhang, Pengfei Li, Yilong Lai, Deyu Zhou
https://arxiv.org/abs/2403.07693

Large, Small or Both: A Novel Data Augmentation Framework Based on Language Models for Debiasing Opinion Summarization
As more than 70$\%$ of reviews in the existing opinion summary data set are positive, current opinion summarization approaches are reluctant to generate negative summaries given the input of negative texts. To address such sentiment bias, a direct approach without the over-reliance on a specific framework is to generate additional data based on large language models to balance the emotional distribution of the dataset. However, data augmentation based on large language models faces two disadvan…

Text Role Classification in Scientific Charts Using Multimodal Transformers
Hye Jin Kim, Nicolas Lell, Ansgar Scherp
https://arxiv.org/abs/2402.14579 https…

Text Role Classification in Scientific Charts Using Multimodal Transformers
Text role classification involves classifying the semantic role of textual elements within scientific charts. For this task, we propose to finetune two pretrained multimodal document layout analysis models, LayoutLMv3 and UDOP, on chart datasets. The transformers utilize the three modalities of text, image, and layout as input. We further investigate whether data augmentation and balancing methods help the performance of the models. The models are evaluated on various chart datasets, and result…

Large, Small or Both: A Novel Data Augmentation Framework Based on Language Models for Debiasing Opinion Summarization
Yanyue Zhang, Pengfei Li, Yilong Lai, Deyu Zhou
https://arxiv.org/abs/2403.07693

Large, Small or Both: A Novel Data Augmentation Framework Based on Language Models for Debiasing Opinion Summarization
As more than 70$\%$ of reviews in the existing opinion summary data set are positive, current opinion summarization approaches are reluctant to generate negative summaries given the input of negative texts. To address such sentiment bias, a direct approach without the over-reliance on a specific framework is to generate additional data based on large language models to balance the emotional distribution of the dataset. However, data augmentation based on large language models faces two disadvan…

ThangDLU at #SMM4H 2024: Encoder-decoder models for classifying text data on social disorders in children and adolescents
Hoang-Thang Ta, Abu Bakar Siddiqur Rahman, Lotfollah Najjar, Alexander Gelbukh
#SMM4H (Social Media Mining for Health) 2024 Workshop, explicitly targeting the classification challenges within tweet data. Task 3 is a multi-class classification task centered on tweets discussing the impact of outdoor environments on symptoms of social anxiety. Task 5 involves a binary classification task focusing on tweets reporting medical disorders in children. We applied transfer learning from pre-trained encoder-decoder models such as BART-base and T5-small to identify the labels of a set of given tweets. We also presented some data augmentation methods to see their impact on the model performance. Finally, the systems obtained the best F1 score of 0.627 in Task 3 and the best F1 score of 0.841 in Task 5.

HAM-TTS: Hierarchical Acoustic Modeling for Token-Based Zero-Shot Text-to-Speech with Model and Data Scaling
Chunhui Wang, Chang Zeng, Bowen Zhang, Ziyang Ma, Yefan Zhu, Zifeng Cai, Jian Zhao, Zhonglin Jiang, Yong Chen
https://arxiv.org/abs/2403.05989

HAM-TTS: Hierarchical Acoustic Modeling for Token-Based Zero-Shot Text-to-Speech with Model and Data Scaling
Token-based text-to-speech (TTS) models have emerged as a promising avenue for generating natural and realistic speech, yet they grapple with low pronunciation accuracy, speaking style and timbre inconsistency, and a substantial need for diverse training data. In response, we introduce a novel hierarchical acoustic modeling approach complemented by a tailored data augmentation strategy and train it on the combination of real and synthetic data, scaling the data size up to 650k hours, leading to…

Repeated Padding as Data Augmentation for Sequential Recommendation
Yizhou Dang, Yuting Liu, Enneng Yang, Guibing Guo, Linying Jiang, Xingwei Wang, Jianzhe Zhao
https://arxiv.org/abs/2403.06372

Repeated Padding as Data Augmentation for Sequential Recommendation
Sequential recommendation aims to provide users with personalized suggestions based on their historical interactions. When training sequential models, padding is a widely adopted technique for two main reasons: 1) The vast majority of models can only handle fixed-length sequences; 2) Batching-based training needs to ensure that the sequences in each batch have the same length. The special value \emph{0} is usually used as the padding content, which does not contain the actual information and is…

This https://arxiv.org/abs/2403.16335 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_ees…

MEDDAP: Medical Dataset Enhancement via Diversified Augmentation Pipeline
The effectiveness of Deep Neural Networks (DNNs) heavily relies on the abundance and accuracy of available training data. However, collecting and annotating data on a large scale is often both costly and time-intensive, particularly in medical cases where practitioners are already occupied with their duties. Moreover, ensuring that the model remains robust across various scenarios of image capture is crucial in medical domains, especially when dealing with ultrasound images that vary based on t…

This https://arxiv.org/abs/2302.05262 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csCV_…

Evaluation of Data Augmentation and Loss Functions in Semantic Image Segmentation for Drilling Tool Wear Detection
Tool wear monitoring is crucial for quality control and cost reduction in manufacturing processes, of which drilling applications are one example. In this paper, we present a U-Net based semantic image segmentation pipeline, deployed on microscopy images of cutting inserts, for the purpose of wear detection. The wear area is differentiated in two different types, resulting in a multiclass classification problem. Joining the two wear types in one general wear class, on the other hand, allows the…

Continuous Control Reinforcement Learning: Distributed Distributional DrQ Algorithms
Zehao Zhou
https://arxiv.org/abs/2404.10645 https://

Continuous Control Reinforcement Learning: Distributed Distributional DrQ Algorithms
Distributed Distributional DrQ is a model-free and off-policy RL algorithm for continuous control tasks based on the state and observation of the agent, which is an actor-critic method with the data-augmentation and the distributional perspective of critic value function. Aim to learn to control the agent and master some tasks in a high-dimensional continuous space. DrQ-v2 uses DDPG as the backbone and achieves out-performance in various continuous control tasks. Here Distributed Distributional…

Inference Stage Denoising for Undersampled MRI Reconstruction
Yuyang Xue, Chen Qin, Sotirios A. Tsaftaris
https://arxiv.org/abs/2402.08692 https://<…

Inference Stage Denoising for Undersampled MRI Reconstruction
Reconstruction of magnetic resonance imaging (MRI) data has been positively affected by deep learning. A key challenge remains: to improve generalisation to distribution shifts between the training and testing data. Most approaches aim to address this via inductive design or data augmentation. However, they can be affected by misleading data, e.g. random noise, and cases where the inference stage data do not match assumptions in the modelled shifts. In this work, by employing a conditional hype…

This https://arxiv.org/abs/2211.05290 has been replaced.
link: https://scholar.google.com/scholar?q=a

Equivariant Contrastive Learning for Sequential Recommendation
Contrastive learning (CL) benefits the training of sequential recommendation models with informative self-supervision signals. Existing solutions apply general sequential data augmentation strategies to generate positive pairs and encourage their representations to be invariant. However, due to the inherent properties of user behavior sequences, some augmentation strategies, such as item substitution, can lead to changes in user intent. Learning indiscriminately invariant representations for al…

This https://arxiv.org/abs/2211.06687 has been replaced.
link: https://scholar.google.com/scholar?q=a

Large-scale Contrastive Language-Audio Pretraining with Feature Fusion and Keyword-to-Caption Augmentation
Contrastive learning has shown remarkable success in the field of multimodal representation learning. In this paper, we propose a pipeline of contrastive language-audio pretraining to develop an audio representation by combining audio data with natural language descriptions. To accomplish this target, we first release LAION-Audio-630K, a large collection of 633,526 audio-text pairs from different data sources. Second, we construct a contrastive language-audio pretraining model by considering di…

This https://arxiv.org/abs/2211.05290 has been replaced.
link: https://scholar.google.com/scholar?q=a

Equivariant Contrastive Learning for Sequential Recommendation
Contrastive learning (CL) benefits the training of sequential recommendation models with informative self-supervision signals. Existing solutions apply general sequential data augmentation strategies to generate positive pairs and encourage their representations to be invariant. However, due to the inherent properties of user behavior sequences, some augmentation strategies, such as item substitution, can lead to changes in user intent. Learning indiscriminately invariant representations for al…

This https://arxiv.org/abs/2401.17738 has been replaced.
link: https://scholar.google.com/scholar?q=a

Harnessing Smartwatch Microphone Sensors for Cough Detection and Classification
This study investigates the potential of using smartwatches with built-in microphone sensors for monitoring coughs and detecting various cough types. We conducted a study involving 32 participants and collected 9 hours of audio data in a controlled manner. Afterward, we processed this data using a structured approach, resulting in 223 positive cough samples. We further improved the dataset through augmentation techniques and employed a specialized 1D CNN model. This model achieved an impressive…

This https://arxiv.org/abs/2403.00199 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csCL_…

Improving Socratic Question Generation using Data Augmentation and Preference Optimization
The Socratic method is a way of guiding students toward solving a problem independently without directly revealing the solution to the problem. Although this method has been shown to significantly improve student learning outcomes, it remains a complex labor-intensive task for instructors. Large language models (LLMs) can be used to augment human effort by automatically generating Socratic questions for students. However, existing methods that involve prompting these LLMs sometimes produce inva…

This https://arxiv.org/abs/2401.03473 has been replaced.
link: https://scholar.google.com/scholar?q=a

ICMC-ASR: The ICASSP 2024 In-Car Multi-Channel Automatic Speech Recognition Challenge
To promote speech processing and recognition research in driving scenarios, we build on the success of the Intelligent Cockpit Speech Recognition Challenge (ICSRC) held at ISCSLP 2022 and launch the ICASSP 2024 In-Car Multi-Channel Automatic Speech Recognition (ICMC-ASR) Challenge. This challenge collects over 100 hours of multi-channel speech data recorded inside a new energy vehicle and 40 hours of noise for data augmentation. Two tracks, including automatic speech recognition (ASR) and autom…

Noise-BERT: A Unified Perturbation-Robust Framework with Noise Alignment Pre-training for Noisy Slot Filling Task
Jinxu Zhao, Guanting Dong, Yueyan Qiu, Tingfeng Hui, Xiaoshuai Song, Daichi Guo, Weiran Xu
https://arxiv.org/abs/2402.14494

Noise-BERT: A Unified Perturbation-Robust Framework with Noise Alignment Pre-training for Noisy Slot Filling Task
In a realistic dialogue system, the input information from users is often subject to various types of input perturbations, which affects the slot-filling task. Although rule-based data augmentation methods have achieved satisfactory results, they fail to exhibit the desired generalization when faced with unknown noise disturbances. In this study, we address the challenges posed by input perturbations in slot filling by proposing Noise-BERT, a unified Perturbation-Robust Framework with Noise Ali…

This https://arxiv.org/abs/2403.00199 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csCL_…

Improving Socratic Question Generation using Data Augmentation and Preference Optimization
The Socratic method is a way of guiding students toward solving a problem independently without directly revealing the solution to the problem. Although this method has been shown to significantly improve student learning outcomes, it remains a complex labor-intensive task for instructors. Large language models (LLMs) can be used to augment human effort by automatically generating Socratic questions for students. However, existing methods that involve prompting these LLMs sometimes produce inva…

Improving the Robustness of Dense Retrievers Against Typos via Multi-Positive Contrastive Learning
Georgios Sidiropoulos, Evangelos Kanoulas
https://arxiv.org/abs/2403.10939

Improving the Robustness of Dense Retrievers Against Typos via Multi-Positive Contrastive Learning
Dense retrieval has become the new paradigm in passage retrieval. Despite its effectiveness on typo-free queries, it is not robust when dealing with queries that contain typos. Current works on improving the typo-robustness of dense retrievers combine (i) data augmentation to obtain the typoed queries during training time with (ii) additional robustifying subtasks that aim to align the original, typo-free queries with their typoed variants. Even though multiple typoed variants are available as …

IMIL: Interactive Medical Image Learning Framework
Adrit Rao, Andrea Fisher, Ken Chang, John Christopher Panagides, Katherine McNamara, Joon-Young Lee, Oliver Aalami
https://arxiv.org/abs/2404.10965

IMIL: Interactive Medical Image Learning Framework
Data augmentations are widely used in training medical image deep learning models to increase the diversity and size of sparse datasets. However, commonly used augmentation techniques can result in loss of clinically relevant information from medical images, leading to incorrect predictions at inference time. We propose the Interactive Medical Image Learning (IMIL) framework, a novel approach for improving the training of medical image analysis algorithms that enables clinician-guided intermedi…

This https://arxiv.org/abs/2309.06358 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csCL_…

Generative Data Augmentation using LLMs improves Distributional Robustness in Question Answering
Robustness in Natural Language Processing continues to be a pertinent issue, where state of the art models under-perform under naturally shifted distributions. In the context of Question Answering, work on domain adaptation methods continues to be a growing body of research. However, very little attention has been given to the notion of domain generalization under natural distribution shifts, where the target domain is unknown. With drastic improvements in the quality and access to generative m…

This https://arxiv.org/abs/2403.11689 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_ees…

MoreStyle: Relax Low-frequency Constraint of Fourier-based Image Reconstruction in Generalizable Medical Image Segmentation
The task of single-source domain generalization (SDG) in medical image segmentation is crucial due to frequent domain shifts in clinical image datasets. To address the challenge of poor generalization across different domains, we introduce a Plug-and-Play module for data augmentation called MoreStyle. MoreStyle diversifies image styles by relaxing low-frequency constraints in Fourier space, guiding the image reconstruction network. With the help of adversarial learning, MoreStyle further expand…

This https://arxiv.org/abs/2309.06358 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csCL_…

Generative Data Augmentation using LLMs improves Distributional Robustness in Question Answering
Robustness in Natural Language Processing continues to be a pertinent issue, where state of the art models under-perform under naturally shifted distributions. In the context of Question Answering, work on domain adaptation methods continues to be a growing body of research. However, very little attention has been given to the notion of domain generalization under natural distribution shifts, where the target domain is unknown. With drastic improvements in the quality and access to generative m…

InternLM-Math: Open Math Large Language Models Toward Verifiable Reasoning
Huaiyuan Ying, Shuo Zhang, Linyang Li, Zhejian Zhou, Yunfan Shao, Zhaoye Fei, Yichuan Ma, Jiawei Hong, Kuikun Liu, Ziyi Wang, Yudong Wang, Zijian Wu, Shuaibin Li, Fengzhe Zhou, Hongwei Liu, Songyang Zhang, Wenwei Zhang, Hang Yan, Xipeng Qiu, Jiayu Wang, Kai Chen, Dahua Lin
htt…

InternLM-Math: Open Math Large Language Models Toward Verifiable Reasoning
The math abilities of large language models can represent their abstract reasoning ability. In this paper, we introduce and open-source our math reasoning LLMs InternLM-Math which is continue pre-trained from InternLM2. We unify chain-of-thought reasoning, reward modeling, formal reasoning, data augmentation, and code interpreter in a unified seq2seq format and supervise our model to be a versatile math reasoner, verifier, prover, and augmenter. These abilities can be used to develop the next m…