Tootfinder

This https://arxiv.org/abs/2402.17188 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csIR_…

PromptMM: Multi-Modal Knowledge Distillation for Recommendation with Prompt-Tuning
Multimedia online platforms (e.g., Amazon, TikTok) have greatly benefited from the incorporation of multimedia (e.g., visual, textual, and acoustic) content into their personal recommender systems. These modalities provide intuitive semantics that facilitate modality-aware user preference modeling. However, two key challenges in multi-modal recommenders remain unresolved: i) The introduction of multi-modal encoders with a large number of additional parameters causes overfitting, given high-dime…

New on the arxiv: “Network reconstruction via the minimum description length principle"
#network

Lifelong Benchmarks: Efficient Model Evaluation in an Era of Rapid Progress
Ameya Prabhu, Vishaal Udandarao, Philip Torr, Matthias Bethge, Adel Bibi, Samuel Albanie
https://arxiv.org/abs/2402.19472

Lifelong Benchmarks: Efficient Model Evaluation in an Era of Rapid Progress
Standardized benchmarks drive progress in machine learning. However, with repeated testing, the risk of overfitting grows as algorithms over-exploit benchmark idiosyncrasies. In our work, we seek to mitigate this challenge by compiling ever-expanding large-scale benchmarks called Lifelong Benchmarks. As exemplars of our approach, we create Lifelong-CIFAR10 and Lifelong-ImageNet, containing (for now) 1.69M and 1.98M test samples, respectively. While reducing overfitting, lifelong benchmarks intr…

This https://arxiv.org/abs/2405.01015 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_sta…

Network reconstruction via the minimum description length principle
A fundamental problem associated with the task of network reconstruction from dynamical or behavioral data consists in determining the most appropriate model complexity in a manner that prevents overfitting, and produces an inferred network with a statistically justifiable number of edges. The status quo in this context is based on $L_{1}$ regularization combined with cross-validation. As we demonstrate, besides its high computational cost, this commonplace approach unnecessarily ties the promo…

Understanding random forests and overfitting: a visualization and simulation study
Lasai Barre\~nada, Paula Dhiman, Dirk Timmerman, Anne-Laure Boulesteix, Ben Van Calster
https://arxiv.org/abs/2402.18612

Understanding random forests and overfitting: a visualization and simulation study
Random forests have become popular for clinical risk prediction modelling. In a case study on predicting ovarian malignancy, we observed training c-statistics close to 1. Although this suggests overfitting, performance was competitive on test data. We aimed to understand the behaviour of random forests by (1) visualizing data space in three real world case studies and (2) a simulation study. For the case studies, risk estimates were visualised using heatmaps in a 2-dimensional subspace. The sim…

Doubly Abductive Counterfactual Inference for Text-based Image Editing
Xue Song, Jiequan Cui, Hanwang Zhang, Jingjing Chen, Richang Hong, Yu-Gang Jiang
https://arxiv.org/abs/2403.02981

Doubly Abductive Counterfactual Inference for Text-based Image Editing
We study text-based image editing (TBIE) of a single image by counterfactual inference because it is an elegant formulation to precisely address the requirement: the edited image should retain the fidelity of the original one. Through the lens of the formulation, we find that the crux of TBIE is that existing techniques hardly achieve a good trade-off between editability and fidelity, mainly due to the overfitting of the single-image fine-tuning. To this end, we propose a Doubly Abductive Count…

An Onboard Framework for Staircases Modeling Based on Point Clouds
Chun Qing, Rongxiang Zeng, Xuan Wu, Yongliang Shi, Gan Ma
https://arxiv.org/abs/2405.01918

An Onboard Framework for Staircases Modeling Based on Point Clouds
The detection of traversable regions on staircases and the physical modeling constitutes pivotal aspects of the mobility of legged robots. This paper presents an onboard framework tailored to the detection of traversable regions and the modeling of physical attributes of staircases by point cloud data. To mitigate the influence of illumination variations and the overfitting due to the dataset diversity, a series of data augmentations are introduced to enhance the training of the fundamental net…

Dendrites endow artificial neural networks with accurate, robust and parameter-efficient learning
Spyridon Chavlis, Panayiota Poirazi
https://arxiv.org/abs/2404.03708

Dendrites endow artificial neural networks with accurate, robust and parameter-efficient learning
Artificial neural networks (ANNs) are at the core of most Deep learning (DL) algorithms that successfully tackle complex problems like image recognition, autonomous driving, and natural language processing. However, unlike biological brains who tackle similar problems in a very efficient manner, DL algorithms require a large number of trainable parameters, making them energy-intensive and prone to overfitting. Here, we show that a new ANN architecture that incorporates the structured connectivi…

LDSF: Lightweight Dual-Stream Framework for SAR Target Recognition by Coupling Local Electromagnetic Scattering Features and Global Visual Features
Xuying Xiong, Xinyu Zhang, Weidong Jiang, Tianpeng Liu
https://arxiv.org/abs/2403.03527

LDSF: Lightweight Dual-Stream Framework for SAR Target Recognition by Coupling Local Electromagnetic Scattering Features and Global Visual Features
Mainstream DNN-based SAR-ATR methods still face issues such as easy overfitting of a few training data, high computational overhead, and poor interpretability of the black-box model. Integrating physical knowledge into DNNs to improve performance and achieve a higher level of physical interpretability becomes the key to solving the above problems. This paper begins by focusing on the electromagnetic (EM) backscattering mechanism. We extract the EM scattering (EMS) information from the complex S…

LEMDA: A Novel Feature Engineering Method for Intrusion Detection in IoT Systems
Ali Ghubaish, Zebo Yang, Aiman Erbad, Raj Jain
https://arxiv.org/abs/2404.16870

LEMDA: A Novel Feature Engineering Method for Intrusion Detection in IoT Systems
Intrusion detection systems (IDS) for the Internet of Things (IoT) systems can use AI-based models to ensure secure communications. IoT systems tend to have many connected devices producing massive amounts of data with high dimensionality, which requires complex models. Complex models have notorious problems such as overfitting, low interpretability, and high computational complexity. Adding model complexity penalty (i.e., regularization) can ease overfitting, but it barely helps interpretabili…

This https://arxiv.org/abs/2403.17240 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csCL_…

The Role of $n$-gram Smoothing in the Age of Neural Networks
For nearly three decades, language models derived from the $n$-gram assumption held the state of the art on the task. The key to their success lay in the application of various smoothing techniques that served to combat overfitting. However, when neural language models toppled $n$-gram models as the best performers, $n$-gram smoothing techniques became less relevant. Indeed, it would hardly be an understatement to suggest that the line of inquiry into $n$-gram smoothing techniques became dorman…

Thermodynamic Overfitting and Generalization: Energetic Limits on Predictive Complexity
Alexander B. Boyd, James P. Crutchfield, Mile Gu, Felix C. Binder
https://arxiv.org/abs/2402.16995

Thermodynamic Overfitting and Generalization: Energetic Limits on Predictive Complexity
Efficiently harvesting thermodynamic resources requires a precise understanding of their structure. This becomes explicit through the lens of information engines -- thermodynamic engines that use information as fuel. Maximizing the work harvested using available information is a form of physically-instantiated machine learning that drives information engines to develop complex predictive memory to store an environment's temporal correlations. We show that an information engine's complex predict…

Specification Overfitting in Artificial Intelligence
Benjamin Roth, Pedro Henrique Luz de Araujo, Yuxi Xia, Saskia Kaltenbrunner, Christoph Korab
https://arxiv.org/abs/2403.08425 …

Specification Overfitting in Artificial Intelligence
Machine learning (ML) and artificial intelligence (AI) approaches are often criticized for their inherent bias and for their lack of control, accountability, and transparency. Consequently, regulatory bodies struggle with containing this technology's potential negative side effects. High-level requirements such as fairness and robustness need to be formalized into concrete specification metrics, imperfect proxies that capture isolated aspects of the underlying requirements. Given possible trade…

Wavelet Scattering Networks for Identifying Radio Galaxy Morphologies
Emma Tolley
https://arxiv.org/abs/2403.03016 https://arxiv.org/…

Wavelet Scattering Networks for Identifying Radio Galaxy Morphologies
Classifying the morphologies of radio galaxies is important to understand their physical properties and evolutionary histories. A galaxy's morphology is often determined by visual inspection, but as survey size increases robust automated techniques will be needed. Deep neural networks are an attractive method for automated classification, but have many free parameters and therefore require extensive training data and are subject to overfitting and generalization issues. We explore hybrid classi…

This https://arxiv.org/abs/2306.13185 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_sta…

An Agnostic View on the Cost of Overfitting in (Kernel) Ridge Regression
We study the cost of overfitting in noisy kernel ridge regression (KRR), which we define as the ratio between the test error of the interpolating ridgeless model and the test error of the optimally-tuned model. We take an "agnostic" view in the following sense: we consider the cost as a function of sample size for any target function, even if the sample size is not large enough for consistency or the target is outside the RKHS. We analyze the cost of overfitting under a Gaussian universality an…

Dendrites endow artificial neural networks with accurate, robust and parameter-efficient learning
Spyridon Chavlis, Panayiota Poirazi
https://arxiv.org/abs/2404.03708

Dendrites endow artificial neural networks with accurate, robust and parameter-efficient learning
Artificial neural networks (ANNs) are at the core of most Deep learning (DL) algorithms that successfully tackle complex problems like image recognition, autonomous driving, and natural language processing. However, unlike biological brains who tackle similar problems in a very efficient manner, DL algorithms require a large number of trainable parameters, making them energy-intensive and prone to overfitting. Here, we show that a new ANN architecture that incorporates the structured connectivi…

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/2303.00202 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csSE_…

PatchZero: Zero-Shot Automatic Patch Correctness Assessment
Automated Program Repair (APR) techniques have shown more and more promising results in fixing real-world bugs. Despite the effectiveness, APR techniques still face an overfitting problem: a generated patch can be incorrect although it passes all tests. It is time-consuming to manually evaluate the correctness of generated patches that can pass all tests. To address this problem, many approaches have been proposed to automatically assess the correctness of patches generated by APR techniques. T…

This https://arxiv.org/abs/2312.04542 has been replaced.
link: https://scholar.google.com/scholar?q=a

SoK: Unintended Interactions among Machine Learning Defenses and Risks
Machine learning (ML) models cannot neglect risks to security, privacy, and fairness. Several defenses have been proposed to mitigate such risks. When a defense is effective in mitigating one risk, it may correspond to increased or decreased susceptibility to other risks. Existing research lacks an effective framework to recognize and explain these unintended interactions. We present such a framework, based on the conjecture that overfitting and memorization underlie unintended interactions. We…

This https://arxiv.org/abs/2107.06714 has been replaced.
link: https://scholar.google.com/scholar?q=a

Robust Data-Driven CARA Optimization
We focus on data-driven, risk-averse optimization problems where decision-makers exhibit constant absolute risk aversion (CARA), represented by an exponential utility function. We consider payoff functions expressible as conic optimization problems, highlighting their expansive use in prescriptive analytics. Aiming to mitigate the overfitting issues inherent in empirical distribution-based optimization, we employ a robust satisficing strategy, which combines a target parameter with a Wasserstei…

Reducing the dimensionality and granularity in hierarchical categorical variables
Paul Wilsens, Katrien Antonio, Gerda Claeskens
https://arxiv.org/abs/2403.03613

Reducing the dimensionality and granularity in hierarchical categorical variables
Hierarchical categorical variables often exhibit many levels (high granularity) and many classes within each level (high dimensionality). This may cause overfitting and estimation issues when including such covariates in a predictive model. In current literature, a hierarchical covariate is often incorporated via nested random effects. However, this does not facilitate the assumption of classes having the same effect on the response variable. In this paper, we propose a methodology to obtain a …

This https://arxiv.org/abs/2306.13185 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_sta…

An Agnostic View on the Cost of Overfitting in (Kernel) Ridge Regression
We study the cost of overfitting in noisy kernel ridge regression (KRR), which we define as the ratio between the test error of the interpolating ridgeless model and the test error of the optimally-tuned model. We take an "agnostic" view in the following sense: we consider the cost as a function of sample size for any target function, even if the sample size is not large enough for consistency or the target is outside the RKHS. We analyze the cost of overfitting under a Gaussian universality an…

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…

Efficient Adapter Tuning of Pre-trained Speech Models for Automatic Speaker Verification
Mufan Sang, John H. L. Hansen
https://arxiv.org/abs/2403.00293 htt…

Efficient Adapter Tuning of Pre-trained Speech Models for Automatic Speaker Verification
With excellent generalization ability, self-supervised speech models have shown impressive performance on various downstream speech tasks in the pre-training and fine-tuning paradigm. However, as the growing size of pre-trained models, fine-tuning becomes practically unfeasible due to heavy computation and storage overhead, as well as the risk of overfitting. Adapters are lightweight modules inserted into pre-trained models to facilitate parameter-efficient adaptation. In this paper, we propose…

Fast Data-driven Greedy Sensor Selection for Ridge Regression
Yasuo Sasaki, Keigo Yamada, Takayuki Nagata, Yuji Saito, Taku Nonomura
https://arxiv.org/abs/2402.10596

Fast Data-driven Greedy Sensor Selection for Ridge Regression
We propose a data-driven sensor-selection algorithm for accurate estimation of the target variables from the selected measurements. The target variables are assumed to be estimated by a ridge-regression estimator which is trained based on the data. The proposed algorithm greedily selects sensors for minimization of the cost function of the estimator. Sensor selection which prevents the overfitting of the resulting estimator can be realized by setting a positive regularization parameter. The gre…

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/2403.00843 has been replaced.
link: https://scholar.google.com/scholar?q=a

Large Language Models are Learnable Planners for Long-Term Recommendation
Planning for both immediate and long-term benefits becomes increasingly important in recommendation. Existing methods apply Reinforcement Learning (RL) to learn planning capacity by maximizing cumulative reward for long-term recommendation. However, the scarcity of recommendation data presents challenges such as instability and susceptibility to overfitting when training RL models from scratch, resulting in sub-optimal performance. In this light, we propose to leverage the remarkable planning c…

This https://arxiv.org/abs/2402.01397 has been replaced.
link: https://scholar.google.com/scholar?q=a

A survey on robustness in trajectory prediction for autonomous vehicles
Autonomous vehicles rely on accurate trajectory prediction to inform decision-making processes related to navigation and collision avoidance. However, current trajectory prediction models show signs of overfitting, which may lead to unsafe or suboptimal behavior. To address these challenges, this paper presents a comprehensive framework that categorizes and assesses the definitions and strategies used in the literature on evaluating and improving the robustness of trajectory prediction models. …

This https://arxiv.org/abs/2403.13241 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csLG_…

Tackling Noisy Labels with Network Parameter Additive Decomposition
Given data with noisy labels, over-parameterized deep networks suffer overfitting mislabeled data, resulting in poor generalization. The memorization effect of deep networks shows that although the networks have the ability to memorize all noisy data, they would first memorize clean training data, and then gradually memorize mislabeled training data. A simple and effective method that exploits the memorization effect to combat noisy labels is early stopping. However, early stopping cannot disti…

This https://arxiv.org/abs/2404.04522 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csCL_…

Q-PEFT: Query-dependent Parameter Efficient Fine-tuning for Text Reranking with Large Language Models
Parameter Efficient Fine-Tuning (PEFT) methods have been extensively utilized in Large Language Models (LLMs) to improve the down-streaming tasks without the cost of fine-tuing the whole LLMs. Recent studies have shown how to effectively use PEFT for fine-tuning LLMs in ranking tasks with convincing performance; there are some limitations, including the learned prompt being fixed for different documents, overfitting to specific tasks, and low adaptation ability. In this paper, we introduce a qu…

Overfitting Reduction in Convex Regression
Zhiqiang Liao, Sheng Dai, Eunji Lim, Timo Kuosmanen
https://arxiv.org/abs/2404.09528 https://

Overfitting Reduction in Convex Regression
Convex regression is a method for estimating an unknown function $f_0$ from a data set of $n$ noisy observations when $f_0$ is known to be convex. This method has played an important role in operations research, economics, machine learning, and many other areas. It has been empirically observed that the convex regression estimator produces inconsistent estimates of $f_0$ and extremely large subgradients near the boundary of the domain of $f_0$ as $n$ increases. In this paper, we provide theoret…

This https://arxiv.org/abs/2401.12084 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_eco…

Temporal Aggregation for the Synthetic Control Method
The synthetic control method (SCM) is a popular approach for estimating the impact of a treatment on a single unit with panel data. Two challenges arise with higher frequency data (e.g., monthly versus yearly): (1) achieving excellent pre-treatment fit is typically more challenging; and (2) overfitting to noise is more likely. Aggregating data over time can mitigate these problems but can also destroy important signal. In this paper, we bound the bias for SCM with disaggregated and aggregated o…

PromptMM: Multi-Modal Knowledge Distillation for Recommendation with Prompt-Tuning
Wei Wei, Jiabin Tang, Yangqin Jiang, Lianghao Xia, Chao Huang
https://arxiv.org/abs/2402.17188 <…

PromptMM: Multi-Modal Knowledge Distillation for Recommendation with Prompt-Tuning
Multimedia online platforms (e.g., Amazon, TikTok) have greatly benefited from the incorporation of multimedia (e.g., visual, textual, and acoustic) content into their personal recommender systems. These modalities provide intuitive semantics that facilitate modality-aware user preference modeling. However, two key challenges in multi-modal recommenders remain unresolved: i) The introduction of multi-modal encoders with a large number of additional parameters causes overfitting, given high-dime…

This https://arxiv.org/abs/2312.09988 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_ees…

Towards Architecture-Agnostic Untrained Network Priors for Image Reconstruction with Frequency Regularization
Untrained networks inspired by deep image prior have shown promising capabilities in recovering a high-quality image from noisy or partial measurements, without requiring training data. Their success has been widely attributed to the spectral bias acting as an implicit regularization induced by suitable network architectures. However, applications of such network-based priors often entail superfluous architectural decisions, overfitting risks, and slow optimization, all of which hinder their pr…

Fast Data-driven Greedy Sensor Selection for Ridge Regression
Yasuo Sasaki, Keigo Yamada, Takayuki Nagata, Yuji Saito, Taku Nonomura
https://arxiv.org/abs/2402.10596

Fast Data-driven Greedy Sensor Selection for Ridge Regression
We propose a data-driven sensor-selection algorithm for accurate estimation of the target variables from the selected measurements. The target variables are assumed to be estimated by a ridge-regression estimator which is trained based on the data. The proposed algorithm greedily selects sensors for minimization of the cost function of the estimator. Sensor selection which prevents the overfitting of the resulting estimator can be realized by setting a positive regularization parameter. The gre…

Artificial Neural Microcircuits as Building Blocks: Concept and Challenges
Andrew Walter, Shimeng Wu, Andy M. Tyrrell, Liam McDaid, Malachy McElholm, Nidhin Thandassery Sumithran, Jim Harkin, Martin A. Trefzer
https://arxiv.org/abs/2403.16327

Artificial Neural Microcircuits as Building Blocks: Concept and Challenges
Artificial Neural Networks (ANNs) are one of the most widely employed forms of bio-inspired computation. However the current trend is for ANNs to be structurally homogeneous. Furthermore, this structural homogeneity requires the application of complex training and learning tools that produce application specific ANNs, susceptible to pitfalls such as overfitting. In this paper, an new approach is explored, inspired by the role played in biology by Neural Microcircuits, the so called ``fundamenta…

Gradient-enhanced deep Gaussian processes for multifidelity modelling
Viv Bone, Chris van der Heide, Kieran Mackle, Ingo H. J. Jahn, Peter M. Dower, Chris Manzie
https://arxiv.org/abs/2402.16059

Gradient-enhanced deep Gaussian processes for multifidelity modelling
Multifidelity models integrate data from multiple sources to produce a single approximator for the underlying process. Dense low-fidelity samples are used to reduce interpolation error, while sparse high-fidelity samples are used to compensate for bias or noise in the low-fidelity samples. Deep Gaussian processes (GPs) are attractive for multifidelity modelling as they are non-parametric, robust to overfitting, perform well for small datasets, and, critically, can capture nonlinear and input-de…

This https://arxiv.org/abs/2304.09783 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_ees…

Application of attention-based Siamese composite neural network in medical image recognition
Medical image recognition often faces the problem of insufficient data in practical applications. Image recognition and processing under few-shot conditions will produce overfitting, low recognition accuracy, low reliability and insufficient robustness. It is often the case that the difference of characteristics is subtle, and the recognition is affected by perspectives, background, occlusion and other factors, which increases the difficulty of recognition. Furthermore, in fine-grained images, …

Random Projection Layers for Multidimensional Time Sires Forecasting
Chin-Chia Michael Yeh, Yujie Fan, Xin Dai, Vivian Lai, Prince Osei Aboagye, Junpeng Wang, Huiyuan Chen, Yan Zheng, Zhongfang Zhuang, Liang Wang, Wei Zhang
https://arxiv.org/abs/2402.10487

Random Projection Layers for Multidimensional Time Sires Forecasting
All-Multi-Layer Perceptron (all-MLP) mixer models have been shown to be effective for time series forecasting problems. However, when such a model is applied to high-dimensional time series (e.g., the time series in a spatial-temporal dataset), its performance is likely to degrade due to overfitting issues. In this paper, we propose an all-MLP time series forecasting architecture, referred to as RPMixer. Our method leverages the ensemble-like behavior of deep neural networks, where each individ…

One-Bit Quantization and Sparsification for Multiclass Linear Classification via Regularized Regression
Reza Ghane, Danil Akhtiamov, Babak Hassibi
https://arxiv.org/abs/2402.10474

One-Bit Quantization and Sparsification for Multiclass Linear Classification via Regularized Regression
We study the use of linear regression for multiclass classification in the over-parametrized regime where some of the training data is mislabeled. In such scenarios it is necessary to add an explicit regularization term, $λf(w)$, for some convex function $f(\cdot)$, to avoid overfitting the mislabeled data. In our analysis, we assume that the data is sampled from a Gaussian Mixture Model with equal class sizes, and that a proportion $c$ of the training labels is corrupted for each class. Under…

This https://arxiv.org/abs/2401.00587 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_ees…

Brain Tumor Segmentation Based on Deep Learning, Attention Mechanisms, and Energy-Based Uncertainty Prediction
Brain tumors are one of the deadliest forms of cancer with a mortality rate of over 80%. A quick and accurate diagnosis is crucial to increase the chance of survival. However, in medical analysis, the manual annotation and segmentation of a brain tumor can be a complicated task. Multiple MRI modalities are typically analyzed as they provide unique information regarding the tumor regions. Although these MRI modalities are helpful for segmenting gliomas, they tend to increase overfitting and comp…

Parameter Efficient Finetuning for Speech Emotion Recognition and Domain Adaptation
Nineli Lashkarashvili, Wen Wu, Guangzhi Sun, Philip C. Woodland
https://arxiv.org/abs/2402.11747

Parameter Efficient Finetuning for Speech Emotion Recognition and Domain Adaptation
Foundation models have shown superior performance for speech emotion recognition (SER). However, given the limited data in emotion corpora, finetuning all parameters of large pre-trained models for SER can be both resource-intensive and susceptible to overfitting. This paper investigates parameter-efficient finetuning (PEFT) for SER. Various PEFT adaptors are systematically studied for both classification of discrete emotion categories and prediction of dimensional emotional attributes. The res…