Tootfinder

Inferring the Graph Structure of Images for Graph Neural Networks
Mayur S Gowda, John Shi, Augusto Santos, Jos\'e M. F. Moura
https://arxiv.org/abs/2509.04677 https://

Inferring the Graph Structure of Images for Graph Neural Networks
Image datasets such as MNIST are a key benchmark for testing Graph Neural Network (GNN) architectures. The images are traditionally represented as a grid graph with each node representing a pixel and edges connecting neighboring pixels (vertically and horizontally). The graph signal is the values (intensities) of each pixel in the image. The graphs are commonly used as input to graph neural networks (e.g., Graph Convolutional Neural Networks (Graph CNNs) [1, 2], Graph Attention Networks (GAT) […

Robust Experts: the Effect of Adversarial Training on CNNs with Sparse Mixture-of-Experts Layers
Svetlana Pavlitska, Haixi Fan, Konstantin Ditschuneit, J. Marius Z\"ollner
https://arxiv.org/abs/2509.05086

Robust Experts: the Effect of Adversarial Training on CNNs with Sparse Mixture-of-Experts Layers
Robustifying convolutional neural networks (CNNs) against adversarial attacks remains challenging and often requires resource-intensive countermeasures. We explore the use of sparse mixture-of-experts (MoE) layers to improve robustness by replacing selected residual blocks or convolutional layers, thereby increasing model capacity without additional inference cost. On ResNet architectures trained on CIFAR-100, we find that inserting a single MoE layer in the deeper stages leads to consistent im…

Accuracy-Constrained CNN Pruning for Efficient and Reliable EEG-Based Seizure Detection
Mounvik K, N Harshit
https://arxiv.org/abs/2509.05190 https://arxiv…

Accuracy-Constrained CNN Pruning for Efficient and Reliable EEG-Based Seizure Detection
Deep learning models, especially convolutional neural networks (CNNs), have shown considerable promise for biomedical signals such as EEG-based seizure detection. However, these models come with challenges, primarily due to their size and compute requirements in environments where real-time detection or limited resources are available. In this study, we present a lightweight one-dimensional CNN model with structured pruning to improve efficiency and reliability. The model was trained with mild …

Scale-interaction transformer: a hybrid cnn-transformer model for facial beauty prediction
Djamel Eddine Boukhari
https://arxiv.org/abs/2509.05078 https://…

Scale-interaction transformer: a hybrid cnn-transformer model for facial beauty prediction
Automated Facial Beauty Prediction (FBP) is a challenging computer vision task due to the complex interplay of local and global facial features that influence human perception. While Convolutional Neural Networks (CNNs) excel at feature extraction, they often process information at a fixed scale, potentially overlooking the critical inter-dependencies between features at different levels of granularity. To address this limitation, we introduce the Scale-Interaction Transformer (SIT), a novel hy…

COMET: Co-Optimization of a CNN Model using Efficient-Hardware OBC Techniques
Boyang Chen, Mohd Tasleem Khan, George Goussetis, Mathini Sellathurai, Yuan Ding, Jo\~ao F. C. Mota
https://arxiv.org/abs/2510.03516

COMET: Co-Optimization of a CNN Model using Efficient-Hardware OBC Techniques
Convolutional Neural Networks (CNNs) are highly effective for computer vision and pattern recognition tasks; however, their computational intensity and reliance on hardware such as FPGAs pose challenges for deployment on low-power edge devices. In this work, we present COMET, a framework of CNN designs that employ efficient hardware offset-binary coding (OBC) techniques to enable co-optimization of performance and resource utilization. The approach formulates CNN inference with OBC representati…

Vision-Based CNN Prediction of Sunspot Numbers from SDO/HMI Images
Fabian C. Quintero-Pareja, Diederik A. Montano-Burbano, Santiago Quintero-Pareja, D. Sierra-Porta
https://arxiv.org/abs/2510.03473

Vision-Based CNN Prediction of Sunspot Numbers from SDO/HMI Images
Sunspot numbers constitute the longest and most widely used record of solar activity, with direct implications for space weather forecasting and heliophysical research. Traditional sunspot counting relies on visual inspection or algorithmic feature detection, both of which are limited by subjectivity, image quality, and methodological inconsistencies. Recent advances in deep learning, particularly convolutional neural networks (CNNs), enable the direct use of solar imagery for automated predict…

Real Time FPGA Based CNNs for Detection, Classification, and Tracking in Autonomous Systems: State of the Art Designs and Optimizations
Safa Mohammed Sali, Mahmoud Meribout, Ashiyana Abdul Majeed
https://arxiv.org/abs/2509.04153

Real Time FPGA Based CNNs for Detection, Classification, and Tracking in Autonomous Systems: State of the Art Designs and Optimizations
This paper presents a comprehensive review of recent advances in deploying convolutional neural networks (CNNs) for object detection, classification, and tracking on Field Programmable Gate Arrays (FPGAs). With the increasing demand for real-time computer vision applications in domains such as autonomous vehicles, robotics, and surveillance, FPGAs have emerged as a powerful alternative to GPUs and ASICs due to their reconfigurability, low power consumption, and deterministic latency. We critica…

IntrusionX: A Hybrid Convolutional-LSTM Deep Learning Framework with Squirrel Search Optimization for Network Intrusion Detection
Ahsan Farabi, Muhaiminul Rashid Shad, Israt Khandaker
https://arxiv.org/abs/2510.00572

IntrusionX: A Hybrid Convolutional-LSTM Deep Learning Framework with Squirrel Search Optimization for Network Intrusion Detection
Intrusion Detection Systems (IDS) face persistent challenges due to evolving cyberattacks, high-dimensional traffic data, and severe class imbalance in benchmark datasets such as NSL-KDD. To address these issues, we propose IntrusionX, a hybrid deep learning framework that integrates Convolutional Neural Networks (CNNs) for local feature extraction and Long Short-Term Memory (LSTM) networks for temporal modeling. The architecture is further optimized using the Squirrel Search Algorithm (SSA), e…

Genuine multipartite entanglement verification with convolutional neural networks
Yi-Jun Luo, Xuan Leng, Chengjie Zhang
https://arxiv.org/abs/2508.13463 https://

Genuine multipartite entanglement verification with convolutional neural networks
In recent years, the detection of genuine multipartite entanglement (GME) via machine learning has received scant attention. Here, we employ convolutional neural networks (CNNs), as well as CNNs enhanced with squeeze-and-excitation (SE) to detect GME. We randomly generated GME states with 4 to 6 qubits and GHZ-diagonal states ranging from 4 to 20 qubits using the semidefinite programming approach. Subsequently, we assessed their classification accuracy. Our results demonstrate that the integrat…

Entropy-Based Non-Invasive Reliability Monitoring of Convolutional Neural Networks
Amirhossein Nazeri, Wael Hafez
https://arxiv.org/abs/2508.21715 https://…

Entropy-Based Non-Invasive Reliability Monitoring of Convolutional Neural Networks
Convolutional Neural Networks (CNNs) have become the foundation of modern computer vision, achieving unprecedented accuracy across diverse image recognition tasks. While these networks excel on in-distribution data, they remain vulnerable to adversarial perturbations imperceptible input modifications that cause misclassification with high confidence. However, existing detection methods either require expensive retraining, modify network architecture, or degrade performance on clean inputs. Here…

Explicit modelling of subject dependency in BCI decoding
Michele Romani, Francesco Paissan, Andrea Foss\`a, Elisabetta Farella
https://arxiv.org/abs/2509.23247 https://

Explicit modelling of subject dependency in BCI decoding
Brain-Computer Interfaces (BCIs) suffer from high inter-subject variability and limited labeled data, often requiring lengthy calibration phases. In this work, we present an end-to-end approach that explicitly models the subject dependency using lightweight convolutional neural networks (CNNs) conditioned on the subject's identity. Our method integrates hyperparameter optimization strategies that prioritize class imbalance and evaluates two conditioning mechanisms to adapt pre-trained models to…

Identification and Denoising of Radio Signals from Cosmic-Ray Air Showers using Convolutional Neural Networks
R. Abbasi, et al.
https://arxiv.org/abs/2508.14711 https://

Identification and Denoising of Radio Signals from Cosmic-Ray Air Showers using Convolutional Neural Networks
Radio pulses generated by cosmic-ray air showers can be used to reconstruct key properties like the energy and depth of the electromagnetic component of cosmic-ray air showers. Radio detection threshold, influenced by natural and anthropogenic radio background, can be reduced through various techniques. In this work, we demonstrate that convolutional neural networks (CNNs) are an effective way to lower the threshold. We developed two CNNs: a classifier to distinguish radio signal waveforms from…

Amplifying Emotional Signals: Data-Efficient Deep Learning for Robust Speech Emotion Recognition
Tai Vu
https://arxiv.org/abs/2509.00077 https://arxiv.org/…

Amplifying Emotional Signals: Data-Efficient Deep Learning for Robust Speech Emotion Recognition
Speech Emotion Recognition (SER) presents a significant yet persistent challenge in human-computer interaction. While deep learning has advanced spoken language processing, achieving high performance on limited datasets remains a critical hurdle. This paper confronts this issue by developing and evaluating a suite of machine learning models, including Support Vector Machines (SVMs), Long Short-Term Memory networks (LSTMs), and Convolutional Neural Networks (CNNs), for automated emotion classifi…

Team Westwood Solution for MIDOG 2025 Challenge
Tengyou Xu, Haochen Yang, Xiang 'Anthony' Chen, Hongyan Gu, Mohammad Haeri
https://arxiv.org/abs/2509.02600 https://

Team Westwood Solution for MIDOG 2025 Challenge
This abstract presents our solution (Team Westwood) for mitosis detection and atypical mitosis classification in the MItosis DOmain Generalization (MIDOG) 2025 challenge. For mitosis detection, we trained an nnUNetV2 for initial mitosis candidate screening with high sensitivity, followed by a random forest classifier ensembling predictions of three convolutional neural networks (CNNs): EfficientNet-b3, EfficientNet-b5, and EfficientNetV2-s. For the atypical mitosis classification, we trained an…

Comprehensive Evaluation of CNN-Based Audio Tagging Models on Resource-Constrained Devices
Jordi Grau-Haro, Ruben Ribes-Serrano, Javier Naranjo-Alcazar, Marta Garcia-Ballesteros, Pedro Zuccarello
https://arxiv.org/abs/2509.14049

Comprehensive Evaluation of CNN-Based Audio Tagging Models on Resource-Constrained Devices
Convolutional Neural Networks (CNNs) have demonstrated exceptional performance in audio tagging tasks. However, deploying these models on resource-constrained devices like the Raspberry Pi poses challenges related to computational efficiency and thermal management. In this paper, a comprehensive evaluation of multiple convolutional neural network (CNN) architectures for audio tagging on the Raspberry Pi is conducted, encompassing all 1D and 2D models from the Pretrained Audio Neural Networks (P…

Short-Duration Gravitational Wave Burst Detection using Convolutional Neural Network
Matteo Pracchia, Sacha Peters, Maxime Fays
https://arxiv.org/abs/2509.13241 https://

Short-Duration Gravitational Wave Burst Detection using Convolutional Neural Network
Detecting unmodeled gravitational wave (GW) bursts presents significant challenges due to the lack of accurate waveform templates required for matched-filtering techniques. A primary difficulty lies in distinguishing genuine signals from transient noise. Machine learning approaches, particularly convolutional neural networks (CNNs), offer promising alternatives for this classification problem. This paper presents a CNN-based pipeline for detecting short GW bursts (duration $< 10~\mathrm{s}$), a…

Interpreting Convolutional Neural Network Activation Maps with Hand-crafted Radiomics Features on Progression of Pediatric Craniopharyngioma after Irradiation Therapy
Wenjun Yang, Chuang Wang, Tina Davis, Jinsoo Uh, Chia-Ho Hua, Thomas E. Merchant
https://arxiv.org/abs/2509.20728

Interpreting Convolutional Neural Network Activation Maps with Hand-crafted Radiomics Features on Progression of Pediatric Craniopharyngioma after Irradiation Therapy
Purpose: Convolutional neural networks (CNNs) are promising in predicting treatment outcome for pediatric craniopharyngioma while the decision mechanisms are difficult to interpret. We compared the activation maps of CNN with hand crafted radiomics features of a densely connected artificial neural network (ANN) to correlate with clinical decisions. Methods: A cohort of 100 pediatric craniopharyngioma patients were included. Binary tumor progression was classified by an ANN and CNN with input of…

Binary Weight Multi-Bit Activation Quantization for Compute-in-Memory CNN Accelerators
Wenyong Zhou, Zhengwu Liu, Yuan Ren, Ngai Wong
https://arxiv.org/abs/2508.21524 https://…

Binary Weight Multi-Bit Activation Quantization for Compute-in-Memory CNN Accelerators
Compute-in-memory (CIM) accelerators have emerged as a promising way for enhancing the energy efficiency of convolutional neural networks (CNNs). Deploying CNNs on CIM platforms generally requires quantization of network weights and activations to meet hardware constraints. However, existing approaches either prioritize hardware efficiency with binary weight and activation quantization at the cost of accuracy, or utilize multi-bit weights and activations for greater accuracy but limited efficie…

A study on Deep Convolutional Neural Networks, transfer learning, and Mnet model for Cervical Cancer Detection
Saifuddin Sagor, Md Taimur Ahad, Faruk Ahmed, Rokonozzaman Ayon, Sanzida Parvin
https://arxiv.org/abs/2509.16250

A study on Deep Convolutional Neural Networks, transfer learning, and Mnet model for Cervical Cancer Detection
Early and accurate detection through Pap smear analysis is critical to improving patient outcomes and reducing mortality of Cervical cancer. State-of-the-art (SOTA) Convolutional Neural Networks (CNNs) require substantial computational resources, extended training time, and large datasets. In this study, a lightweight CNN model, S-Net (Simple Net), is developed specifically for cervical cancer detection and classification using Pap smear images to address these limitations. Alongside S-Net, six…

Deep Learning Inductive Biases for fMRI Time Series Classification during Resting-state and Movie-watching
Behdad Khodabandehloo, Reza Rajimehr
https://arxiv.org/abs/2509.16973 …

Deep Learning Inductive Biases for fMRI Time Series Classification during Resting-state and Movie-watching
Deep learning has advanced fMRI analysis, yet it remains unclear which architectural inductive biases are most effective at capturing functional patterns in human brain activity. This issue is particularly important in small-sample settings, as most datasets fall into this category. We compare models with three major inductive biases in deep learning including convolutional neural networks (CNNs), long short-term memory networks (LSTMs), and Transformers for the task of biological sex classific…

Implicit Augmentation from Distributional Symmetry in Turbulence Super-Resolution
Julia Balla, Jeremiah Bailey, Ali Backour, Elyssa Hofgard, Tommi Jaakkola, Tess Smidt, Ryley McConkey
https://arxiv.org/abs/2509.20683

Implicit Augmentation from Distributional Symmetry in Turbulence Super-Resolution
The immense computational cost of simulating turbulence has motivated the use of machine learning approaches for super-resolving turbulent flows. A central challenge is ensuring that learned models respect physical symmetries, such as rotational equivariance. We show that standard convolutional neural networks (CNNs) can partially acquire this symmetry without explicit augmentation or specialized architectures, as turbulence itself provides implicit rotational augmentation in both time and spac…

Efficient and Verifiable Privacy-Preserving Convolutional Computation for CNN Inference with Untrusted Clouds
Jinyu Lu, Xinrong Sun, Yunting Tao, Tong Ji, Fanyu Kong, Guoqiang Yang
https://arxiv.org/abs/2508.12832

Efficient and Verifiable Privacy-Preserving Convolutional Computation for CNN Inference with Untrusted Clouds
The widespread adoption of convolutional neural networks (CNNs) in resource-constrained scenarios has driven the development of Machine Learning as a Service (MLaaS) system. However, this approach is susceptible to privacy leakage, as the data sent from the client to the untrusted cloud server often contains sensitive information. Existing CNN privacy-preserving schemes, while effective in ensuring data confidentiality through homomorphic encryption and secret sharing, face efficiency bottlenec…

Compressing CNN models for resource-constrained systems by channel and layer pruning
Ahmed Sadaqa, Di Liu
https://arxiv.org/abs/2509.08714 https://arxiv.or…

Compressing CNN models for resource-constrained systems by channel and layer pruning
Convolutional Neural Networks (CNNs) have achieved significant breakthroughs in various fields. However, these advancements have led to a substantial increase in the complexity and size of these networks. This poses a challenge when deploying large and complex networks on edge devices. Consequently, model compression has emerged as a research field aimed at reducing the size and complexity of CNNs. One prominent technique in model compression is model pruning. This paper will present a new tech…

Machine learning revolution for exoplanet direct imaging detection: transformer architectures
Yu-Chia Lin
https://arxiv.org/abs/2508.14508 https://arxiv.or…

Machine learning revolution for exoplanet direct imaging detection: transformer architectures
Directly imaging exoplanets is a formidable challenge due to extreme contrast ratios and quasi-static speckle noise, motivating the exploration of advanced post-processing methods. While Convolutional Neural Networks (CNNs) have shown promise, their inherent limitations in capturing long-range dependencies in image sequences hinder their effectiveness. This study introduces a novel hybrid deep learning architecture that combines a CNN feature extractor with a Transformer encoder to leverage tem…

Real-Time Obstacle Avoidance for a Mobile Robot Using CNN-Based Sensor Fusion
Lamiaa H. Zain, Raafat E. Shalaby
https://arxiv.org/abs/2509.08095 https://ar…

Real-Time Obstacle Avoidance for a Mobile Robot Using CNN-Based Sensor Fusion
Obstacle avoidance is a critical component of the navigation stack required for mobile robots to operate effectively in complex and unknown environments. In this research, three end-to-end Convolutional Neural Networks (CNNs) were trained and evaluated offline and deployed on a differential-drive mobile robot for real-time obstacle avoidance to generate low-level steering commands from synchronized color and depth images acquired by an Intel RealSense D415 RGB-D camera in diverse environments. …

Spectral and Rhythm Feature Performance Evaluation for Category and Class Level Audio Classification with Deep Convolutional Neural Networks
Friedrich Wolf-Monheim
https://arxiv.org/abs/2509.07756

Spectral and Rhythm Feature Performance Evaluation for Category and Class Level Audio Classification with Deep Convolutional Neural Networks
Next to decision tree and k-nearest neighbours algorithms deep convolutional neural networks (CNNs) are widely used to classify audio data in many domains like music, speech or environmental sounds. To train a specific CNN various spectral and rhythm features like mel-scaled spectrograms, mel-frequency cepstral coefficients (MFCC), cyclic tempograms, short-time Fourier transform (STFT) chromagrams, constant-Q transform (CQT) chromagrams and chroma energy normalized statistics (CENS) chromagrams…

ImageNet-trained CNNs are not biased towards texture: Revisiting feature reliance through controlled suppression
Tom Burgert, Oliver Stoll, Paolo Rota, Beg\"um Demir
https://arxiv.org/abs/2509.20234

ImageNet-trained CNNs are not biased towards texture: Revisiting feature reliance through controlled suppression
The hypothesis that Convolutional Neural Networks (CNNs) are inherently texture-biased has shaped much of the discourse on feature use in deep learning. We revisit this hypothesis by examining limitations in the cue-conflict experiment by Geirhos et al. To address these limitations, we propose a domain-agnostic framework that quantifies feature reliance through systematic suppression of shape, texture, and color cues, avoiding the confounds of forced-choice conflicts. By evaluating humans and n…

Evaluating the Impact of Radiographic Noise on Chest X-ray Semantic Segmentation and Disease Classification Using a Scalable Noise Injection Framework
Derek Jiu, Kiran Nijjer, Nishant Chinta, Ryan Bui, Ben Liu, Kevin Zhu
https://arxiv.org/abs/2509.25265

Evaluating the Impact of Radiographic Noise on Chest X-ray Semantic Segmentation and Disease Classification Using a Scalable Noise Injection Framework
Deep learning models are increasingly used for radiographic analysis, but their reliability is challenged by the stochastic noise inherent in clinical imaging. A systematic, cross-task understanding of how different noise types impact these models is lacking. Here, we evaluate the robustness of state-of-the-art convolutional neural networks (CNNs) to simulated quantum (Poisson) and electronic (Gaussian) noise in two key chest X-ray tasks: semantic segmentation and pulmonary disease classificati…

Transformer Networks for Continuous Gravitational-wave Searches
Prasanna. M. Joshi, Reinhard Prix
https://arxiv.org/abs/2509.10912 https://arxiv.org/pdf/25…

Transformer Networks for Continuous Gravitational-wave Searches
Wide-parameter-space searches for continuous gravitational waves (CWs) using semi-coherent matched-filter methods require enormous computing power, which limits their achievable sensitivity. Here we explore an alternative search method based on training neural networks as classifiers on detector strain data with minimal pre-processing. Contrary to previous studies using convolutional neural networks (CNNs), we investigate the suitability of the transformer architecture, specifically the Vision …

Efficient Deep Neural Receiver with Post-Training Quantization
SaiKrishna Saketh Yellapragada, Esa Ollila, Mario Costa
https://arxiv.org/abs/2508.06275 https://

Efficient Deep Neural Receiver with Post-Training Quantization
Deep learning has recently garnered significant interest in wireless communications due to its superior performance compared to traditional model-based algorithms. Deep convolutional neural networks (CNNs) have demonstrated notable improvements in block error rate (BLER) under various channel models and mobility scenarios. However, the high computational complexity and resource demands of deep CNNs pose challenges for deployment in resource-constrained edge systems. The 3rd Generation Partnersh…

A Deep Learning Model of Lightning Stroke Density
Randall Jones II, Joel A. Thornton, Chris J. Wright, Robert Holzworth
https://arxiv.org/abs/2509.10399 https://

A Deep Learning Model of Lightning Stroke Density
Lightning plays a crucial role in the Earth's climate system, yet existing parameterizations for use in forecasting and earth system models show room for improvement in capturing spatial and temporal variations in its frequency. This study develops deep learning-based parameterizations of lightning stroke density using meteorological variables from the ERA and IMERG datasets. Convolutional neural networks (CNNs) with U-Net architectures are trained using World Wide Lightning Location Network (W…

Incorporating Visual Cortical Lateral Connection Properties into CNN: Recurrent Activation and Excitatory-Inhibitory Separation
Jin Hyun Park, Cheng Zhang, Yoonsuck Choe
https://arxiv.org/abs/2509.15460

Incorporating Visual Cortical Lateral Connection Properties into CNN: Recurrent Activation and Excitatory-Inhibitory Separation
The original Convolutional Neural Networks (CNNs) and their modern updates such as the ResNet are heavily inspired by the mammalian visual system. These models include afferent connections (retina and LGN to the visual cortex) and long-range projections (connections across different visual cortical areas). However, in the mammalian visual system, there are connections within each visual cortical area, known as lateral (or horizontal) connections. These would roughly correspond to connections wi…

Bayesian Topological Convolutional Neural Nets
Sarah Harkins Dayton, Hayden Everett, Ioannis Schizas, David L. Boothe Jr., Vasileios Maroulas
https://arxiv.org/abs/2510.11704 ht…

Bayesian Topological Convolutional Neural Nets
Convolutional neural networks (CNNs) have been established as the main workhorse in image data processing; nonetheless, they require large amounts of data to train, often produce overconfident predictions, and frequently lack the ability to quantify the uncertainty of their predictions. To address these concerns, we propose a new Bayesian topological CNN that promotes a novel interplay between topology-aware learning and Bayesian sampling. Specifically, it utilizes information from important ma…

200,000 Deep Learning Inferred Periods of Stellar Variability from The All-Sky Automated Survey for Supernovae
Meir E. Schochet, Penelope Planet, Zachary R. Claytor, Jamie Tayar, Adina D. Feinstein
https://arxiv.org/abs/2509.14423

200,000+ Deep Learning Inferred Periods of Stellar Variability from The All-Sky Automated Survey for Supernovae
Stars exhibit a range of variability periods that depend on their mass, age, and evolutionary stage. For space-based photometric data, convolutional neural networks (CNNs) have demonstrated success in recovering and measuring periodic variability from photometric missions like Kepler and TESS. All-sky ground-based surveys can have similar if not longer baselines than space-based missions, however these datasets are more challenging to work with due to irregular sampling, more complex systematic…

R-Net: A Reliable and Resource-Efficient CNN for Colorectal Cancer Detection with XAI Integration
Rokonozzaman Ayon, Md Taimur Ahad, Bo Song, Yan Li
https://arxiv.org/abs/2509.16251

R-Net: A Reliable and Resource-Efficient CNN for Colorectal Cancer Detection with XAI Integration
State-of-the-art (SOTA) Convolutional Neural Networks (CNNs) are criticized for their extensive computational power, long training times, and large datasets. To overcome this limitation, we propose a reasonable network (R-Net), a lightweight CNN only to detect and classify colorectal cancer (CRC) using the Enteroscope Biopsy Histopathological Hematoxylin and Eosin Image Dataset (EBHI). Furthermore, six SOTA CNNs, including Multipath-based CNNs (DenseNet121, ResNet50), Depth-based CNNs (Inceptio…

Learning to Look: Cognitive Attention Alignment with Vision-Language Models
Ryan L. Yang, Dipkamal Bhusal, Nidhi Rastogi
https://arxiv.org/abs/2509.21247 https://

Learning to Look: Cognitive Attention Alignment with Vision-Language Models
Convolutional Neural Networks (CNNs) frequently "cheat" by exploiting superficial correlations, raising concerns about whether they make predictions for the right reasons. Inspired by cognitive science, which highlights the role of attention in robust human perception, recent methods have sought to guide model attention using concept-based supervision and explanation regularization. However, these techniques depend on labor-intensive, expert-provided annotations, limiting their scalability. We …

Vision Transformers: the threat of realistic adversarial patches
Kasper Cools, Clara Maathuis, Alexander M. van Oers, Claudia S. H\"ubner, Nikos Deligiannis, Marijke Vandewal, Geert De Cubber
https://arxiv.org/abs/2509.21084

Vision Transformers: the threat of realistic adversarial patches
The increasing reliance on machine learning systems has made their security a critical concern. Evasion attacks enable adversaries to manipulate the decision-making processes of AI systems, potentially causing security breaches or misclassification of targets. Vision Transformers (ViTs) have gained significant traction in modern machine learning due to increased 1) performance compared to Convolutional Neural Networks (CNNs) and 2) robustness against adversarial perturbations. However, ViTs rem…

Audio-Visual Speech Enhancement: Architectural Design and Deployment Strategies
Anis Hamadouche, Haifeng Luo, Mathini Sellathurai, Tharm Ratnarajah
https://arxiv.org/abs/2508.08468

Audio-Visual Speech Enhancement: Architectural Design and Deployment Strategies
This paper introduces a new AI-based Audio-Visual Speech Enhancement (AVSE) system and presents a comparative performance analysis of different deployment architectures. The proposed AVSE system employs convolutional neural networks (CNNs) for spectral feature extraction and long short-term memory (LSTM) networks for temporal modeling, enabling robust speech enhancement through multimodal fusion of audio and visual cues. Multiple deployment scenarios are investigated, including cloud-based, edg…

Explain and Monitor Deep Learning Models for Computer Vision using Obz AI
Neo Christopher Chung, Jakub Binda
https://arxiv.org/abs/2508.18188 https://arxiv…

Explain and Monitor Deep Learning Models for Computer Vision using Obz AI
Deep learning has transformed computer vision (CV), achieving outstanding performance in classification, segmentation, and related tasks. Such AI-based CV systems are becoming prevalent, with applications spanning from medical imaging to surveillance. State of the art models such as convolutional neural networks (CNNs) and vision transformers (ViTs) are often regarded as ``black boxes,'' offering limited transparency into their decision-making processes. Despite a recent advancement in explaina…

Comparative Analysis of Attention Mechanisms for Automatic Modulation Classification in Radio Frequency Signals
Ferhat Ozgur Catak, Murat Kuzlu, Umit Cali
https://arxiv.org/abs/2508.09996

Comparative Analysis of Attention Mechanisms for Automatic Modulation Classification in Radio Frequency Signals
Automatic Modulation Classification (AMC) is a critical component in cognitive radio systems and spectrum management applications. This study presents a comprehensive comparative analysis of three attention mechanisms (i.e., baseline multi-head attention, causal attention, and sparse attention) integrated with Convolutional Neural Networks (CNNs) for radio frequency (RF) signal classification. It proposes a novel CNN-Transformer hybrid architecture that leverages different attention patterns to…

Hierarchical Graph Feature Enhancement with Adaptive Frequency Modulation for Visual Recognition
Feiyue Zhao, Zhichao Zhang
https://arxiv.org/abs/2508.11497 https://

Hierarchical Graph Feature Enhancement with Adaptive Frequency Modulation for Visual Recognition
Convolutional neural networks (CNNs) have demonstrated strong performance in visual recognition tasks, but their inherent reliance on regular grid structures limits their capacity to model complex topological relationships and non-local semantics within images. To address this limita tion, we propose the hierarchical graph feature enhancement (HGFE), a novel framework that integrates graph-based rea soning into CNNs to enhance both structural awareness and feature representation. HG…

SCRNet: Spatial-Channel Regulation Network for Medical Ultrasound Image Segmentation
Weixin Xu, Ziliang Wang
https://arxiv.org/abs/2508.13899 https://arxiv…

SCRNet: Spatial-Channel Regulation Network for Medical Ultrasound Image Segmentation
Medical ultrasound image segmentation presents a formidable challenge in the realm of computer vision. Traditional approaches rely on Convolutional Neural Networks (CNNs) and Transformer-based methods to address the intricacies of medical image segmentation. Nevertheless, inherent limitations persist, as CNN-based methods tend to disregard long-range dependencies, while Transformer-based methods may overlook local contextual information. To address these deficiencies, we propose a novel Feature…

ViT-FIQA: Assessing Face Image Quality using Vision Transformers
Andrea Atzori, Fadi Boutros, Naser Damer
https://arxiv.org/abs/2508.13957 https://arxiv.or…

ViT-FIQA: Assessing Face Image Quality using Vision Transformers
Face Image Quality Assessment (FIQA) aims to predict the utility of a face image for face recognition (FR) systems. State-of-the-art FIQA methods mainly rely on convolutional neural networks (CNNs), leaving the potential of Vision Transformer (ViT) architectures underexplored. This work proposes ViT-FIQA, a novel approach that extends standard ViT backbones, originally optimized for FR, through a learnable quality token designed to predict a scalar utility score for any given face image. The le…

Retrieval-Augmented VLMs for Multimodal Melanoma Diagnosis
Jihyun Moon, Charmgil Hong
https://arxiv.org/abs/2509.08338 https://arxiv.org/pdf/2509.08338

Retrieval-Augmented VLMs for Multimodal Melanoma Diagnosis
Accurate and early diagnosis of malignant melanoma is critical for improving patient outcomes. While convolutional neural networks (CNNs) have shown promise in dermoscopic image analysis, they often neglect clinical metadata and require extensive preprocessing. Vision-language models (VLMs) offer a multimodal alternative but struggle to capture clinical specificity when trained on general-domain data. To address this, we propose a retrieval-augmented VLM framework that incorporates semantically…

Boosted Training of Lightweight Early Exits for Optimizing CNN Image Classification Inference
Yehudit Aperstein, Alexander Apartsin
https://arxiv.org/abs/2509.08318 https://

Boosted Training of Lightweight Early Exits for Optimizing CNN Image Classification Inference
Real-time image classification on resource-constrained platforms demands inference methods that balance accuracy with strict latency and power budgets. Early-exit strategies address this need by attaching auxiliary classifiers to intermediate layers of convolutional neural networks (CNNs), allowing "easy" samples to terminate inference early. However, conventional training of early exits introduces a covariance shift: downstream branches are trained on full datasets, while at inference they pro…