Convolutional Neural Networks

Also known as CNN

Convolutional neural networks use shared filters to detect local patterns, then combine them across layers to classify, segment, or predict structured data such as images, video, audio, and sensor signals. Common approaches include residual networks and U-Net-style encoder–decoders, alongside depthwise, dilated, deformable, and input-adaptive convolutions; work also explores 1D and 3D convolutions, physics-informed losses, and quantization or pruning for efficient deployment. CNNs are tested on benchmarks ranging from ImageNet and CIFAR to medical scans, remote-sensing imagery, and time-series datasets, with attention to accuracy, speed, memory, calibration, and performance under domain shift. A central tension is that local convolutional structure can be efficient and data-effective, while some tasks benefit from broader context or attention, and strong benchmark results do not always ensure robust or clinically reliable behavior.

Latest papers

418 papers37 papers in the last four weeks, up 16% on the four weeks before. 0.2% of all new papers.

Attention Residual U-Net for Enhanced Cross-Dataset Polyp Localization in Endoscopy
Nov 2, 2026Romil Imtiaz, Dimitris K. IakovidisMedical Image Analysis Medical Image Localization
Department of Computer Science and Biomedical Informatics, University of Thessaly, Lamia, Greece
CNN-Based Retinal OCT Classification: Research Gap Analysis and a From-Scratch Baseline, ED126-A
Nov 1, 2026Shkelqim SherifiRetinal Disease Classification Optical Coherence Tomography
Dept. of Computer Science, University of Tetovo, Tetove, R.N.Macedonia
Systematic Evaluation of Robustness in Fine-tuned Models
Nov 1, 2026Angela John, Hamayoon BehmanushAdversarial Robustness Robust Classification
Saarland Informatics Campus, Saarland University
Structured Channel Network Pruning with Bi-Sparse Matrix Factorization
Oct 31, 2026Jingjing Liu, Ziyang Wang, Xianchao Xiu +1Channel Pruning Neural Network Pruning
School of Microelectronics, Shanghai Key Laboratory of Chips and Systems for Intelligent Connected Vehicle, Shanghai University, Shanghai 200444, China · State Key Laboratory of Integrated Chips and Systems, Fudan University, Shanghai 201203, China · School of Mechatronic Engineering and Automation, Shanghai University, Shanghai 200444, China +1
Does Vendor Image Processing Matter? Learning Echocardiography Display Appearance from Native Beamspace Data
Oct 30, 2026Elias Stenhede, Arian RanjbarUltrasound Imaging Echocardiography
Medical Technology & E-Health, Akershus University Hospital, Norway
Memorization Capacity of Invariant Convolutional Neural Nets
Oct 28, 2026Sjoerd Dirksen, Patrick Finke, Paul GeuchenNeural Network Memorization Convolutional Neural Networks
Mathematical Institute, Utrecht University, The Netherlands
Deep learning for non-transvenous ICD screening: tailored neural network architectures, extended experiments, and explainability
Oct 27, 2026Bartosz Morawski, Samuel J. Ward, Alex Touze +4Electrocardiography Convolutional Neural Networks
School of Mathematical Sciences, University of Southampton, UK · School of Human Development and Health, Faculty of Medicine, University of Southampton, UK · Department of Cardiology, University Hospital Southampton NHS Foundation Trust, Southampton, UK
FreqPKC: Frequency-Aware PeakConv for Radar Semantic Segmentation
Oct 24, 2026Yangyong Deng, Pengyu Zhang, Shaoqiu Song +2Semantic Segmentation Millimeter-Wave Radar
College of Electronic Science and Technology, National University of Defense Technology, Changsha, Hunan 410073, China.
How Robust Are CNNs and Vision Transformers for Alzheimer's MRI Classification Across Datasets?
Oct 24, 2026Hafija Aktar, Molly Croes, Frank S. Menniti +1Alzheimer's Disease Classification Cross-Dataset Generalization
Department of Computer Science, University of Rhode Island, Kingston, RI 02881, USA · Department of Biomedical and Pharmaceutical Sciences, George & Anne Ryan Institute for Neuroscience, University of Rhode Island, Kingston, RI 02881, USA
Automated Nucleus Segmentation in Histology Images: An Attention U-Net Approach with Comprehensive Preprocessing and Inference Pipelines
Oct 22, 2026Akshat G, Divyansh Gupta, Tusar Kanti MishraHistopathology Image Segmentation Convolutional Neural Networks
Manipal Institute of Technology Bengaluru, Manipal Academy of Higher Education, Manipal, India
The role of locality and weight sharing in convolutional neural networks
Oct 21, 2026Francesco Mori, Melanie WeberConvolutional Neural Networks Neural Network Training Dynamics
Center of Mathematical Sciences and Applications, Harvard University · John A. Paulson School of Engineering and Applied Sciences, Harvard University
FM-Occ: Feature-Diverse Upsampling and Memory-Aware Decoding for 3D Occupancy Prediction
Oct 21, 2026Yujia Zhai, Guoming Huang, Zhuanghuai Wang +13D Occupancy Prediction 3D Semantic Segmentation
Great Bay University
CNN-based classifier for subject-independent MBTI Extraversion/Introversion preference classification from short-time EEG signals
Oct 20, 2026Filip Postepski, Grzegorz M. WojcikConvolutional Neural Networks Cross-Subject EEG Decoding
Department of Neuroinformatics and Biomedical Engineering, Institute of Computer Science and Mathematics, Maria Curie-Sk lodowska University, Akademicka 9, Lublin, 20-031, Lubelskie, Poland.
Inferring continuous cognitive traits from limited neuroimaging data using pairwise convolutional neural networks
Oct 20, 2026Marjan Rashidi, Robert Bain, Craig Stark +3Neuroimaging Convolutional Neural Networks
Department of Cognitive Sciences, University of California, Irvine · Department of Neurobiology & Behavior, University of California, Irvine · Department of Psychological & Brain Sciences, University of California, Santa Barbara
Learning without relearning physical symmetry: an SO(3)-equivariant convolutional network (CNN) on the sphere
Oct 16, 2026Joshua Williamson, Niall Jeffrey, Lorne WhitewayEquivariant Neural Networks Convolutional Neural Networks
Department of Physics & Astronomy, University College London, Gower Street, London, WC1E 6BT, UK · Department of Physics & King’s Institute for Artificial Intelligence, King’s College London, Strand, London WC2R 2LS, United Kingdom
TAN: A Size- and Form-Adaptive Masked-Convolution Encoder for Tissue Graphs
Oct 16, 2026Jan Herschel, Anselm von GladissMedical Image Representation Learning Computational Pathology
Institute for Computer Science, University of Koblenz, Germany · MTI Mittelrhein, University of Koblenz, Germany
Missed Detections and False Alarms in a CNN Technosignature Detector on Breakthrough Listen Data
Oct 15, 2026Omer ImranRadio Astronomy Distribution Shift Robustness
Independent researcher
Data-Efficient ConvNeXt Pretraining for High-Resolution Sentinel-1 GRD SAR Representation Learning
Oct 15, 2026Yuki Natsume, Sang-Ho Yun, Chai Kiat YeoSelf-Supervised Pre-Training Masked Autoencoders
College of Computing and Data Science, Nanyang Technological University, Singapore · Earth Observatory of Singapore, Nanyang Technological University, Singapore · Asian School of the Environment, Nanyang Technological University, Singapore +1
Detection of Potato Plant Leaf Diseases using Convolutional Neural Networks
Oct 14, 2026Haimanot Bitew Alemayehu, Simachew Melaku Ayalew, Chilotie Desalew Mengesha +3Plant Disease Classification Convolutional Neural Networks
College of Engineering & Technology, Injibara University, Ethiopia
Resolution Allocation with Learnable Resizing and Spectral Filter Parameterization
Oct 14, 2026Wei Wu, Eric C. LarsonConvolutional Neural Networks Frequency-Domain Feature Learning
Department of Computer Science, Southern Methodist University, Dallas, TX, USA
On Making $\mathrm{SE}(2)$ -Invariant Networks Optimal
Oct 12, 2026Tomas Karella, Emily Shinkle, Alice Elisabeth Anastasia Allen +3Invariant Representation Learning Equivariant Neural Networks
CAI-3: Information Sciences Los Alamos National Laboratory · Machine Learning in Molecular Dynamics Max Planck Institute for Polymer Research · T-5: Applied Mathematics and Plasma Physics Los Alamos National Laboratory
Neural Network Preconditioning: A Case Study for the Solution of the Parametric Helmholtz Equation
Oct 12, 2026Luc Giraud, Carola Kruse, Paul Mycek +2PDE Solving Neural PDE Solvers
Inria, Concace joint team between Airbus CR&T, Cerfacs and Inria · Cerfacs, Concace joint team between Airbus CR&T, Cerfacs and Inria · Current affiliation: Opticalp +1
Memorization in image classification: test set behavior and scaling laws
Oct 12, 2026Jeevesh Attri, Florentin GuthNeural Network Memorization Neural Network Training Dynamics
Center for Data Science New York University · Center for Computational Neuroscience Flatiron Institute · Work done while partially affiliated with Center for Data Science, New York University.
RIECNN: Real-Time Image Enhanced CNN for Traffic Sign Recognition
Oct 10, 2026Reem Abdel-Salam, Rana Mostafa, Ahmed H. Abdel-GawadConvolutional Neural Networks Autonomous Driving Perception
Computer Engineering Department, Cairo University, Giza, Egypt
Region Aware Squeeze-and-Excitation Networks for Image Segmentation
Oct 10, 2026Jack Roberts, Praneeth Tummala, Kavi Sarna +1Channel Attention Image Segmentation
Department of Computer Science, Brown University, Providence, RI, USA · Department of Computer Science, Bowdoin College, Brunswick, ME, USA
Use Of Convolutional Neural Networks In Detection Of Branch Dieback Disease In Pequi Trees
Oct 10, 2026Ronilson Rodrigues Pinho, Elua Ramos Coutinho, Nilza de Lima Pereira Sales +2Plant Disease Classification Convolutional Neural Networks
Federal University of Rio de Janeiro – UFRJ- Institute of Computing – IC - Postgraduate Program in Informatics - PPGI- Rio de Janeiro, 20010-974, Brazil · Federal Center for Technological Education Celso Suckow da Fonseca- CEFET-RJ-BSI- Rio de Janeiro, RJ, 20785-220, Brazil · Fluminense Federal University – UFF - Instituto de Ciência e Tecnologia – Rio das Ostras - RJ - 28895-532, Brazil +1
Layer-wise Input Recoverability in Deep Neural Networks
Oct 9, 2026Maxwell Spiridonov, Alireza Rahmansetayesh, Pierre BaldiConvolutional Neural Networks Neural Network Interpretability
Department of Computer Science, University of California, Irvine
SADL: A Size-Adaptive Decision Layer for Chronic Stroke Lesion Segmentation in ISLES 2026
Oct 9, 2026Marek Wodzinski, Gniewosz Drwiega, Wojciech SzymanskiMedical Image Segmentation Convolutional Neural Networks
Sano – Centre for Computational Personalised Medicine International Research Foundation, Krakow, Poland · AGH University of Krakow, Krakow, Poland
Mesh-Native Tokenisation: Retrofitting Foundation Models to Unstructured Data
Oct 8, 2026Georg Maierhofer, Miles Cranmer, Payel MukhopadhyayPhysical Foundation Models Convolutional Neural Networks
University of Cambridge
SV-TAD: Native Sparse Convs for Efficient Temporal Action Detection
Oct 8, 2026Ricardo Pizarro, Roberto Valle, José M. Buenaposada +2Temporal Action Detection Efficient ViTs
Universidad de Alcal´a, Alcal´a de Henares, Spain · Universidad Polit´ecnica de Madrid, Madrid, Spain · Universidad Rey Juan Carlos, M´ostoles, Spain

Nov 2, 2026J/K move · Enter open · S save

Attention Residual U-Net for Enhanced Cross-Dataset Polyp Localization in Endoscopy

Romil Imtiaz, Dimitris K. Iakovidis

Department of Computer Science and Biomedical Informatics, University of Thessaly, Lamia, Greece

Medical Image Analysis Medical Image Localization Endoscopy Convolutional Neural Networks Cross-Dataset Generalization

Open paper AskPDF arXiv

Precise localization of pathologies in endoscopy is a critical task in medical imaging, with deep learning (DL) frameworks now serving as the primary methodology for automated lesion detection. Today, generic object detection methods, such as YOLO, provide state-of-the-art performance in this context. However, their robustness often decreases under real-world clinical conditions due to variations across endoscopic devices, intestinal content, dataset bias, and the presence of small or low-contrast lesions. Motivated by these challenges, we propose a novel polyp detection framework based on a Attention Residual U-Net offering enhanced polyp localization. Instead of directly regressing bounding boxes from global feature representations, the proposed method learns lesion-focused spatial representations and converts them into bounding-box predictions during inference. Unlike conventional encoder-decoder localization frameworks that directly propagate all encoder activations into the decoding pathway, the proposed method selectively suppresses irrelevant background responses before feature reconstruction. This encourages the network to focus on lesion-relevant spatial evidence under heterogeneous imaging conditions. To achieve this, the framework integrates residual feature propagation, attention-guided encoder filtering, and multi-scale contextual learning. The proposed framework was evaluated on multiple public endoscopic datasets acquired using different devices. The comparative experimental results validate its effectiveness over the relevant state-of-the-art methods, with an improvement up to 22.0% in terms of the area under the receiving operating characteristic (AUC).