Swin

Follow this topic Ask about this topic

Momentum

2 papers in the last four weeks, against 2 the four weeks before. 0.0% of all new papers.

Jul 13Week of Sep 28

Latest papers 28

All topics

Masked Swingers: Harnessing Data Augmentation to Advance Autoencoders for Self-Supervised Learning
Sep 29, 2026Anthony Fuller, Scott C. Lowe, Daniel G. Kyrollos +3Self-Supervised Learning Autoencoder Architectures
Vector Institute · Carleton University · University of Guelph +1
4D Parallelism Unlocks Exascale Bayesian Neural Networks for High-Fidelity Atmospheric Modeling
Sep 14, 2026Deifilia Kieckhefen, Juan Pedro Gutiérrez Hermosillo Muriedas, Lars Helge Heyen +12Atmospheric Dynamics Bayesian Neural Networks
Karlsruhe Institute of Technology, Germany · Forschungszentrum Jülich, Germany · CSC – IT Center for Science Ltd., Finnland +1
Swin Meets EfficientNet: Lightweight Architectures for GAN-Based Face Forensics
Sep 1, 2026Sejuti Basu, Ashima Sood, Vijay Kumar +1Facial Images Generative Adversarial Network
International Institute of Information Technology, Bangalore, India · School of Computing, Engineering, and Intelligent Systems, Ulster University, Londonderry, United Kingdom · Department of Information Technology, Dr B R Ambedkar National Institute of Technology Jalandhar, Punjab, India
Federated Multi-Task Learning for Bladder Tumor Segmentation and MIBC Classification Using a Hybrid CNN-Transformer Architecture
Aug 31, 2026Malhar Udmale, Divyanshu Dwivedi, Aarohi Dhand +3Tumor Segmentation Hybrid Transformer
Indian Institute of Information Technology Allahabad, Prayagraj, India · Manipal University Jaipur, Jaipur, India · Norwegian University of Science and Technology, Trondheim, Norway
Multimodal Skin Lesion Classification with Swin Transformer and Clinical Metadata Fusion
Aug 4, 2026Nethmi Pathirana, Isuru Munasinghe, Dileeka AlwisSkin Lesion Classification Lesion Segmentation
School of Computing, Informatics Institute of Technology, Colombo, Sri Lanka · Department of Electronic and Telecommunication Engineering, University of Moratuwa, Katubedda, Sri Lanka
Food Image Segmentation with LLM-Derived Ingredient Labels and Multimodal Fusion
Jul 28, 2026Jui-Feng Chi, Wei-Ta Chu, Sheng-Long LinMultimodal Fusion Swin
National Cheng Kung University, Tainan, Taiwan
Post-Operative Glioma Segmentation via Loss Stabilization, Normalization and Subspace Attention
Jul 23, 2026Alexandru Crişan, Diana BorzaBrain Tumor Segmentation Swin
Babes-Bolyai University, Cluj-Napoca, Romania
AI-Driven Surrogate Models for Predicting Electrode-Scale Discharge Behavior in Lithium-Ion Batteries
Jul 22, 2026Mengda Xing, Jean-Marie Lagniez, Alejandro FrancoLithium-Ion Batteries Surrogate Models
CRIL, UA · CRIL, UMR 8188, Université d’Artois, Rue Jean Souvraz SP 18, F-62307 Lens Cedex, France · LRCS +1
SwinAD: Multi-stage feature reconstruction for unsupervised industrial anomaly detection
Jul 16, 2026Huong Ninh, Chien Thai, Mai Xuan Trang +3Multimodal Industrial Anomaly Detection Graph Anomaly Detection
Institute of Artificial Intelligence, University of Engineering and Technology, Vietnam National University · Applied AI Lab, Phenikaa School of Computing, Phenikaa University
Self-supervised training for high-resolution close-range multispectral remote sensing imagery
Jul 13, 2026Leon-Friedrich Thomas, Mikael Änäkkälä, Antti LajunenSwin Remote Sensing
University of Helsinki, Department of Agricultural Sciences, P.O. Box 28, Fi-00014 Helsinki, Finland · University of Helsinki, Department of Forest Sciences, P.O. Box 27, Fi-00014 Helsinki, Finland
ScratNet: A Swin-Based Multi-Scale Dilated Network with Precision Refinement for Semiconductor Scratch Segmentation
Jul 11, 2026Sachin Ranjan, Hoon KimMulti-Scale Convolution Defect Detection
Machine Intelligence and Data Science (MINDS) Lab and the M.S. Program in Electronics Engineering, Incheon National University, Incheon 22012, South Korea · Machine Intelligence and Data Science (MINDS) Lab and the Department of Electronics Engineering, Incheon National University, Incheon 22012, South Korea
CSWinUNETR: Segmentation of Thin Anatomical Structures in Medical Images
Jun 18, 2026Junho Moon, Haejun Chung, Ikbeom JangVessel Segmentation U-Net
Hanyang University, Seoul, Republic of Korea · Hankuk University of Foreign Studies, Yongin, Republic of Korea
Diffusion-Refined Segmentation and Vision-Language Interpretation for Pediatric Brain Tumor MRI
Jun 12, 2026Wentao Ke, Jianche LiuBrain Tumor Segmentation Magnetic Resonance Imaging
Department of Mechanical Engineering Stanford University · School of Medicine Stanford University
Transformer-Guided Graph Attention for Direct Cardiac Mesh Reconstruction: A Structural Digital Twin Framework
Jun 11, 2026Abhishek H S, Akash Ganamukhi, Abhimanyu Suresh +3End-To-End 4D Heart Mesh Recovery Across Full-Stack Swin
CAVE Labs, C-IoT, Dept. of CSE, PES University · C-IoT, Dept. of CSE, PES University
An Attention-Based Denoising Model for Diffusion Weighted Imaging
Jun 2, 2026Prithviraj Verma, Pawan Kumar, Chandan Deshani +1Swin
Institute of Infrastructure Technology Research and Management (IITRAM), India · University of Sheffield, United Kingdom
Efficient Transformer-Based Localized Patch Sampling for Choroid Plexus Segmentation in Multiple Sclerosis
Jun 2, 2026Po-Jui Lu, Alessandro Cagol, Mario Ocampo-Pineda +12Multiple Sclerosis Swin
Translational Imaging in Neurology (ThINk) Basel, Department of Biomedical Engineering, Faculty of Medicine, University Hospital Basel and University of Basel, Basel, Switzerland · Department of Neurology, University Hospital Basel, Basel, Switzerland · Research Center for Clinical Neuroimmunology and Neuroscience Basel (RC2NB), University Hospital Basel and University of Basel, Basel, Switzerland +4
SwInception -- Local Attention Meets Convolutions
May 28, 2026David Hagerman, Roman Naeem, Jakob Lindqvist +3Swin Self-Supervised Vision Transformers
Chalmers University of technology, 412 96 Gothenburg, Sweden · Zenseact, Lindholmspiren 2, 417 56 Gothenburg, Sweden
Not All NVFP4 QAT Recipes Are Equal: How Architecture and Scale Shape Model Quality for Anomaly Segmentation
May 26, 2026Zijian Du, Oleg RybakovQuantization-Aware Training Swin
NVIDIA
Geometry-Aware Contrastive Learning for Few-Shot Automatic Modulation Recognition
May 26, 2026Guanqun Zhao, Yitong Liu, Jiaxuan Fang +2Contrastive Learning Frequency-Aware Regularization
Beijing University of Posts and Telecommunications, Beijing, China
Exploring deep learning for Event-Based Saliency Prediction with a Transformer-based model
May 22, 2026Romaric Mazna, Jean Martinet, Sai Deepesh PokalaSaliency Swin
1i3S/CNRS, Université Côte d’Azur
Benchmarking transferability of SSL pretraining to same and different modality segmentation tasks
May 18, 2026Jue Jiang, Harini VeeraraghavanSwin Amodal Segmentation
Department of Medical Physics, Memorial Sloan Kettering Cancer Center
Long-horizon prediction of three-dimensional wall-bounded turbulence with CTA-Swin-UNet and resolvent analysis
May 18, 2026Bo Chen, Yitong Fan, Jie Yao +1Turbulent Flows Long-Horizon Forecasting
School of Aeronautics and Astronautics, Shanghai Jiao Tong University, Shanghai 200240, China · School of Interdisciplinary Science, Beijing Institute of Technology, Beijing 100081, China
On Privacy-Preserving Image Transmission in Low-Altitude Networks: A Swin Transformer-Based Framework with Federated Learning
May 12, 2026Kexin Zhang, Lixin Li, Yuna Yan +5Unmanned Aerial Vehicles Semantic Communications
School of Electronics and Information, Northwestern Polytechnical University, Xi’an 710129, China · DecoreX Intelligent Technologies Co., Ltd., Xi’an 710075, China · Samsung AI Center, Cambridge CB1 2JH, UK +2
Spatial-Frequency Gated Swin Transformer for Remote Sensing Single-Image Super-Resolution
May 10, 2026Md Aminur Hossain, Parekh Valkesh, Ayush V. Patel +3Hyperspectral Image Super-Resolution Real-World Image Super-Resolution
Space Applications Centre, ISRO, Ahmedabad, India · New L J Institute of Engineering and Technology, Ahmedabad, India · Pandit Deendayal Energy University, Gandhinagar, India +2
InfiltrNet: Dual-Branch CNN-Transformer Architecture for Brain Tumor Infiltration Risk Prediction
May 4, 2026S M Asif Hossain, Shruti KshirsagarBrain Tumor Segmentation Brain Tumor Classification
School of Computing, Wichita State University, Wichita, Kansas, USA
Co-distilled attention guided masked image modeling with noisy teacher for self-supervised learning on medical images
Apr 16, 2026Jue Jiang, Aneesh Rangnekar, Harini VeeraraghavanSemi-Supervised Medical Image Segmentation Swin
Memorial Sloan Kettering Cancer Center
Comparison of Image Processing Models in Quark Gluon Jet Classification
Jan 29, 2026Daeun Kim, Jaeyoon Cho, Jiwon Lee +5Swin Contrastive Learning
Department of Physics, Inha University, Incheon, Republic of Korea
SwinIFS: Landmark Guided Swin Transformer For Identity Preserving Face Super Resolution
Jan 4, 2026Habiba Kausar, Saeed Anwar, Omar Jamal Hammad +1Generative Super-Resolution Blind Face Restoration
King Fahd University of Petroleum and Minerals, KSA · The University of Western Australia, Australia · The University of Regina, Canada

Sep 29, 2026, cs.CVJ/K move · Enter open · S save

Masked Swingers: Harnessing Data Augmentation to Advance Autoencoders for Self-Supervised Learning

Anthony Fuller, Scott C. Lowe, Daniel G. Kyrollos, Graham W. Taylor+2

Vector Institute · Carleton University · University of Guelph+1

Self-Supervised Learning Autoencoder Architectures Swin Data Augmentation

Open paper AskPDF arXiv

Self-supervised learning (SSL) removes the need for annotations and makes models that are capable across more domains than supervised learning. The autoencoder SSL framework learns by reconstructing its own input after information loss through a bottleneck or noise injection. Masked autoencoders (MAE) are the most successful instantiation of this framework: they encode a random subset of patches, then decode the masked-out patches. In this work, we introduce key modifications to improve MAEs. Our method augments an image in two different ways, then masks and encodes each view separately. It then exchanges the global representations (CLS tokens) between views before decoding the masked patches. By design, our Masked Swingers encourages learning a view-agnostic summary of the image to facilitate efficient transfer. We perform extensive experiments, and find Masked Swingers outperforms MAE by +3-5% on ImageNet-1K kNN and provides large gains on fine-grained tasks, e.g., relative gains of +45% on instance retrieval, +22% on animal re-ID, and +76% on Omniglot character recognition. To boot, Swingers reduces error -64% relative to MAE on three new state-probing datasets, opening the door to world modeling. Welcome to our Swingers party.

Momentum

Related topics

Latest papers 28