Vision Transformer

Also known as ViT

Ask about this topic

Overview

Vision Transformers divide images into patches and use self-attention to model relationships across them, supporting tasks from image classification to dense prediction and video understanding. Common approaches include supervised or self-supervised pretraining, hierarchical and local-global attention, and adaptation through fine-tuning, prompts, or lightweight adapters. Work also explores faster inference through token pruning, merging, quantization, and efficient attention, alongside interpretability and robustness tests on benchmarks such as ImageNet, COCO, and ADE20K. A central tension is that global context and flexible representations can come with high data and compute demands, while stronger spatial priors or compression may improve efficiency but affect transfer and fine detail.

Latest papers

CardsList

375 papers33 papers in the last four weeks, down 25% on the four weeks before. 0.2% of all new papers.

  1. Attentive multilayer fusion for vision transformers

    Jan 14, 2026Laure Ciernik, Marco Morik, Lukas Thede +4Linear ProbingVision Transformer

    Machine Learning Group, Technische Universität Berlin, Berlin, Germany · Hector Fellow Academy, Karlsruhe, Germany · Berlin Institute for the Foundations of Learning and Data (BIFOLD), Berlin, Germany +7

  2. CLARiTy: A Vision Transformer for Multi-Label Classification and Weakly-Supervised Localization of Chest X-ray Pathologies

    Dec 18, 2025John M. Statheros, Hairong Wang, Richard KleinChest X-Ray ClassificationMedical Image Localization

    School of Computer Science and Applied Mathematics, University of the Witwatersrand, Johannesburg, South Africa

  3. The Inductive Bottleneck: Data-Driven Emergence of Representational Sparsity in Vision Transformers

    Dec 8, 2025Kanishk AwadhiyaRepresentation LearningVision Transformer

    Indian Institute of Technology, Delhi

  4. Unifying Convolution and Attention via Convolutional Nearest Neighbors

    Nov 18, 2025Mingi Kang, Jeová Farias Sales Rocha NetoHybrid CNN-Transformer ArchitecturesSelf-Attention

    Bowdoin College

  5. Patch Rebirth: Fast and Transferable Model Inversion of Vision Transformers

    Sep 27, 2025Seongsoo Heo, Dong-Wan ChoiVision TransformerInverse Problems

    Inha University

  6. Interpreting vision transformers via residual replacement model

    Sep 22, 2025Jinyeong Kim, Junhyeok Kim, Yumin Shim +3Transformer InterpretabilityVision Transformer

    Yonsei University

  7. Geometrically Constrained and Token-Based Probabilistic Spatial Transformers

    Sep 14, 2025Johann Schmidt, Tom Siegl, Martin Becker +1Vision TransformerImage Classification

    Artificial Intelligence Lab, Otto-von-Guericke University Magdeburg, Germany · University of Rostock, Germany · Becker Lab, University of Marburg, Germany

  8. Post-Disaster Affected Area Segmentation with a Vision Transformer (ViT)-based EVAP Model using Sentinel-2 and Formosat-5 Imagery

    Jul 21, 2025Yi-Shan Chu, Hsuan-Cheng WeiRemote Sensing Image UnderstandingWeakly Supervised Image Segmentation

    Department of Mathematical Science, National Chengchi University, Taipei, Taiwan · Division of Satellite Data Application, Taiwan Space Agency, Hsinchu, Taiwan · Institute of Statistical Science, Academia Sinica, Taipei, Taiwan

  9. Enhancing Self-Supervised Visual Representation Learning via Low-Rank Adapted LLMs

    Jul 1, 2025Selim Kuzucu, Muhammad Ferjad Naeem, Anna Kukleva +2Vision TransformerSelf-Supervised Visual Representation Learning

    Max Planck Institute for Informatics, SIC · Google

  10. GViT: Representing Images as Gaussians for Visual Recognition

    Jun 30, 2025Jefferson Hernandez, Ruozhen He, Guha Balakrishnan +2Image ClassificationVisual Representation Learning

    Rice University · University of California, Irvine

  11. Unlocking Pretrained Vision Transformers for Time Series Classification

    Jun 10, 2025Simon Roschmann, Quentin Bouniot, Vasilii Feofanov +2Time Series ClassificationVision Transformer

    Helmholtz Munich · Technical University of Munich · Munich Center for Machine Learning +2

  12. SEMA: a Scalable and Efficient Mamba like Attention via Token Localization and Averaging

    Jun 10, 2025Nhat Thanh Tran, Fanghui Xue, Shuai Zhang +4Self-AttentionVision Transformer

    Department of Mathematics; University of California, Irvine; Irvine, CA 92697, USA · Qualcomm AI Research; San Diego, CA 92121, USA

  13. Quick ViTs: Speeding up Vision Transformers through Equivariance

    May 21, 2025David Nordström, Johan Edstedt, Fredrik Kahl +1Vision TransformerEquivariant Neural Networks

    Chalmers University of Technology · Linköping University · University of Amsterdam

  14. Hierarchical Vision Transformer with Prototypes for Interpretable Medical Image Classification

    Feb 13, 2025Luisa Gallée, Meinrad Beer, Michael GötzMedical Image ClassificationExplainable Medical Image Analysis

    Experimental Radiology, Ulm University Medical Center, Germany · XAIRAD - Cooperation for Artificial Intelligence in Experimental Radiology, Germany · Department of Diagnostic and Interventional Radiology, Ulm University Medical Center, Germany +2

  15. Understanding Transformer-Based Vision Models via Modular Feature Inversion

    Dec 9, 2024Jan Rathjens, Shirin Reyhanian, David Kappel +1Transformer InterpretabilityVision Transformer

    Institute for Neural Computation Faculty of Computer Science Ruhr University Bochum · Center for Cognitive Interaction Technology Faculty of Technology Bielefeld University