Vision Transformer

Also known as ViT

Follow this topic Ask about this topic

Latest papers 351

50 papers in the last four weeks, up 39% on the four weeks before. 0.3% of all new papers.

All topics

Vertical Fusion: Condensing Internal Representations for Robust ViT Classification
Jul 11, 2026Francesco Di Salvo, Shyam Nandan Rai, Hamed Damirchi +4Vision Transformer Image Classification
University of Bamberg, Bamberg, Bavaria, Germany · AIML, The University of Adelaide, Adelaide, South Australia, Australia
Gradient-Skipping Relevance Propagation for Efficient Explainability of Vision Transformers
Jul 11, 2026Christopher Buratti, Michele Marchetti, Federica Parlapiano +3Transformer Interpretability Vision Transformer
DII, Polytechnic University of Marche · CHIMOMO, University of Modena and Reggio Emilia
ScratNet: A Swin-Based Multi-Scale Dilated Network with Precision Refinement for Semiconductor Scratch Segmentation
Jul 11, 2026Sachin Ranjan, Hoon KimImage Segmentation Vision Transformer
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
Subtoken Vision Transformer for Fine-grained Recognition
Jul 10, 2026Jie Zhu, Ivy Zhang, Minchul Kim +1Vision Transformer Visual Tokenization
Michigan State University · Cranbrook Kingswood School · University of North Carolina at Chapel Hill
Vision Transformers Learn Gestalt-Like Figure-Ground Cues from Natural Images
Jul 9, 2026Matthias Tangemann, Benjamin Lo, Zygmunt Pizlo +3Visual Representation Learning Vision Transformer
University of Toronto · 2Vector Institute · 3McGill University +2
Texture Representations in Deep Vision Models: Comparing CNNs, Vision Transformers, and Human Perception
Jul 9, 2026Ludovica de Paolis, Marco Baroni, Alessandro Laio +1Visual Representation Learning Vision Transformer
Department of Neuroscience, International School for Advanced Studies (SISSA), Trieste, Italy · Department of Language and Translation Sciences, Pompeu Fabra University, Barcelona, Spain · ICREA, Barcelona, Spain +1
Adversarial Decoys: Misdirecting Attention-Based Defenses in ViT
Jul 8, 2026Giulia Marchiori Pietrosanti, Giulio Rossolini, Giorgio ButtazzoAdversarial Patch Attacks Adversarial Attacks
Department of Excellence in Robotics and AI, Sant’Anna School of Advanced Study, Italy
AA-ViT: Anatomically Aware Vision Transformer with Structural and Frequency Guidance for Contrast Enhanced Brain MRI Synthesis
Jul 8, 2026Talha Meraj, Tom Flannery, Charlie Cummins +6Vision Transformer Medical Image Synthesis
Department of Computing and Electronic Engineering, Atlantic Technological University, Sligo, Ireland · Mathematical Modelling and Intelligent Systems for Health and Environment (MISHE), Faculty of Engineering and Design, Atlantic Technological University, Sligo, Ireland · JANUS Research Centre, Atlantic Technological University, Letterkenny, Ireland +5
Rethinking Depth Pruning for Vision Transformers: A Heterogeneity-Aware Perspective
Jul 4, 2026Zhenfeng Su, Kang Zhao, Han Bao +4Vision Transformer Efficient ViTs
School of Data Science, The Chinese University of Hong Kong, Shenzhen, China · Huawei Technologies Co., Ltd., Shenzhen, China · Tsinghua University, Beijing, China +1
When Geometry Aligns: Dihedral Hidden-State Transformations in UNet, ViT, and DiT Architectures
Jul 3, 2026Mojtaba Faramarzi, Alex Lamb, Irina RishDiffusion Transformer Vision Transformer
University of Montreal, Canada · Mila - Quebec AI Institute · Tsinghua University +1
Beyond Post-Quantization: Native Hash Learning with a Dedicated HASH Token
Jul 3, 2026Xinze Liu, Ding Wang, Hengjie Zhu +1Vision Transformer Image Retrieval
Institute of Information Engineering, CAS, Beijing 100190, China · School of Cyber Security, University of Chinese Academy of Sciences, Beijing 100190, China · Department of Applied Mathematics and Statistics, Johns Hopkins University, Baltimore, Maryland 21218, USA
Transformer Geometry Observatory TGO-II: Representational Similarity Observatory
Jul 2, 2026Kaustubh Kapil, Kishor P. UplaIntrinsic Dimensionality Representational Similarity Analysis
Department of Electronics Engineering Sardar Vallabhai National Institute of Technology (SVNIT), Surat, India
When Token Compression Breaks: Structural Pruning vs. Token Reduction for Robust ViT Segmentation under High Compression
Jul 2, 2026Tien-Phat Nguyen, Ngai-Man CheungDistribution Shift Robustness Vision Transformer
Temasek Laboratories, Singapore University of Technology and Design, Singapore
Understanding Geometric Representations in Self-Supervised Vision Transformers via Subspace Intervention
Jul 2, 2026Weichen Zhou, Yawen Zou, Chunzhi Gu +3Neural Representation Geometry Linear Probing
University of Toyama, Toyama, Japan · University of Fukui, Fukui, Japan · Chukyo University, Aichi, Japan +1
DRDN: Decoupled Representation Dynamic Network for From-Scratch ViT Class-Incremental Learning
Jul 2, 2026Bingchen Huang, Yifu Chen, Zhiling Wang +1Class-Incremental Learning Vision Transformer
Meituan Vision AI Department, Beijing 100190, China
Mirror-Fusion Attention for Reflection-Aware Self-Supervised Representation Learning
Jul 1, 2026Ruixin Li, Jin Liu, Yuling Shi +1Representation Learning Vision Transformer
Department of Computer Science and Engineering, University of Bologna, Bologna, Italy · Jilin University, Changchun, China · Shanghai Jiao Tong University, Shanghai, China
Soft Mixture-of-Recursions: Going Deeper with Recursive Vision Transformers
Jul 1, 2026Sang In Lee, Jihun ParkVision Transformer Recurrent Transformers
Chungnam National University Daejeon, South Korea
Active Spatial Guidance: Eliminating Injected Positional Mechanisms in Vision Transformers
Jul 1, 2026Cong Liu, Xiaofang Li, Simon X. YangVision Transformer
School of Engineering, Yancheng Institute of Technology, No. 1 Xiwang Middle Avenue, Yancheng, 224051, Jiangsu, PR China · School of Computer Information Engineering, Changzhou Institute of Technology, No. 666 Liaohe Road, Xinbei District, Changzhou, 213032, Jiangsu, PR China · Advanced Robotics and Intelligent Systems Laboratory, School of Engineering, University of Guelph, 50 Stone Road East, Guelph, N1G 2W1, Ontario, Canada
Does Your ViT Still Need U-Net for Segmentation?
Jun 30, 2026Xin Li, Wenhui Zhu, Xuanzhao Dong +6Vision Transformer U-Net
Arizona State University, Tempe, AZ, USA · Clemson University, Clemson, SC, USA · Mayo Clinic, Scottsdale, AZ, USA
Reweighting Framewise Attention in Video Transformers for Facial Expression Understanding
Jun 29, 2026Seongro Yoon, Donghyeon Cho, Jinsun Park +1Vision Transformer Facial Expression Recognition
Inria, Université Côte d’Azur, France · Hanyang University, South Korea · Pusan National University, South Korea
CLEAR-MoE: Shared-Basis Expert Extraction from Frozen Vision Transformers via Calibration-Driven Layer Selection
Jun 26, 2026Md Irtiza Hossain, Humaira Ayesha, Junaid Ahmed SifatVision Transformer Low-Rank Matrix Decomposition
Brac University
A Unified Framework for Vision Transformers Equivariant to Discrete Subgroups of $\mathrm{O}(2)$
Jun 26, 2026Tīkun Ông, Georg BökmanVision Transformer Equivariant Neural Networks
Independent Researcher · University of Amsterdam
DnA: Denoising Attention for Visual Tasks
Jun 25, 2026Ron Campos, Subhajit Maity, Xin Li +2Visual Attention Vision Transformer
University of Central Florida, USA · University of North Carolina at Charlotte, USA
Layer-Specific Prompt Fusion Discovery via Differentiable Search in Vision Foundation Models
Jun 24, 2026Xi Xiao, Xingjian Li, Yunbei Zhang +7Vision Transformer Vision Foundation Model Adaptation
UAB · CMU · Tulane +3
REViT: Roto-reflection Equivariant Convolutional Vision Transformer
Jun 24, 2026Sheir A. Zaheer, Alexander C. Holston, Chan Y. ParkVision Transformer Equivariant Neural Networks
1KC Machine Learning Lab, Seoul, Rep. of Korea.
Adaptive Hebbian Memory Routing in Vision Transformers for Few-Shot Learning
Jun 23, 2026Mohammed Yusuf Mujawar, Noorbakhsh Amiri GolilarzHebbian Learning Vision Transformer
Department of Computer Science The University of Alabama, Tuscaloosa, AL, USA
TuringViT: Making SOTA Vision Transformers Accessible to All
Jun 23, 2026Qiman Wu, Hanlin Chen, Lyujie Chen +19Vision Foundation Models Vision Transformer
Foundation Model Team, Xpeng Inc.
UniverSat: Resolution- and Modality-Agnostic Transformers for Earth Observation
Jun 22, 2026Yohann Perron, Guillaume Astruc, Nicolas Gonthier +2Geospatial Representation Learning Vision Transformer
LIGM, Ecole Nationale des Ponts et Chaussées, IP Paris, Univ Gustave Eiffel, CNRS · EFEO · LASTIG, Univ Gustave Eiffel, IGN, ENSG +2
IViT: A Novel Interpretable Visual Transformer for Skin Disease Detection
Jun 22, 2026Haibiao Li, Di Lin, Xue Jiang +3Skin Lesion Classification Vision Transformer
School of Information and Software Engineering, University of Electronic Science and Technology of China, Chengdu, Sichuan, 610054, P. R. China · Department of Dermatology, Chongqing Traditional Chinese Medicine Hospital, Chongqing, 400021, P. R. China · Chongqing Health Center for Women and Children, Chongqing, 400013, P. R. China
Performance and Interpretability of Convolutional, Transformer, and Hybrid Deep Learning Models in Colorectal Histology Classification
Jun 21, 2026Reza BozorgpourHybrid CNN-Transformer Architectures Vision Transformer
College of Engineering & Applied Science, Department of Biomedical Engineering, University of Wisconsin-Milwaukee, Milwaukee, WI, USA

Jul 11, 2026J/K move · Enter open · S save

Vertical Fusion: Condensing Internal Representations for Robust ViT Classification

Francesco Di Salvo, Shyam Nandan Rai, Hamed Damirchi, Ignacio Meza De la Jara+3

University of Bamberg, Bamberg, Bavaria, Germany · AIML, The University of Adelaide, Adelaide, South Australia, Australia

Vision Transformer Image Classification

Open paper AskPDF arXiv

Despite exposing rich intermediate representations, Vision Transformers (ViTs) are almost exclusively utilized as black-box feature extractors, where only the last layer is considered for downstream tasks. We challenge this convention by introducing the notion of recoverability: the capacity of intermediate representations to correct last-layer failures. By evaluating independent classification probes at every model depth across 16 datasets, we observe that intermediate probes correctly classify 18% to 76% of samples that the last-layer probe misclassifies. We show that these gains are not primarily driven by predictive diversity, but by a redundancy-correctness correspondence, where the internal hierarchy acts as a series of stable, redundant probes of a shared discriminative signal. While established horizontal ensemble strategies (i.e., across multiple models) can improve performance, they incur high computational cost and ignore this vertical signal within a single model. To bridge this gap, we propose VFusion, a principled vertical aggregation strategy employing a learnable mapping into a low-dimensional latent space that synthesizes features across the internal ViT hierarchy. VFusion substantially outperforms established aggregation baselines in both in-distribution and out-of-distribution settings, notably closing 45% of the accuracy gap between the best individual layer and a theoretical oracle performance. Our gains consistently generalize across model sizes and pre-training regimes, confirming that VFusion offers a robust and efficient alternative to horizontal ensemble methods. The code is available at https://github.com/francescodisalvo05/vit-vertical-fusion.