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

Positional Encodings Anchor Spatial Structure in Vision Transformers: A Geometric Perspective on Robustness
May 28, 2026Mahmoud MannesDistribution Shift Robustness Vision Transformer
ESSTHS
Parameter-Efficient Subspace Decoupling ViT for Mitigating Multi-Task Negative Transfer in Histological Scoring
May 28, 2026Youhan Huang, Jiajun Li, Yilin Fang +2Vision Transformer Multi-Task Learning
1Beijing University of Posts and Telecommunications, Beijing, China · 2Beijing University of Chemical Technology, Beijing, China · 3Capital Medical University, Beijing, China
AI for Maritime Security: Comparative Evaluation of CNN and Vision Transformer Architectures for Maritime Object Detection
May 28, 2026Ismet Gocer, Zakirul Bhuiayn, Shakeel Ahmad +1Vision Transformer Object Detection
Southampton Solent University School of Technology and Maritime Industries Southampton, United Kingdom
Unsupervised Semantic Segmentation Facilitates Model Understanding
May 28, 2026Xiaoyan Yu, Lisa Mais, Jannik Franzen +4Transformer Interpretability Vision Transformer
Max-Delbrück-Center (MDC), Berlin, Germany · Helmholtz Imaging · Humboldt-Universität zu Berlin, Berlin, Germany +2
Is an Image Also Worth 16x16=256 Superpixels? A Framework for Attentional Image Classification
May 26, 2026Pedro Henrique da Costa Avelar, Anderson R. Tavares, Luís C. LambGraph Attention Networks Vision Transformer
ufrgs · uom
AdaMerge: Salience-Aware Adaptive Token Merging for Training-Free Acceleration of Vision Transformers
May 26, 2026Semi Lee, Hyejin Go, Hyesong ChoiToken Merging Self-Attention
Electronic Engineering · Soongsil University · Seoul, South Korea
CNNs, Transformers, Hybrid, and Vision Language Models for Skin Cancer Detection
May 25, 2026Durjoy Dey, Yuhong Yan, Hassan HajjdiabHybrid CNN-Transformer Architectures Vision Transformer
Department of Computer Science and Software Engineering, Concordia University, Montreal, Canada · Ebovir Biotechnologie Inc., Montreal, Canada
Benchmarking Convolutional, Transformer, Hybrid, and Vision Language Models for Multi Disease Retinal Screening
May 25, 2026Durjoy Dey, Aymane Ajbar, Yuhong YanHybrid CNN-Transformer Architectures Vision Transformer
Department of Computer Science and Software Engineering Concordia University Montreal, QC, Canada · Ebovir Biotechnologie Inc. Montreal, QC, Canada
Event-to-Video Reconstruction using Spatio-Temporal and Frequency-Enhanced Deep Neural Networks
May 25, 2026Ramna Maqsood, Paulo Nunes, Luís Ducla Soares +1Event-Based Vision Vision Transformer
Instituto de Telecomunicações, Instituto Universitário de Lisboa (ISCTE-IUL) Lisbon, Portugal · Instituto de Telecomunicac¸˜oes, Instituto Universit´ario de Lisboa (ISCTE-IUL) Lisbon, Portugal
X-Edit: Exact, Explicit, and Explainable Null-Space Editing for Medical Vision Transformers
May 24, 2026Yuanye Liu, Siyuan Zhou, Ke Zhang +3Vision Transformer Medical Image Classification
Fudan University, Shanghai, China · Johns Hopkins University, Baltimore, USA · National University of Singapore, Singapore +1
Self-Supervised Contrastive Learning for Cardiac MR Sequence Classification
May 24, 2026Yuli Wang, Hyewon Jung, Dongshen Peng +10Vision Transformer Vision Foundation Model Adaptation
Department of Radiology and Radiological Science, Johns Hopkins University School of Medicine, Baltimore, MD, 21205, USA · Department of Electrical and Computer Engineering, Johns Hopkins University,2026 Baltimore, MD, 21218, USA · Department of Computer Science, University of North Carolina at Chapel Hill, Chapel Hill, NC 27599 +4
Muon in Vision Transformers: Optimizer-Recipe Interactions and Gradient Spectra
May 23, 2026Ben S. Southworth, Shuai Jiang, Daniel McBride +2Vision Transformer Muon Optimizer
Los Alamos National Laboratories Los Alamos, NM 87545 · Sandia National Laboratories Albuquerque, NM 87123 · Lehigh University Bethlehem, PA 18015
Vision Transformers Need Better Token Interaction
May 22, 2026Linxiang SuVisual Representation Learning Vision Transformer
University of Szeged
Revitalizing Dense Material Segmentation: Stabilized Vision Transformers and the Generalization Paradox
May 22, 2026Allan Kazakov, Duygu Cakir, Hilal Kurt İrfanoğlu +1Image Segmentation Vision Transformer
Bahcesehir University, Istanbul, Turkey · Poder Bilişim Teknolojileri Sanayi ve Ticaret A.Ş., Istanbul, Turkey · Galatasaray University, Istanbul, Turkey
Improved Belief-Attention in Vision Task
May 22, 2026Guoqiang ZhangVisual Attention Self-Attention
University of Exeter
TextTeacher: What Can Language Teach About Images?
May 21, 2026Tobias Christian Nauen, Stanislav Frolov, Brian Bernhard Moser +3Cross-Modal Knowledge Distillation Visual Representation Learning
RPTU University Kaiserslautern-Landau · German Research Center for Artificial Intelligence (DFKI)
Vision Transformers and Convolutional Neural Networks for Land Use Scene Classification
May 20, 2026Arun D. KulkarniRemote Sensing Image Understanding Vision Transformer
Computer Science Department, University of Texas at Tyler, Tyler, TX 75799, USA
FTerViT: Fully Ternary Vision Transformer
May 20, 2026Szymon Ruciński, Pietro Bonazzi, Engin Türetken +3Ternary Quantization Vision Transformer
CSEM, Neuchâtel, Switzerland · ETH Zürich, Zurich, Switzerland
Weierstrass Positional Encoding for Vision Transformers
May 20, 2026Zhihang Xin, Rui Wang, Xitong Hu +1Vision Transformer Positional Encoding
School of Mathematics and Data Science, Jiangnan University, Wuxi 214122, China · School of Artificial Intelligence and Computer Science, Jiangnan University, Wuxi 214122, China
UniRefiner: Teaching Pre-trained ViTs to Self-Dispose Dross via Contrastive Register
May 19, 2026Congpei Qiu, Zhaoyu Hu, Wei Ke +3Vision Transformer Vision Foundation Model Adaptation
Xi’an Jiaotong University, School of Software Engineering · Harbin Institute of Technology (Shenzhen) · Shenzhen Loop Area Institute +1
Exposing Functional Fusion: A New Class of Strategic Backdoor in Dynamic Prompt Architectures
May 19, 2026Zeyao Liu, Zhendong Zhao, Xiaojun Chen +3Adversarial Attacks Vision Transformer
Institute of Information Engineering, Chinese Academy of Sciences · State Key Laboratory of Cyberspace Security Defense · School of Cyber Security, University of Chinese Academy of Sciences +1
Resolving Representation Ambiguity in Feedforward Novel View Synthesis Transformer via Semantic-Spatial Decoupling
May 18, 2026Yihang Wu, Yihang Sun, Shaofeng Zhang +4Disentangled Representation Learning Vision Transformer
Institute of Trustworthy Embodied Artificial Intelligence (TEAI), Fudan University · 3Sch. of Artificial Intelligence & Sch. of Computer Science, Shanghai Jiao Tong University · University of Science and Technology of China +1
Token-Space Mask Prediction for Efficient Vision Transformer Segmentation
May 18, 2026Calvin Galagain, Martyna Poreba, François GouletteVision Transformer Efficient ViTs
Universit´e Paris-Saclay, CEA List · U2IS, ENSTA Paris, Institut Polytechnique de Paris · F-91120 Palaiseau, France
Unleashing Vision Transformer Potential In Image Quality Assessment via Global-Local Adaptive Interaction
May 18, 2026Yu Li, Puchao Zhou, Yachun Mi +3Vision Transformer Vision Foundation Model Adaptation
Harbin Institute of Technology · Meituan
Systematic Evaluation of Vision Transformers for Automated Cervical Cancer Classification: Optimization, Statistical Validation, and Clinical Interpretability
May 17, 2026Nisreen Albzour, Sarah S. LamVision Transformer Efficient ViTs
School of Systems Science and Industrial Engineering, Binghamton University, Binghamton, NY 13902, USA
From Sparsity to Simplicity: Enabling Simpler Sequential Replacements via Sparse Attention Distillation
May 15, 2026Yuxin Ren, Maxwell D Collins, Miao Hu +1Self-Attention Vision Transformer
University of Arizona, Tucson AZ, USA · TetraMem, Inc., San Jose CA, USA
Representative Attention For Vision Transformers
May 14, 2026Yuntong Li, Hainuo Wang, Hengxing Liu +2Vision Transformer Efficient ViTs
College of Intelligence and Computing, Tianjin University, Tianjin 300350, China
Backbone is All You Need: Assessing Vulnerabilities of Frozen Foundation Models in Synthetic Image Forensics
May 13, 2026Chiara Musso, Joy Battocchio, Andrea Montibeller +1Adversarial Attacks Vision Transformer
University of Trento Trento, Italy
Do Vision Transformers Need All-to-All Attention? Global Communication Through Elastic Learned Cores
May 12, 2026Alan Z. Song, Yinjie Chen, Mu Nan +3Visual Representation Learning Vision Transformer
Carnegie Mellon University · University of Hong Kong
Spectral Vision Transformer for Efficient Tokenization with Limited Data
May 12, 2026Alexandra G. Roberts, Maneesh John, Jinwei Zhang +10Medical Imaging Image Tokenization

May 28, 2026J/K move · Enter open · S save

Positional Encodings Anchor Spatial Structure in Vision Transformers: A Geometric Perspective on Robustness

Mahmoud Mannes

ESSTHS

Distribution Shift Robustness Vision Transformer Positional Encoding

Open paper AskPDF arXiv

Positional embeddings (PEs) in Vision Transformers (ViTs) are known to impact performance and robustness, but their role in shaping internal spatial representations is not well understood. In this work, we study how different forms of PEs influence the representational geometry of ViTs and how these changes relate to robustness under content-disrupting distribution shifts. We introduce a metric, the Spatial Similarity Distance Correlation (SSDC), to quantify spatial structure in token representations. Using this metric, we show that ViTs trained without PEs still develop non-trivial spatial structure, but this structure is driven by visual content and collapses under token permutation. In contrast, we find that all PEs considered (learned absolute, sinusoidal, and rotary) are associated with a consistent shift toward an index-anchored spatial organization. Representations in these models remain stable under perturbations that disrupt content, and exhibit substantially improved robustness to such distributional shifts. We further show that while different PEs produce distinct depth-wise trajectories of spatial structure, their robustness properties are largely similar (with secondary variation across encoding schemes), suggesting that robustness appears to depend on the presence of a stable positional reference frame more than it depends on the specific encoding mechanism. These results offer a geometric account of how positional encodings shape internal representations, with implications for the principled design of future encoding schemes.