Vision Foundation Models

Follow this topic Ask about this topic

Momentum

8 papers in the last four weeks, down 33% on the four weeks before. 0.1% of all new papers.

Jul 13Week of Sep 28

Latest papers 89

All topics

One Block, Multiple Depths: Recurrent Vision Transformers with Depth-Programmed Experts
Oct 8, 2026Adrian Bulat, Yassine Ouali, Georgios TzimiropoulosEfficient ViTs Mixture of Experts
Samsung AI Cambridge · Technical University of Iasi · Queen Mary University of London
DisParQ: Self-Supervised Part Concepts for Interpretable Vision Foundation Models
Oct 7, 2026Adam Pardyl, Siddhartha Gairola, Sukrut Rao +4Explainable Image Classification Vision Foundation Models
Jagiellonian University, Faculty of Mathematics and Computer Science · Jagiellonian University, Doctoral School of Exact and Natural Sciences · Max Planck Institute for Informatics, Saarland Informatics Campus +2
SPACE-CLIPv2: Decoding Local Geometry from Frozen CLIP for Monocular Depth Estimation
Oct 4, 2026Hyun Song, Taewan Cho, Kangmin Kim +1Vision-Language Models Vision Foundation Models
School of Computing, iRASC Lab., Gachon University
PolyOCR-Venus: Unified OCR Foundation Models for Text-Centric Visual Intelligence
Sep 29, 2026GuangJian Team, Kaili Huang, Yongshuo Zhang +22Document Understanding Vision Foundation Models
Ant Group
Hard Vision, Easy Vision: What GPT-6 Astra Reveals Across Computer Vision
Sep 28, 2026Hanoona Rasheed, Mohammed Irfan Kurpath, Bin Ren +3Vision Foundation Models Large Vision-Language Models
Mohamed bin Zayed University of Artificial Intelligence · Apertix
UltraBench 2: Towards Robust Evaluation of Vision Foundation Models on Ultrasound
Sep 23, 2026Ashwath Radhachandran, Adam Tupper, Christian Gagné +1Ultrasound Image Segmentation Medical Imaging Foundation Models
Bioengineering Department, University of California, Los Angeles · Institut Intelligence et Données (IID), Université Laval Mila – Quebec AI Institute · Radiological Sciences Department, UCLA David Geffen School of Medicine
Towards robust multimodal 3D object detection via visual foundation models
Sep 20, 2026Ziying Song, Lin Liu, Hongyu Pan +4Multimodal Robustness Vision Foundation Models
School of Computer Science and Technology, Beijing Jiaotong University, Beijing 100044, China · Horizon Robotics, Beijing 100000, China · University of Macau, Macao 999078, China +1
Exploring 2D backbone effects for indoor semantic occupancy prediction
Sep 15, 2026Shizhang Fanga, Wanling Yea, Qi ZhengVision Foundation Models Semantic Occupancy Mapping
aCollege of Electronics and Information Engineering, Shenzhen University, Shenzhen, China
"World Knowledge" in the Weights: Reading Concept Circuits of Vision Transformers
Sep 8, 2026Yanlin Chen, Tang Li, Xi PengTransformer Interpretability Vision Foundation Models
Department of Computer & Information Sciences, University of Delaware, USA · Department of Computer Science, University of Virginia, USA
CrACK: Adversarial Attacks on Cross-Model Consistency in Collaborative Vision Foundation Models
Sep 7, 2026Feifei Liu, Jintao Cheng, Chi Man Vong +1Vision Foundation Models Adversarial Robustness
the School of Data science and Engineering, South China Normal University · Hong Kong University of Science and Technology · University of Macau
VidaForge: Open Research Infrastructure for Video Pretraining Data Recipes
Sep 6, 2026Yan Ma, Jiadi Su, Zhulin Hu +4Vision Foundation Models Training Data Curation
Fudan University · Generative Artificial Intelligence Research Lab (GAIR) · Shanghai Jiao Tong University +2
What Do Scan-Derived Class Prototypes Add? Disentangling Supervision, Prototype Content and Query Protocol in Recognition over Frozen Foundation Features
Sep 3, 2026Chenxi Tao, Hong-In Won, Seung-Kyum ChoiPrototype-Based Classification Vision Foundation Models
George W. Woodruff School of Mechanical Engineering, Georgia Institute of Technology, Atlanta, 30332, GA, USA
What, Where, and How: Probing Spatiotemporal Representations in Video Foundation Models
Sep 1, 2026Sharon S. Musa, Fereshteh Forghani, Harrish Thasarathan +3Vision Foundation Models Video Representation Learning
Lassonde School of Engineering, York University, Toronto, Canada · Vector Institute, Toronto, Canada · FAIR, Meta Superintelligence Labs +2
Do Satellites See Commuters? A Critical Benchmark of Vision Foundation Models
Sep 1, 2026Ashiq Shukoor Iqbal, Wilson Wongso, Flora D. SalimVision Foundation Models Geospatial Foundation Models
The University of New South Wales · Sydney, NSW, Australia
Restrict, Don't Retrain: Inference-Time VLM Guidance for Zero-Shot Aerial Segmentation
Sep 1, 2026Teresa DiMeola, Charles Walter, Hong XiaoRemote Sensing Image Segmentation Vision Foundation Models
Dept. of Computer and Information Science University of Mississippi
Evaluating 2D and 3D-Aware Vision Foundation Models for Vehicle Attribute Recognition
Aug 30, 2026Alexandre V. Delazeri, Gabriel E. Lima, Eduil Nascimento +2Vision Foundation Models Fine-Grained Visual Perception
Department of Informatics, Federal University of Paraná, Curitiba, Brazil · Department of Technological Development and Quality, Paraná Military Police, Curitiba, Brazil · Graduate Program in Informatics, Pontifical Catholic University of Paraná, Curitiba, Brazil
WildFin: An In-the-Wild Dataset for Fish Behavioral Recognition
Aug 21, 2026Abigail G. Grassick, Jerome Tze-Hou Hsu, Ethan Lin +10Vision Foundation Models Video Action Recognition
Cornell University, 14850 Ithaca, NY · University of Colorado Boulder, 80309 Boulder, CO · HHMI Janelia Research Campus, 20147, Ashburn VA
A Controlled Study of Self-Supervised Image and Video Pretraining under Limited Resources
Aug 13, 2026Brunó B. Englert, Gijs DubbelmanVision Foundation Models Self-Supervised Pre-Training
Eindhoven University of Technology
Understanding Why Foundation Models Work for Diffusion-Generated Image Detection
Aug 12, 2026Davide Cozzolino, Giovanni Poggi, Luisa VerdolivaVision Foundation Models AI-Generated Image Detection
University Federico II of Naples, 80125 Naples, Italy
P3CA: Encoder-Agnostic Interpretation of Vision Foundation Model Embeddings via Spatial Probing
Aug 10, 2026Amoon Jamzad, Dilakshan Srikanthan, Faranak Akbarifar +2Vision Foundation Models Representation Probing
School of Computing, Queen’s University, Kingston, Ontario, K7L 2N8, Canada
LoRA-based Adaptation Alone Is Not Enough: Understanding the Limits of Foundation Models for Face Presentation Attack Detection
Aug 10, 2026Peter Lorenz, Anjith George, Marcel SébastienVision Foundation Models Vision Foundation Model Adaptation
Idiap Research Institute, Martigny, Switzerland · University of Lausanne (UNIL), Lausanne, Switzerland
Foundation Models are Implicit Deepfake Detectors
Aug 10, 2026Stefan Smeu, Dragos-Alexandru Boldisor, Elisabeta Oneata +1Vision Foundation Models Deepfake Detection
1Bitdefender, Romania · 2POLITEHNICA Bucharest
Damage Classification for 3D Point Cloud Data via 3D Data Analysis and Vision Foundation Model-based 2D Projections
Aug 9, 2026Evan Perez, Kalelo Dukuray, Erika Ardiles-Cruz +1Point Cloud Anomaly Detection Vision Foundation Models
Dept. of Computer Science, City College of New York, NY 10031, USA · Air Force Research Lab, Rome, NY 13441, USA
Invisible Shortcuts: Why Vision Encoders Know Your Camera
Aug 5, 2026Vladan Stojnić, Ryan Ramos, Giorgos Kordopatis-Zilos +2Vision Foundation Models Shortcut Learning
VRG, FEE, Czech Technical University in Prague · The University of Osaka
Foveated Probes Recover Localized Binding Information in Vision Foundation Models
Aug 1, 2026Mateusz Michalkiewicz, Mahsa Baktashmotlagh, Guha BalakrishnanVisual Representation Learning Vision Foundation Models
Rice University, Houston, TX, USA · The University of Queensland, Brisbane, QLD, Australia
Generated Images Are Easier to Forget: A Machine Unlearning Perspective for Synthetic Image Detection
Aug 1, 2026Jun Nie, Yonggang Zhang, Tongliang Liu +3Vision Foundation Models AI-Generated Image Detection
University of Science and Technology of China · Hong Kong Baptist University · The Hong Kong University of Science and Technology +1
Foundation Models for Face Presentation Attack Detection: A Unified Linear-Probing Benchmark
Jul 29, 2026Peter Lorenz, Anjith George, Sébastien MarcelVision Foundation Models Linear Probing
Idiap Research Institute, Martigny, Switzerland · University of Lausanne (UNIL), Lausanne, Switzerland
A Scale-adaptive Vision Model Links C. elegans Neuronal Morphology to Behavior for Neurotoxicity Assessment
Jul 25, 2026Haochao Ying, Shenchong Lv, Yutao Sun +8Vision Foundation Models Toxicity Detection
School of Public Health and Second Affiliated Hospital, Zhejiang University School of Medicine, Hangzhou, 310058, China. · State Key Laboratory of Transvascular Implantation Devices and TIDRI, Second Affiliated Hospital of Zhejiang University School of Medicine, Hangzhou, 310009, China. · Polytechnic Institute, Zhejiang University, Hangzhou, 310058, China. +5
Rethinking Multi-Branch and Cross-Backbone Fusion for Vehicle Re-Identification under Foundation-Model Pretraining
Jul 24, 2026Yu Wang, Hongyu YangVision Foundation Models Hybrid CNN-Transformer Architectures
Huahuan (Yunnan) Technology Co., Ltd., Yunnan, China
Do Vision Encoders Exhibit Human-like Color Thresholds?
Jul 17, 2026Engy Ehab, Pablo Hernández-Cámara, Nahla Belal +3Vision Foundation Models
Computer Vision Center, Spain · Universitat Aut`onoma de Barcelona, Spain · Image Processing Lab, Universitat de Val`encia, Spain +1

Oct 8, 2026, cs.CVJ/K move · Enter open · S save

One Block, Multiple Depths: Recurrent Vision Transformers with Depth-Programmed Experts

Adrian Bulat, Yassine Ouali, Georgios Tzimiropoulos

Samsung AI Cambridge · Technical University of Iasi · Queen Mary University of London

Efficient ViTs Mixture of Experts Vision Foundation Models

Open paper AskPDF arXiv

In this work, we show that a single Transformer block, applied recurrently, can match the accuracy of a full-depth vision encoder at comparable inference FLOPs without intermediate feature distillation. reViT restores depth-specific transformations by representing the FFN at each recurrent depth as a convex combination of a small shared expert bank. A continuous normalized-depth coordinate programs this mixture, defining a resampleable trajectory through FFN parameter space. We evaluate this design in two regimes: supervised ImageNet-1k training and distillation from a DINOv2 teacher. Across both regimes, controlled adaptations identify weight-space merging as the strongest tested MoE family at a matching one-FFN budget, ahead of the token-dispatch and output-mixture alternatives. Trained from scratch, reViT-B/16 attains DeiT III accuracy with about 70% fewer stored parameters. An 8-experts model distilled using only the teacher's output features retains nearly all of its DINOv2 teacher's linear-probe accuracy and transfers across classification, segmentation, and depth prediction. Elastic-depth training allows one checkpoint (trained model) to operate at multiple tested depths by resampling the same normalized coordinate interval. For fixed-depth deployment, the recurrent block can be materialized as a conventional dense graph, removing online routing and merging without changing the one-FFN-per-depth compute but expanding deployment storage.

Momentum

Related topics

Latest papers 89