Vision Foundation Model Adaptation

Follow this topic Ask about this topic

Momentum

22 papers in the last four weeks, up 83% on the four weeks before. 0.2% of all new papers.

Jul 13Week of Sep 28

Latest papers 204

All topics

SV-TAD: Native Sparse Convs for Efficient Temporal Action Detection
Oct 8, 2026Ricardo Pizarro, Roberto Valle, José M. Buenaposada +2Temporal Action Detection Efficient ViTs
Universidad de Alcal´a, Alcal´a de Henares, Spain · Universidad Polit´ecnica de Madrid, Madrid, Spain · Universidad Rey Juan Carlos, M´ostoles, Spain
Diffusion Meta-Prompting and Steering for Generalizable Foundation Model Adaptation
Oct 8, 2026Deepak Sridhar, Yi Li, Kartikeya Bhardwaj +7Prompt Learning Vision Foundation Model Adaptation
University of California, San Diego · Qualcomm AI Research
One-Shot Adaptive Segmentation For Scientific Images
Oct 7, 2026Tejaswi V. Panchagnula, Allison M. Davis, Fengqing ZhuImage Segmentation Vision Foundation Model Adaptation
Elmore Family School of Electrical and Computer Engineering Purdue University West Lafayette, Indiana, USA 47907
BagDINO: Multi-View Baggage Re-Identification with DINOv3
Oct 7, 2026Vita Santa Barletta, Danilo Caivano, Rebecca Margiotta +2Vision Foundation Model Adaptation
University of Bari Aldo moro Department of Computer Science Bari, Italia · University of Bari Aldo Moro, SER&Practices Department of Computer Science Bari, Italia · SER&Practices Spin-off of the University of Bari Aldo Moro Bari, Italia
Do Better Visual Representations Always Lead to Better End-to-End Autonomous Driving?
Oct 7, 2026Zihao Zhang, Haochen Tian, Tianyu Li +5End-to-End Autonomous Driving Representation Alignment
Southeast University · OpenDriveLab at The University of Hong Kong · Shenzhen Loop Area Institute
TIRA: Tumor Immune Representation Adaptation for Zero-Shot Cross-Cancer MSI and TMB Prediction
Oct 7, 2026Dasari Naga RajuClinical Prediction Domain Generalization
Independent Researcher, Andhra Pradesh, India
Forensic Reserve: Eliciting Latent Knowledge for Image Forgery Detection
Oct 6, 2026Jiahua Li, Zixu John, Tom Zhong +5Image Forgery Detection Vision Foundation Model Adaptation
University of Oxford, the United Kingdom · Independent Researcher · Imperial College London, the United Kingdom +1
Beyond Training from Scratch: Foundation Models for Data-Efficient and Generalizable Cardiac MRI Reconstruction
Oct 6, 2026Anam Hashmi, Mayug Maniparambil, Julia Dietlmeier +2Image Reconstruction Vision Foundation Model Adaptation
Research Ireland Centre for Research Training in Machine Learning, Ireland · Dublin City University, Ireland · University College Dublin, Ireland +1
Localize Any Object in X-Ray Security Scans without Human Annotation
Oct 5, 2026Yaqi Cai, Mingxuan Liu, Lorenzo Vaquero +5Self-Supervised Learning Synthetic Data Generation
University of Trento · Fondazione Bruno Kessler · Dalian University of Technology +1
FAST: Flow Any Scene Transformer
Sep 30, 2026Yongjian Zhang, Longguang Wang, Zhuo Song +3Optical Flow Vision Transformer
School of Electronics and Communication Engineering, the Shenzhen Campus of Sun Yat-sen University, Sun Yat-sen University, Shenzhen, China · Hong Kong Polytechnic University, HKSAR, China · School of Computer Science and Engineering, Sun Yat-sen University, Guangzhou, China
DCM-SAM: Defect-Conditioned Mixture of LoRA Experts for NPU-Deployed AM Defect Segmentation
Sep 30, 2026Md Mushfiqur Rahaman, Md Mahedi Hasan, Imtiaz Ahmed +1Mixture of Experts Vision Foundation Model Adaptation
Department of Industrial and Management Systems Engineering West Virginia University, Morgantown, WV · School of Mathematical and Data Sciences West Virginia University, Morgantown, WV · Lane Department of Computer Science & Electrical Engineering West Virginia University, Morgantown, WV
When to Adapt: Multi-Signal Domain Shift Detection for Efficient Training-Free Adaptation in Open-Vocabulary Segmentation
Sep 29, 2026Michele Antonazzi, Alejandra C. Hernandez, José Araujo +2Distribution Shift Continual Test-Time Adaptation
EECS and Digital Futures, KTH Royal Institute of Technology, Stockholm, Sweden · Ericsson Research, Ericsson AB, Stockholm, Sweden
HyperSAM: A Promptable Foundation Model for Hyperspectral Remote Sensing
Sep 29, 2026Li Pang, Xinqiao Wu, Jing Yao +5Synthetic Data Augmentation Vision Foundation Model Adaptation
School of Mathematics and Statistics, Xi’an Jiaotong University, Xi’an 710049, China · Faculty of Electronic and Information Engineering, Xi’an Jiaotong University, Xi’an 710049, China · State Key Laboratory of Remote Sensing and Digital Earth, Aerospace Information Research Institute, Chinese Academy of Sciences, Beijing 100094, China +4
Forensic-Aware Continual Adaptation for Image Forgery Localization
Sep 29, 2026Chenqi Kong, Song Xia, Anwei Luo +3Image Forgery Detection Vision Foundation Model Adaptation
School of Computing, National University of Singapore, Singapore. · ROSE Lab, School of EEE, Nanyang Technological University, Singapore. · School of Computing and Artificial Intelligence, Jiangxi University of Finance and Economics, Nanchang, China. +1
You Only Reprogram Once: Rethinking Prolonged Training for Visual Reprogramming
Sep 29, 2026Zizhao Li, Mohammed Yaqoob Ansari, Xinyu Su +3VLM Adaptation Vision Foundation Model Adaptation
The University of Melbourne · Fudan University
Boosting Metric Depth Completion via Training-Free Adaptive Response Geometry
Sep 28, 2026Mia Zhang, Jizong PengPost-Hoc Calibration Depth Completion
dConstruct Robotics · University of Waterloo
DBCF: Dual-Branch Complementary Fusion of Foundation Models for Generalized Deepfake Detection
Sep 28, 2026Fengming Gu, Mingjie He, Zonghui Guo +2Vision Foundation Model Adaptation Deepfake Detection
School of Advanced Interdisciplinary Sciences, University of Chinese Academy of Sciences, Beijing, 100049, China · State Key Laboratory of AI Safety, Institute of Computing Technology, Chinese Academy of Sciences, Beijing, 100190, China · University of Chinese Academy of Sciences, Beijing, 100049, China +1
The Devil is in the Spectrum Bias: Spectrum-Balanced Feature Matching for Robust Representation Distillation
Sep 28, 2026Kuniaki Saito, Yoshitaka UshikuRepresentation Learning Vision Foundation Model Adaptation
OMRON SINIC X Corporation
WildHSR: Metric Feed-Forward 4D People-Scene Reconstruction from a 3D Foundation Model
Sep 24, 2026Jerrin Bright, John ZelekVision Foundation Model Adaptation Dynamic Scene Reconstruction
Vision and Image Processing Lab, University of Waterloo, Canada
Geometry-Conditioned Visual Place Recognition in Natural Environments
Sep 23, 2026Walter Nedov, Saimunur Rahman, Kavindie Katuwandeniya +3Visual Representation Learning Visual Place Recognition
CSIRO Robotics, CSIRO, Australia · Queensland University of Technology, Australia
nnFoundation: 3D Foundation Models for Radiology
Sep 22, 2026Constantin Ulrich Harsy, Tassilo Wald, Karol Gotkowski +803D Foundation Models Medical Imaging Foundation Models
Vision Foundation Models with Synthetic-Only Training for Monocular Spacecraft Pose Estimation
Sep 22, 2026John Church, Vazghen NikolianVision Foundation Model Adaptation Object Pose Estimation
Both authors contributed equally to this work; author order is alphabetical.
RootQuantV2: Adapting a Vision Foundation Model for Root-Trait Regression from Minirhizotron Imagery
Sep 22, 2026Kinjalk Parth, Sebastian Varela, Andrew D. B. LeakeyPlant Phenotyping Vision Foundation Model Adaptation
Department of Plant Biology, University of Illinois at Urbana-Champaign, Urbana, IL 61801, USA · Center for Advanced Bioenergy and Bioproducts Innovation, Urbana, IL 61801, USA
0.5%>100%: Bidirectional Reciprocal Learning for Referring Image Segmentation
Sep 21, 2026Xiaoqiang Lu, Licheng Jiao, Lingling Li +5VLM Adaptation Vision Foundation Model Adaptation
Key Laboratory of Intelligent Perception and Image Understanding of Ministry of Education, International Research Center for Intelligent Perception and Computation, School of Artificial Intelligence, Xidian University, Xi’an, Shaanxi Province, 710071, China
MUSE: Dependency-Aware Adaptation of a Frozen Vision Backbone for Multivariate Time Series Forecasting
Sep 21, 2026Xinying Cai, Junkai Lu, Yuhan Zhu +3Multivariate Time Series Forecasting Time Series Forecasting
East China Normal University
AnalogDepth: Multi-view Geometry from FPV drones under Analog Video Transmission
Sep 21, 2026André Amorim, Pedro F. ProençaDepth Estimation Multi-View 3D Reconstruction
NOVA School of Science and Technology, NOVA University Lisbon, Caparica, Portugal.
Comparative Performance and Parameter-Efficient Adaptation of DINOv2 for Active Trachoma Classification
Sep 20, 2026Kibrom Gebremedhin, Hadush Hailu, Bruk Gebregziabher +1Channel Attention Vision Foundation Model Adaptation
Department of Computer Science Mekelle University Mekelle, Ethiopia · Department of Computer Science Maharishi International University Fairfield, IA, USA · Signal Technologies Germany +1
GAPrompt++: Multi-Granular Geometry-Aware Point Cloud Prompt for 3D Vision Model
Sep 17, 2026Zixiang Ai, Zhenyu Cui, Yufei Guo +4Point Cloud Learning Vision Foundation Model Adaptation
Wangxuan Institute of Computer Technology, Peking University, Beijing 100871, China · Intelligent Science and Technology Academy of CASIC, Beijing 100041, China · Institute of Software, Chinese Academy of Sciences, Beijing 100190, China +1
Bridging Vision Foundation Model Priors with CLIP for Spatial-aware Few-shot Anomaly Detection in Medical Images
Sep 14, 2026Juzheng Miao, Yuchen Yuan, Cheng Chen +1Few-Shot Anomaly Detection Medical Image Anomaly Detection
Department of Computer Science and Engineering, The Chinese University of Hong Kong, Hong Kong, China · Department of Electrical and Computer Engineering, The University of Hong Kong, Hong Kong, China · School of Biomedical Engineering, The University of Hong Kong, Hong Kong, China +1
Spectral Adapters for Segment Anything Model-based Segmentation of Colorectal Liver Metastases in Computed Tomography
Sep 11, 2026Ramtin Mojtahedi, Mohammad Hamghalam, Jacob J. Peoples +6Promptable Image Segmentation Vision Foundation Model Adaptation
School of Computing, Queen’s University, Kingston, ON, Canada · Toronto General Hospital Research Institute, University Health Network, 200 Elizabeth Street, Toronto, ON M5G 2C4, Canada · Department of Electrical Engineering, Qazvin Branch, Islamic Azad University, Qazvin, Iran +6

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

SV-TAD: Native Sparse Convs for Efficient Temporal Action Detection

Ricardo Pizarro, Roberto Valle, José M. Buenaposada, Luis M. Bergasa+1

Universidad de Alcal´a, Alcal´a de Henares, Spain · Universidad Polit´ecnica de Madrid, Madrid, Spain · Universidad Rey Juan Carlos, M´ostoles, Spain

Temporal Action Detection Efficient ViTs Vision Foundation Model Adaptation Convolutional Neural Networks

Open paper AskPDF arXiv

To adapt billion-parameter Vision Transformers for long-video understanding, recent methods freeze the backbone and train lightweight convolutional modules. While effective for parameter-efficient training, existing adapters do not reduce inference-time computation, leaving scalability with respect to video length largely unaddressed. Token selection can reduce attention cost by pruning redundant tokens, but it breaks the spatial grid structure required by convolutional adapters. This forces an expensive dense reconstruction, nullifying much of the potential speedup. We address this by introducing native sparse 2D convolutions, a primitive that allows these adapters, for the first time, to operate directly and efficiently on dynamically pruned token sets. We integrate this primitive into SV-TAD, an adapter framework for temporal action detection, reducing VideoMAEv2-L computation by up to 64% and achieving 2.2x faster inference, while maintaining state-of-the-art accuracy on THUMOS-14 and ActivityNet-1.3. When scaled to InternVideoNext-L, our approach surpasses the previous state of the art at roughly half its computational cost. Moreover, the sparse formulation naturally supports auxiliary task tokens, which improves fine-grained assembly detection on ATTACH.

Momentum

Related topics

Latest papers 204