Vision Foundation Model Adaptation

Ask about this topic

Overview

This field studies how to reuse pretrained vision models when target tasks, data, or sensors differ from their original training conditions. Common approaches include full or partial fine-tuning, parameter-efficient methods such as LoRA and prompt or adapter tuning, feature alignment, and distillation into smaller models. Applications range from medical and remote-sensing segmentation to video understanding, robotics, and 3D geometry, often with limited labels or shifted test data. A central tension is that adaptation can improve target-task accuracy while weakening robustness or transfer to unfamiliar settings, so efficiency and out-of-domain performance remain important evaluation criteria.

Latest papers

CardsList

328 papers33 papers in the last four weeks, up 22% on the four weeks before. 0.2% of all new papers.

  1. Segment Anything Model Based Context Guided Mamba Unet for Medical Image Segmentation

    Oct 29, 2026Chenchen Wang, You ZhouMedical Image SegmentationU-Net

    School of Computer Science and Informatics, Cardiff University, Cardiff, UK · Department of Infection and Immunity, School of Medicine, Cardiff University, Cardiff, UK

  2. Venus-DefakerOne2: A Vision-Forensics Foundation Model with Broader Coverage

    Oct 27, 2026Chenfan Qu, Yachao Liang, Mingqi Fang +27Image Forgery DetectionDeepfake Detection

    GuangJian Team, Ant Group · Technical Committee on Digital Media Forensics and Security, CSIG

  3. A note on data-efficient finetuning of vision foundation models

    Oct 27, 2026Niclas Hergenröther, Antonio OrvietoVision Foundation Model AdaptationVision Foundation Models

    ELLIS Institute Tübingen, Max Planck Institute for Intelligent Systems, Tübingen AI Center

  4. Multibranch Ensemble Head in Vision Foundation Models for Efficient Cucumber Phenological Stage Classification

    Oct 27, 2026Kostiantyn KhabarlakVision Foundation Model AdaptationEnsemble Learning

    Dnipro University of Technology, Ukraine

  5. SAGE: Saliency-Annealed Gated Encoder for Universal Vision Recognition

    Oct 27, 2026Le Yang, Yucheng Huang, Junyu Chen +4Vision TransformerVision Foundation Model Adaptation

    Huawei Technologies Co., Ltd.

  6. GIFT: Representation Geometry Matters for Single-Domain Generalized Object Detection

    Oct 26, 2026Yin Zhang, Yaoyue Zheng, Yongqiang Zhang +2Cross-Domain GeneralizationObject Detection

    School of Instrument Science and Engineering, Harbin Institute of Technology · Computer Vision Center, Universitat Autònoma de Barcelona · Institute of Artificial Intelligence and Robotics, Xi’an Jiaotong University +1

  7. Single-Image Food Mass Estimators Do Not Transfer Their Gram Scale Across Datasets

    Oct 21, 2026Yongsheng LianCross-Dataset GeneralizationVision Foundation Model Adaptation

    University of Louisville, Louisville, KY, USA

  8. Convergent Performance, Divergent Mechanisms in LoRA-Adapted Vision Foundation Models for Brain MRI

    Oct 20, 2026Cecilia Diana-Albelda, Fiona Kekwick, Raghav Mehta +6Vision Foundation Model AdaptationLow-Rank Adaptation

    Department of Electronic Technology and Communications, Universidad Autónoma de Madrid, Madrid, Spain · Department of Computing, Imperial College London, London, United Kingdom · Department of Brain Sciences, Imperial College London, London, United Kingdom +3

  9. Communication-Efficient Federated Domain Generalization in Edge Networks via Dynamic Prototype Regulation

    Oct 19, 2026Yuankun Xia, Hui Wang, Ling Yuan +3Federated LearningFederated Domain Generalization

    School of Computer Science and Technology, Zhejiang Normal University, Jinhua 321004, China

  10. IntriAdapt: Generalizable Intrinsic-Guided Test-Time Adaptation for Metric Geometry Estimation

    Oct 17, 2026Jiaxing Chen, Zizheng Yan, Jingyu Zhuang +4Test-Time Adaptation3D Reconstruction

  11. From Adults to Children: Benchmarking Foundation Models for Chest X-Ray Classification under Domain Shift

    Oct 15, 2026Sara Inácio, Hugo Proença, João C. NevesMedical Imaging Foundation ModelsChest X-Ray Classification

    University of Beira Interior, Portugal · NOVA LINCS · IT: Instituto de Telecomunicações

  12. FuseAdapt: Parameter-Efficient Multimodal Fusion for Semantic Segmentation with Missing Modalities

    Oct 15, 2026Xin Zhang, Robby T. TanMultimodal Semantic SegmentationMultimodal Fusion

    National University of Singapore

  13. GDBA-Net: A Gated Dual-Branch Adaptation of SAM2 for Robust Cross-Domain Nuclei Segmentation

    Oct 14, 2026Biplab Poudel, Betserai Albert Magarire, Anish Kumar Shah +2Histopathology Image SegmentationMedical Image Segmentation

    Department of Electrical Engineering and Computer Science, University of Missouri, Columbia, MO 65211, USA · Bond Life Sciences Center, University of Missouri, Columbia, MO 65211, USA · Department of Applied Computing, Lander University, Greenwood, SC 29649, USA +2

  14. COMPASS: Contextual Moment Prior Alignment for Generalizable AIGI Detection

    Oct 13, 2026Zhan Yang, Tiancheng Shen, Weijie Lyu +4AI-Generated Image DetectionDeepfake Detection

    Zhejiang University · University of California, Merced · KAUST +1

  15. Variational Filtering for Bayesian Last Layers with an Independent Binary Probit Surrogate

    Oct 12, 2026Dimitrije Markovic, Conor Heins, Alexander Tschantz +1Bayesian Neural NetworksBayesian Inference

    Independent Researcher Vienna, Austria · Independent Researcher Berlin, Germany · University of Sussex Brighton, UK +1

  16. Learning Features, Not Layouts: Feature-Axis Attention as a Transfer Prior for Medical Imaging

    Oct 9, 2026Aon Safdar, Mohamed SaadeldinMedical Image Representation LearningVision Transformer

    University College Dublin, Ireland

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

    Oct 8, 2026Ricardo Pizarro, Roberto Valle, José M. Buenaposada +2Temporal Action DetectionEfficient ViTs

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

  18. Diffusion Meta-Prompting and Steering for Generalizable Foundation Model Adaptation

    Oct 8, 2026Deepak Sridhar, Yi Li, Kartikeya Bhardwaj +7Prompt LearningVision Foundation Model Adaptation

    University of California, San Diego · Qualcomm AI Research

  19. One-Shot Adaptive Segmentation For Scientific Images

    Oct 7, 2026Tejaswi V. Panchagnula, Allison M. Davis, Fengqing ZhuImage SegmentationVision Foundation Model Adaptation

    Elmore Family School of Electrical and Computer Engineering Purdue University West Lafayette, Indiana, USA 47907

  20. 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

  21. 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 DrivingRepresentation Alignment

    Southeast University · OpenDriveLab at The University of Hong Kong · Shenzhen Loop Area Institute

  22. TIRA: Tumor Immune Representation Adaptation for Zero-Shot Cross-Cancer MSI and TMB Prediction

    Oct 7, 2026Dasari Naga RajuClinical PredictionDomain Generalization

    Independent Researcher, Andhra Pradesh, India

  23. Forensic Reserve: Eliciting Latent Knowledge for Image Forgery Detection

    Oct 6, 2026Jiahua Li, Zixu John, Tom Zhong +5Image Forgery DetectionVision Foundation Model Adaptation

    University of Oxford, the United Kingdom · Independent Researcher · Imperial College London, the United Kingdom +1

  24. Beyond Training from Scratch: Foundation Models for Data-Efficient and Generalizable Cardiac MRI Reconstruction

    Oct 6, 2026Anam Hashmi, Mayug Maniparambil, Julia Dietlmeier +2Image ReconstructionVision Foundation Model Adaptation

    Research Ireland Centre for Research Training in Machine Learning, Ireland · Dublin City University, Ireland · University College Dublin, Ireland +1

  25. Localize Any Object in X-Ray Security Scans without Human Annotation

    Oct 5, 2026Yaqi Cai, Mingxuan Liu, Lorenzo Vaquero +5Self-Supervised LearningSynthetic Data Generation

    University of Trento · Fondazione Bruno Kessler · Dalian University of Technology +1

  26. KALEIDO: Input-Space Adaptation of a Vision Model for Time-Series Forecasting Through Gated Fold Geometries

    Oct 3, 2026Xiangyu Shi, Qinghua Liu, Sam Heshmati +1Time Series ForecastingZero-Shot Time Series Forecasting

    Northwestern University · Ohio State University · Bosch Research North America

  27. LoRA's Second Descent Extends Beyond Parameter Parity

    Oct 3, 2026Yueran MaDouble DescentLow-Rank Adaptation

    The University of Queensland Brisbane, Australia

  28. Frame-Level Temporal Alignment for Human-to-Robot Visual Adaptation

    Oct 3, 2026Xizhe Zhang, Jingfeng Zhang, Zirun Zhou +1Robot LearningTransfer Learning

    The University of Auckland · Fudan University

  29. A Geometric-Transformation Feature-Adaptive Manifold Restoration Method for Open-Vocabulary Semantic Segmentation of Remote Sensing Images

    Oct 3, 2026Jianzheng Wang, Huan Ni, Xiaonan Niu +2Remote Sensing Image SegmentationOpen-Vocabulary Semantic Segmentation

    School of Remote Sensing and Geomatics Engineering, Nanjing University of Information Science and Technology, China, Nanjing, 210044, China · Nanjing Center, China Geological Survey, Nanjing, 210016, China · School of Automation, Southeast University, Nanjing, 210096, China

  30. SigLIP2 for aerial fire risk classification

    Oct 2, 2026Yunus Serhat BıçakçıImage ClassificationWildfire Detection

    Department of Artificial Intelligence and Machine Learning Faculty of Applied Sciences, Marmara University Istanbul, Türkiye