Domain Adaptation

Ask about this topic

Overview

Domain adaptation studies how to make a model trained in one setting work in another, where images, sensors, language, populations, or conditions may differ. Common approaches align feature distributions with methods such as MMD, CORAL, or adversarial training; generate pseudo-labels for target data; or fine-tune models with a small labeled set, often using lightweight adapters. Recent work also explores source-free and test-time adaptation, as well as foundation models, across settings such as medical imaging, speech, graphs, remote sensing, and sim-to-real transfer. A central challenge is that alignment can cause negative transfer when label spaces or class proportions differ, so methods must balance target gains with preservation of useful source knowledge and be tested under realistic shifts.

Latest papers

CardsList

253 papers26 papers in the last four weeks, up 30% on the four weeks before. 0.2% of all new papers.

  1. CataractSAM-2: A Domain-Adapted Model for Anterior Segment Surgery Segmentation and Scalable Ground-Truth Annotation

    Mar 23, 2026Mohammad Eslami, Dhanvinkumar Ganeshkumar, Saber Kazeminasab +8Medical Image SegmentationSurgical Video Understanding

    Harvard Ophthalmology AI Lab, Massachusetts Eye and Ear, Harvard Medical School, Boston, MA, USA · Thomas Jefferson High School for Science and Technology, Chantilly, Virginia, USA · Massachusetts Eye and Ear, Harvard Medical School, Boston, MA, USA

  2. Lessons and Open Questions from a Unified Study of Camera-Trap Species Recognition Over Time

    Mar 20, 2026Sooyoung Jeon, Hongjie Tian, Lemeng Wang +7Temporal Domain AdaptationWildlife Monitoring

    The Ohio State University · Boston University

  3. ProCal: Probability Calibration for Neighborhood-Guided Source-Free Domain Adaptation

    Mar 19, 2026Ying Zheng, Yiyi Zhang, Yi Wang +1Source-Free Domain AdaptationDomain Adaptation

    Department of Electrical and Electronic Engineering, The Hong Kong Polytechnic University, Hong Kong, China. · Department of Computer Science and Engineering, The Chinese University of Hong Kong, Hong Kong, China.

  4. Boundary-aware Prototype-driven Adversarial Alignment for Cross-Corpus EEG Emotion Recognition

    Mar 18, 2026Guangli Li, Canbiao Wu, Na Tian +2EEG Emotion RecognitionDomain-Adversarial Learning

    School of Biological Science and Medical Engineering, Hunan University of Technology, Zhuzhou 412008, China. · School of Biomedical Engineering, Health Science Center, Shenzhen University, Shenzhen 518060, China · Guangdong Provincial Key Laboratory of Biomedical Measurements and Ultrasound Imaging, Shenzhen 518060, China +1

  5. The Finetuner's Fallacy: When to Pretrain with Your Finetuning Data

    Mar 17, 2026Christina Baek, Ricardo Pio Monti, David Schwab +31Language Model PretrainingDomain-Adaptive Pretraining

    DatologyAI

  6. Seeing Beyond: Extrapolative Domain Adaptive Panoramic Segmentation

    Mar 16, 2026Yuanfan Zheng, Kunyu Peng, Xu Zheng +1Semantic SegmentationDomain Adaptation

    Hunan University · Karlsruhe Institute of Technology · INSAIT, Sofia University “St. Kliment Ohridski” +1

  7. Spectral Rectification for Parameter-Efficient Adaptation of Foundation Models in Colonoscopy Depth Estimation

    Mar 16, 2026Xiaoxian Zhang, Minghai Shi, Lei LiMonocular Depth EstimationVision Foundation Model Adaptation

    Department of Biomedical Engineering, National University of Singapore, Singapore · Department of Radiotherapy, The First Affiliated Hospital of Xi’an Jiaotong University, Xi’an, China

  8. Point-Identification of a Robust Predictor Under Latent Shift with Imperfect Proxies

    Mar 16, 2026Zahra Rahiminasab, Reza Soumi, Arto Klami +1Proximal Causal InferenceDistribution Shift Robustness

    Department of Computer Science, Aalto University · Department of Computer Science, University of Helsinki · ELLIS Institute Finland +1

  9. A Self-Evolving Defect Detection Framework for Industrial Photovoltaic Systems

    Mar 16, 2026Haoyu He, Yu Duan, Wenzhen Liu +5Fault DetectionIndustrial Inspection

    EcoFlow Inc, Shenzhen, China · School of Electrical Engineering, Xi’an Jiaotong University, Xi’an, China

  10. A Lightweight, Transferable, and Self-Adaptive Framework for Intelligent DC Arc-Fault Detection in Photovoltaic Systems

    Mar 16, 2026Xiaoke Yang, Long Gao, Haoyu He +5Fault DetectionPower Systems

    EcoFlow Inc, Shenzhen, China. · AAU Energy, Aalborg University, Denmark

  11. Robust Building Damage Detection in Cross-Disaster Settings Using Domain Adaptation

    Mar 16, 2026Asmae Mouradi, Shruti KshirsagarDisaster Damage AssessmentBuilding Damage Assessment

    School of Computing, Wichita State University, Wichita, Kansas, USA

  12. Toward Scalable Co-located Practical Learning: Assisting with Computer Vision and Multimodal Analytics

    Mar 14, 2026Xinyu Li, Linxuan Zhao, Yueqiao Jin +5Human Activity RecognitionVideo Object Detection

    Centre for Learning Analytics at Monash, Monash University, Melbourne, Australia · Department of Civil and Environmental Engineering, Monash University, Melbourne, Australia · Faculty of Education and School of Computing & Data Science, The University of Hong Kong, Hong Kong +1

  13. Open World MRI Reconstruction with Bias-Calibrated Adaptation

    Mar 13, 2026Jiyao Liu, Shangqi Gao, Lihao Liu +5Image ReconstructionDomain Adaptation

    Fudan University, Shanghai, China · University of Cambridge, Cambridge, United Kingdom · Shanghai Artificial Intelligence Laboratory, Shanghai, China

  14. Test-time Ego-Exo-centric Adaptation for Action Anticipation via Multi-Label Prototype Growing and Dual-Clue Consistency

    Mar 10, 2026Zhaofeng Shi, Heqian Qiu, Lanxiao Wang +4Test-Time AdaptationNext-Action Prediction

    University of Electronic Science and Technology of China, Chengdu, China

  15. BiCLIP: Domain Canonicalization via Structured Geometric Transformation

    Mar 9, 2026Pranav Mantini, Shishir K. ShahVLM AdaptationDomain Adaptation

    University of Houston, Department of Computer Science · The University of Oklahoma, School of Computer Science

  16. AutoAdapt: An Automated Domain Adaptation Framework for LLMs

    Mar 9, 2026Sidharth Sinha, Anson Bastos, Xuchao Zhang +3Domain Adaptation for LLMsDomain Adaptation

    Microsoft, M365 Research, India · Microsoft, M365 Research, Redmond · Microsoft Research, India

  17. Adversarial Domain Adaptation Enables Knowledge Transfer Across Heterogeneous RNA-Seq Datasets

    Mar 9, 2026Kevin Dradjat, Massinissa Hamidi, Blaise HanczarCancer Subtype ClassificationDomain Adaptation

    IBISC Laboratory, University Paris-Saclay (Univ. Evry), France · ADLIN, Paris, France

  18. IMSE: Intrinsic Mixture of Spectral Experts Fine-tuning for Test-Time Adaptation

    Mar 9, 2026Sunghyun Baek, Jaemyung Yu, Seunghee Koh +3Test-Time AdaptationDomain Adaptation

    Korea Advanced Institute of Science and Technology (KAIST) · LG Energy Solution

  19. RePer-360: Releasing Perspective Priors for 360∘^\circ Depth Estimation via Self-Modulation

    Mar 6, 2026Cheng Guan, Chunyu Lin, Zhijie Shen +2Domain AdaptationDepth Estimation

    Institute of Information Science, Beijing Jiaotong University, Beijing 100044, China. · Visual Intelligence +X International Cooperation Joint Laboratory of MOE, Beijing 100044, China.

  20. Semantic Bridging Domains: Pseudo-Source as Test-Time Connector

    Mar 4, 2026Xizhong Yang, Huiming Wang, Ning Xu +1Domain AdaptationSource-Free Domain Adaptation

    Southeast University · Kuaishou Technology

  21. A Theory of Random Graph Shift in Truncated-Spectrum vRKHS

    Feb 27, 2026Zhang Wan, Tingting Mu, Samuel KaskiGraph Domain AdaptationDistribution Shift Robustness

    Department of Computer Science, University of Manchester, UK · Department of Computer Science, Aalto University, Finland · ELLIS Institute Finland

  22. Towards Dynamic Dense Retrieval with Routing Strategy

    Feb 26, 2026Zhan Su, Fengran Mo, Jinghan Zhang +4Prefix TuningDense Retrieval

    Université de Montréal, Montréal, Québec, Canada · Clemson University, Clemson, South Carolina, USA · University of Washington, America

  23. Small Wins Big: Comparing Large Language Models and Domain Fine-Tuned Models for Sarcasm Detection in Code-Mixed Hinglish Text

    Feb 25, 2026Bitan Majumder, Anirban SenSarcasm DetectionSmall Language Models

    Pondicherry University · Ashoka University

  24. Localized Dynamics-Aware Domain Adaption for Off-Dynamics Offline Reinforcement Learning

    Feb 24, 2026Zhangjie Xia, Yu Yang, Pan XuOffline RLDomain Adaptation

    New York University · Duke University

  25. Contrastive meta-domain adaptation for robust skin lesion classification across clinical and acquisition conditions

    Feb 23, 2026Rodrigo Mota, Kelvin Cunha, Emanoel dos Santos +6Skin Lesion ClassificationDomain Adaptation

    Centro de Informática, Universidade Federal de Pernambuco, Brazil

  26. Prefer-DAS: Learning from Local Preferences and Sparse Prompts for Domain Adaptive Segmentation of Electron Microscopy

    Feb 23, 2026Jiabao Chen, Shan Xiong, Jialin PengDomain AdaptationUnsupervised Domain Adaptation

    College of Computer Science and Technology, Huaqiao University, Xiamen 361021, China

  27. Fairness-Aware Partial-label Domain Adaptation for Voice Classification of Parkinson's and ALS

    Feb 20, 2026Arianna Francesconi, Zhixiang Dai, Arthur Stefano Moscheni +7Parkinson's Disease Detection from SpeechDomain Adaptation

    School of Computer and Communication Sciences, EPFL (École polytechnique fédérale de Lausanne), Lausanne, Switzerland · Unit of Artificial Intelligence and Computer Systems, Università Campus Bio-Medico di Roma, Rome, Italy · Eustema S.p.A., Research and Development Centre, Naples, Italy +2

  28. Improving Generalizability of Hip Fracture Risk Prediction via Domain Adaptation Across Multiple Cohorts

    Feb 20, 2026Shuo Sun, Meiling Zhou, Chen Zhao +8Cross-Dataset GeneralizationClinical Risk Prediction

    Department of Mathematical Sciences, Michigan Technological University, Houghton, MI, USA · Department of Statistics, Grand Valley State University, Allendale, MI, USA · Department of Computer Science, Kennesaw State University, Marietta, GA, USA +6

  29. Text-only adaptation in LLM-based ASR through text denoising

    Jan 28, 2026Andrés Carofilis, Sergio Burdisso, Esaú Villatoro-Tello +8Domain Adaptation for ASRDomain Adaptation

    Idiap Research Institute · EPFL, Lausanne · Uniphore +2

  30. Predict the Retrieval! Test time adaptation for Retrieval Augmented Generation

    Jan 16, 2026Xin Sun, Zhongqi Chen, Qiang Liu +5Retrieval-Augmented GenerationTest-Time Adaptation

    NLPR, MAIS, CASIA · Ant Group · USTC