Domain Adaptation

Follow this topic Ask about this topic

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

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

A General Representation-Based Approach to Multi-Source Domain Adaptation
Apr 26, 2026Ignavier Ng, Yan Li, Zijian Li +3Multi-Source Domain Adaptation Unsupervised Domain Adaptation
Carnegie Mellon University · Mohamed bin Zayed University of Artificial Intelligence
Unlocking Optical Prior: Spectrum-Guided Knowledge Transfer for SAR Generalized Category Discovery
Apr 24, 2026Jingyuan Xia, Ruikang Hu, Ye Li +3Domain Adaptation Frequency-Domain Feature Learning
College of Electronic Science and Technology, National University of Defense Technology, Changsha, 410073, China · State Key Laboratory of Complex System Simulation and Modeling Technology, Beijing, 100091, China
Knowledge-driven Augmentation and Retrieval for Integrative Temporal Adaptation
Apr 23, 2026Weisi Liu, Guangzeng Han, Xiaolei HuangDomain Adaptation Retrieval-Augmented Classification
University of Memphis
SyMTRS: Benchmark Multi-Task Synthetic Dataset for Depth, Domain Adaptation and Super-Resolution in Aerial Imagery
Apr 23, 2026Safouane El Ghazouali, Nicola Venturi, Michael Rueegsegger +1Domain Adaptation Monocular Depth Estimation
TOELT LLC AI lab / HSLU Winterthur, Swintzerland · Competence Center for Artificial Intelligence and Simulation, armasuisse S+T, 3602 Thun, Switzerland
Back to Source: Open-Set Continual Test-Time Adaptation via Domain Compensation
Apr 23, 2026Yingkai Yang, Chaoqi Chen, Hui HuangDomain Adaptation Continual Test-Time Adaptation
College of Computer Science and Software Engineering, Shenzhen University
Cross-Domain Data Selection and Augmentation for Automatic Compliance Detection
Apr 23, 2026Fariz Ikhwantri, Dusica MarijanDomain Adaptation Training Data Selection
Validation Intelligence for Autonomous Software Systems Simula Research Laboratory Oslo, Norway
Stabilizing In-Context Multi-Source Domain Adaptation for Biomedical Images Through Controls
Apr 22, 2026Ana Sanchez-Fernandez, Thomas Pinetz, Werner Zellinger +1Multi-Source Domain Adaptation Batch Effect Correction
ELLIS Unit Linz, LIT AI Lab and Institute for Machine Learning, JKU Linz, Austria · Institute of Artificial Intelligence, Center for Medical Data Science, Medical University Vienna · Clinical Research Center for Medical AI, JKU Linz, Austria
CoDA: Towards Effective Cross-domain Knowledge Transfer via CoT-guided Domain Adaptation
Apr 21, 2026Jianzhi Yan, Le Liu, Buzhou Tang +3Domain Adaptation Cross-Domain Transfer Learning
Harbin Institute of Technology, Shenzhen, 518100, China · Pengcheng Laboratory, Shenzhen, 518100, China
Variational Autoencoder Domain Adaptation for Cross-System Generalization in ML-Based SOP Monitoring
Apr 20, 2026Leyla Sadighi, Stefan Karlsson, Carlos Natalino +7Domain Adaptation
School of Computer Science and Statistics, IRIS research group, ADAPT Centre, Trinity College Dublin (TCD), Dublin, Ireland · 3Micropol Fiberoptics AB, Stockholm, Sweden · Department of Electrical Engineering, Chalmers University of Technology, Gothenburg, Sweden +2
Evaluating Hallucinations in Domain-Adapted Large Language Models
Apr 19, 2026Sanchita Porwal, Sai Prasath S, Xingjian Bi +1LLM Evaluation Domain Adaptation
College of Computing Georgia Institute of Technology Atlanta, GA 30318, USA
Trustworthy deep domain adaptation for wearable photoplethysmography signal analysis with decision-theoretic uncertainty quantification
Apr 19, 2026Ciaran BenchUncertainty Quantification Domain Adaptation
Department of Data Science and AI National Physical Laboratory Teddington, UK
PA-TCNet: Pathology-Aware Temporal Calibration with Physiology-Guided Target Refinement for Cross-Subject Motor Imagery EEG Decoding in Stroke Patients
Apr 17, 2026Xiangkai Wang, Yun Zhao, Dongyi He +5Cross-Subject EEG Decoding Brain-Computer Interfaces
School of Artificial Intelligence, Chongqing University of Technology, Chongqing 401135, China; Chongqing Key Laboratory of Embodied Intelligence Perception and Autonomous Learning for Humanoid Robots; Key Laboratory of Advanced Equipment Intelligence of the Chongqing Education Commission, Chongqing 401135, China · School of Smart Health, Chongqing Polytechnic University of Electronic Technology, Chongqing 401131, China · Department of Language Science and Technology, The Hong Kong Polytechnic University, Hung Hom, Hong Kong SAR, China +2
BioTrain: Sub-MB, Sub-50mW On-Device Fine-Tuning for Edge-AI on Biosignals
Apr 14, 2026Run Wang, Victor J. B. Jung, Philip Wiese +5On-Device Training Fine-Tuning
Integrated Systems Laboratory (IIS), ETH Zurich, Switzerland · Department of Electrical, Electronic and Information Engineering (DEI), University of Bologna, Italy · Department of Control and Computer Engineering (DAUIN), Politecnico di Torino, Italy
Clustering-Enhanced Domain Adaptation for Cross-Domain Intrusion Detection in Industrial Control Systems
Apr 14, 2026Luyao WangNetwork Intrusion Detection Domain Adaptation
University of Malaya, Malaysia
Whisper-AuT: Domain-Adapted Audio Encoder for Efficient Audio-LLM Training
Apr 12, 2026Jielin Qiu, Ming Zhu, Wenting Zhao +11Audio Representation Learning Domain Adaptation
Salesforce AI Research
PAS: Estimating the target accuracy before domain adaptation
Apr 10, 2026Raphaella Diniz, Jackson de Faria, Martin EsterDomain Adaptation Task Transferability Estimation
School of Computing Science Simon Fraser University Canada
TAPE: A two-stage parameter-efficient adaptation framework for foundation models in OCT-OCTA analysis
Apr 6, 2026Xiaofei Su, Zengshuo Wang, Minghe Sun +2Vision Foundation Model Adaptation Medical Image Segmentation
Nankai University Optometry & Vision Science Institute, National Key Laboratory of Intelligent Tracking and Forecasting for Infectious Diseases, Tianjin Key Laboratory of Intelligent Robotic, Institute of Robotics and Automatic Information System, Nankai University, Tianjin, 300350, China · Institute of Intelligence Technology and Robotic Systems, Shenzhen Research Institute of Nankai University, Shenzhen, 518083, China
DSBD: Dual-Aligned Structural Basis Distillation for Graph Domain Adaptation
Apr 3, 2026Yingxu Wang, Kunyu Zhang, Jiaxin Huang +4Graph Domain Adaptation Domain Adaptation
Zhengzhou University · The Hebei University of Technology · California State Polytechnic University +1
Transfer Learning for Loan Recovery Prediction under Distribution Shifts with Heterogeneous Feature Spaces
Apr 3, 2026Christopher Gerling, Hanqiu Peng, Ying Chen +1Cross-Domain Transfer Learning Domain Adaptation
Humboldt-Universität zu Berlin, Unter den Linden 6, 10099 Berlin, Germany · National University of Singapore, 10 Lower Kent Ridge Road, Singapore 119076, Singapore
$k$ NNProxy: Efficient Training-Free Proxy Alignment for Black-Box Zero-Shot LLM-Generated Text Detection
Apr 2, 2026Kahim Wong, Kemou Li, Haiwei Wu +1AI-Generated Text Detection Robustness of Machine-Generated Text Detection
State Key Laboratory of Internet of Things for Smart City and the Department of Computer and Information Science, Faculty of Science and Technology, University of Macau, Macao 999078, China · School of Information and Software Engineering, University of Electronic Science and Technology of China, Chengdu 611731, China
MIRANDA: MId-feature RANk-adversarial Domain Adaptation toward climate change-robust ecological forecasting with deep learning
Apr 1, 2026Yuchang Jiang, Jan Dirk Wegner, Vivien Sainte Fare GarnotDomain Adaptation Domain-Adversarial Learning
DM3L, UZH, Zurich, Switzerland
Fisheye3R: Adapting Unified 3D Feed-Forward Foundation Models to Fisheye Lenses
Mar 30, 2026Ruxiao Duan, Erin Hong, Dongxu Zhao +33D Foundation Models Domain Adaptation
Yale University · Google
UniDA3D: A Unified Domain-Adaptive Framework for Multi-View 3D Object Detection
Mar 30, 2026Hongjing Wu, Cheng Chi, Jinlin Wu +3Multi-View 3D Object Detection Autonomous Driving Perception
the Shenzhen Campus of Sun Yat-sen University, Shenzhen, China · The State Key Laboratory of Blockchain and Data Security, Zhejiang University, Hangzhou, China · the Beijing Academy of Artificial Intelligence, Beijing, China +2
Tunable Domain Adaptation Using Unfolding
Mar 27, 2026Snehaa Reddy, Jayaprakash Katual, Satish MulletiDomain Adaptation
The authors are with the Department of Electrical Engineering, Indian Institute of Technology Bombay, Mumbai, India.
GUIDE: Resolving Domain Bias in GUI Agents through Real-Time Web Video Retrieval and Plug-and-Play Annotation
Mar 27, 2026Rui Xie, Zhi Gao, Chenrui Shi +3Multimodal RAG Domain Adaptation
Shanghai Jiao Tong University, Shanghai, China · State Key Laboratory for General Artificial Intelligence, BIGAI, Beijing, China · Beijing Institute of Technology, Beijing, China
Dual-branch Graph Domain Adaptation for Cross-scenario Multi-modal Emotion Recognition
Mar 27, 2026Yuntao Shou, Jun Zhou, Tao Meng +2Graph Domain Adaptation Emotion Recognition in Conversations
College of Computer and Mathematics, Central South University of Forestry and Technology · Department of Computer Science, State University of New York
Toward domain-specific machine translation and quality estimation systems
Mar 26, 2026Javad Pourmostafa Roshan SharamiMachine Translation Domain Adaptation
Realiz3D: 3D Generation Made Photorealistic via Domain-Aware Learning
Mar 25, 2026Ido Sobol, Kihyuk Sohn, Yoav Blum +4Multi-View Image Synthesis Image Generation
Technion · Meta AI
Probabilistic Geometric Alignment via Bayesian Latent Transport for Domain-Adaptive Foundation Models
Mar 24, 2026Aueaphum Aueawatthanaphisut, Kuepon AuewattanapisutPAC-Bayesian Theory Domain Adaptation
School of Information, Computer, and Communication Technology Sirindhorn International Institute of Technology, Thammasat University Pathumthani, Thailand · epartment of Architecture, Faculty of Architecture Khon Kaen University Khon Kaen, Thailand
Adapting Self-Supervised Speech Representations for Cross-lingual Dysarthria Detection in Parkinson's Disease
Mar 23, 2026Abner Hernandez, Eunjung Yeo, Kwanghee Choi +12Self-Supervised Speech Representation Learning Domain Adaptation
1FAU Erlangen-Nürnberg, Germany · 2UT Austin, USA · 3CMU, USA +5

Apr 26, 2026J/K move · Enter open · S save

A General Representation-Based Approach to Multi-Source Domain Adaptation

Ignavier Ng, Yan Li, Zijian Li, Yujia Zheng+2

Carnegie Mellon University · Mohamed bin Zayed University of Artificial Intelligence

Multi-Source Domain Adaptation Unsupervised Domain Adaptation Domain Adaptation Predictive Representation Learning

Open paper AskPDF arXiv

A central problem in unsupervised domain adaptation is determining what to transfer from labeled source domains to an unlabeled target domain. To handle high-dimensional observations (e.g., images), a line of approaches use deep learning to learn latent representations of the observations, which facilitate knowledge transfer in the latent space. However, existing approaches often rely on restrictive assumptions to establish identifiability of the joint distribution in the target domain, such as independent latent variables or invariant label distributions, limiting their real-world applicability. In this work, we propose a general domain adaptation framework that learns compact latent representations to capture distribution shifts relative to the prediction task and address the fundamental question of what representations should be learned and transferred. Notably, we first demonstrate that learning representations based on all the predictive information, i.e., the label's Markov blanket in terms of the learned representations, is often underspecified in general settings. Instead, we show that, interestingly, general domain adaptation can be achieved by partitioning the representations of Markov blanket into those of the label's parents, children, and spouses. Moreover, its identifiability guarantee can be established. Building on these theoretical insights, we develop a practical, nonparametric approach for domain adaptation in a general setting, which can handle different types of distribution shifts.