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

268 papers21 papers in the last four weeks, down 25% on the four weeks before. 0.2% of all new papers.

  1. Source-Free Domain Adaptation for Multi-Label Image Classification: A Framework, Baselines, and Benchmark

    Nov 16, 2026Salih Numan Büyükbaş, Erchan Aptoula, Mamatha Thota +1Source-Free Domain AdaptationDomain Adaptation

  2. DRA-HTR: Disentangling Representation and Adaptation for Handwritten Text Recognition

    Nov 13, 2026Gayan H. Pathirage, Florent Imbert, Denis Coquenet +1Domain AdaptationUnsupervised Domain Adaptation

  3. Domain Adaptation Based Pipeline for Character Classification and Handwritten Text Recognition

    Nov 13, 2026Florent Imbert, Simon Corbillé, Hui Han +1Optical Character RecognitionDomain Adaptation

  4. Hybrid quantum learning for imbalanced blood-cell classification: domain adaptation and classifier design

    Nov 11, 2026Gabriele D'Angeli, Cyrill Aebischer, Eryk Schiller +4Medical Image ClassificationHybrid Quantum-Classical ML

  5. Domain-Adversarial Adaptation from MURA to In-House Radiographs for Improved Adult Elbow Fracture Classification

    Nov 9, 2026M. Bolhassani, W. Furtado, D. Duvall +4Domain AdaptationMedical Imaging

  6. Discriminator-free adversarial domain adaptation for robust speech classification

    Nov 9, 2026Yacouba Kaloga, Ina KodrasiDomain AdaptationUnsupervised Domain Adaptation

  7. The comparison of density estimation for transfer learning in Banach, Hilbert, Euclidean spaces

    Nov 8, 2026Maryam Alsadat Kazemian, Azam BastanfardDomain AdaptationUnsupervised Domain Adaptation

  8. DAPointRWKV: Domain Adaptive Vision RWKV for Point Cloud Completion

    Nov 7, 2026Yinghui Li, Qianyu Zhou, Hao Yang +3Point Cloud CompletionDomain Adaptation

  9. FIND: Frequency Invariance Disentanglement for Test-Time Adaptation in LiDAR 3D Detection

    Nov 6, 2026Dongxiao Li, Zixuan Hu, Ling-Yu DuanLidar-Based 3D Object DetectionDomain Adaptation

  10. WearableBridge: Task-Guided Latent Transport for Free-Living Activity Recognition

    Nov 6, 2026Jingjing Zou, Yixin WangHuman Activity RecognitionWearable Sensing

  11. TEXMET: A Deep Learning Benchmark for Archaeological Textile Reconstruction

    Nov 3, 2026Muhammad Hamza Zafar, Davit Gigilashvili, Jon Yngve HardebergJigsaw Puzzle SolvingDomain Adaptation

  12. Integrating Domain Adaptation and Retrieval-Augmented Generation for Saline-Alkali Land Reclamation Planning

    Nov 2, 2026Zuguang He, Congcong Zheng, Wanyue Chen +5AI-Assisted Decision MakingRetrieval-Augmented Generation

  13. Upcycling Language Models for Multiple Specialized Domains

    Oct 29, 2026Mingzi Cao, Xi Wang, Nikolaos AletrasDomain Adaptation for LLMsDomain Adaptation

  14. Prototype-Guided Dynamic Domain Modulation and a Large-Scale Multi-SKU Benchmark for Shampoo Bottle Surface Defect Detection

    Oct 28, 2026Yuehang Li, Xiao Wang, Qiang Chen +4Industrial InspectionDomain Adaptation

  15. Beyond Wasserstein Proximity: Finding Better Transfer Sources

    Oct 26, 2026Gordei Verbii, Georgii Killinkarov, Vladimir YafarovTransfer LearningDomain Adaptation

  16. Residual Expert Routing for Text-Only Domain Adaptation of Factorized Transducer ASR

    Oct 23, 2026Shashi Kumar, Esaú Villatoro-Tello, Thibault Bañeras-Roux +4Domain Adaptation for ASRDomain Adaptation

  17. To Route or to Adapt? Multi-Expert Diffusion Planners in Unseen Regions

    Oct 22, 2026Yun Li, Ehsan Javanmardi, Simon Thompson +7Autonomous Driving PlanningDiffusion-Based Planning

  18. Learning Domain Trajectories with Flow Matching for Gradual Domain Adaptation

    Oct 22, 2026Yubo Huang, Yushe Cao, Zixi Wang +4Domain AdaptationUnsupervised Domain Adaptation

  19. No Frames, Just Frequencies: Bandwidth-Efficient Deployment-Time Adaptation for Smart Glasses

    Oct 21, 2026Francesco Corti, Moritz Becker, Olga SaukhDomain AdaptationTest-Time Adaptation

  20. Balancing Foundation Models and Trait-Specific Learning for Forehead-Crease Recognition

    Oct 21, 2026Geetanjali Sharma, Aryan Jain, Dev Nagaich +2Biometric IdentificationZero-Shot Learning

  21. Combating Catastrophic Forgetting in Continual Domain Adaptation via Knowledge Recasting

    Oct 20, 2026Zijie Liu, Zhen Tan, Charles Fleming +1Continual Learning for LLMsDomain Adaptation

  22. AdaptMIL: Domain Adaptation for Multiple Instance Learning in Digital Pathology

    Oct 20, 2026Ben Vardi, Dana Schonberger, Yuval Friedmann +4Domain AdaptationComputational Pathology

  23. Input- and Feature-Space Correction for Cross-Hospital IHC Grading

    Oct 15, 2026Jongwoon Lee, Jhair Gallardo, Christopher KananDomain AdaptationHistopathology Image Classification

  24. A large-scale climate-aware satellite image dataset for domain adaptive land-cover semantic segmentation

    Oct 15, 2026Songlin Liu, Linwei Chen, Li Zhang +2Remote Sensing Image SegmentationLand Cover Classification

  25. Improving Category-Aware Active Domain Adaptation via Uncertainty-Guided Region Coverage

    Oct 14, 2026My Tra Nguyen Huynh, Viet Cuong TaDomain AdaptationActive Learning

  26. Self-improving data synthesis can scale embedding-model adaptation across domains and tasks

    Oct 10, 2026Zucan Lyu, Rui Tang, Jianlyu Chen +2Synthetic Data GenerationInformation Retrieval

  27. Domain Adaptation of SAM 2.1 for Building-Component Segmentation in Image-Based 3D Reconstruction

    Oct 8, 2026Ehsan Agha Ebrahimi, Yong-Cheol Lee, Keith G. MillsSemantic SegmentationSegment Anything Models

  28. MemFLoRA: Memory-Floor LoRA for CNN Adaptation at the Edge

    Oct 6, 2026Mehmet Emre Akbulut, Johannes Geier, Ulf SchlichtmannOn-Device TrainingMemory-Efficient Fine-Tuning