mlsanityData to 7 Oct 2026

Deep Visual Domain Adaptation

arXiv 2012.14176 ↗First posted 28 Dec 2020cs.CVcited by 91

Not on the map. Why?

Abstract (arXiv)

Domain adaptation (DA) aims at improving the performance of a model on target domains by transferring the knowledge contained in different but related source domains. With recent advances in deep learning models which are extremely data hungry, the interest for visual DA has significantly increased in the last decade and the number of related work in the field exploded. The aim of this paper, therefore, is to give a comprehensive overview of deep domain adaptation methods for computer vision applications. First, we detail and compared different possible ways of exploiting deep architectures for domain adaptation. Then, we propose an overview of recent trends in deep visual DA. Finally, we mention a few improvement strategies, orthogonal to these methods, that can be applied to these models. While we mainly focus on image classification, we give pointers to papers that extend these ideas for other applications such as semantic segmentation, object detection, person re-identifications, and others.

Key facts. Cited by 91 papers in the map (data through 7 Oct 2026). First posted on arXiv 28 Dec 2020.

Builds on

No reference list yet.

Built on by

Cited by year

Citing papers per year: 2021: 33; 2022: 35; 2023: 22; 2024: 1.

91 papers.

Sort:

By area:

  1. 2021MeGA-CDA: Memory Guided Attention for Category-Aware Unsupervised Domain Adaptive Object Detectioncited by 106
  2. 2021Model-Based Domain Generalizationcited by 103
  3. 2022Deep Unsupervised Domain Adaptation: A Review of Recent Advances and Perspectivescited by 98
  4. 2021TVT: Transferable Vision Transformer for Unsupervised Domain Adaptationcited by 81
  5. 2023CLIP goes 3D: Leveraging Prompt Tuning for Language Grounded 3D Recognitioncited by 77
  6. 2021MT3: Meta Test-Time Training for Self-Supervised Test-Time Adaptioncited by 65
  7. 2021Multi-Modal 3D Object Detection in Autonomous Driving: a Surveycited by 63
  8. 2021Regularizing Nighttime Weirdness: Efficient Self-supervised Monocular Depth Estimation in the Darkcited by 57
  9. 2021DORO: Distributional and Outlier Robust Optimizationcited by 54
  10. 2021ACAV100M: Automatic Curation of Large-Scale Datasets for Audio-Visual Video Representation Learningcited by 50
  11. 2021Contrast and Mix: Temporal Contrastive Video Domain Adaptation with Background Mixingcited by 49
  12. 2023Synthetic Datasets for Autonomous Driving: A Surveycited by 48
38 more
  1. 2022Domain Adaptive Object Detection for Autonomous Driving under Foggy Weathercited by 41
  2. 2021Towards Robust and Adaptive Motion Forecasting: A Causal Representation Perspectivecited by 40
  3. 2022Attention Consistency on Visual Corruptions for Single-Source Domain Generalizationcited by 37
  4. 2021Specificity-Preserving Federated Learning for MR Image Reconstructioncited by 35
  5. 2022Audio-Adaptive Activity Recognition Across Video Domainscited by 35
  6. 2022Neural Optimal Transport with General Cost Functionalscited by 34
  7. 2023Cross-Modal Fine-Tuning: Align then Refinecited by 34
  8. 2022Temporal Domain Generalization with Drift-Aware Dynamic Neural Networkscited by 32
  9. 2021The Multi-Agent Behavior Dataset: Mouse Dyadic Social Interactionscited by 31
  10. 2023Joint Learning of Label and Environment Causal Independence for Graph Out-of-Distribution Generalizationcited by 29
  11. 2021In the light of feature distributions: moment matching for Neural Style Transfercited by 26
  12. 2021An Information-theoretic Approach to Distribution Shiftscited by 25
  13. 2023Meta-learning approaches for few-shot learning: A survey of recent advancescited by 25
  14. 2022On the Road to Online Adaptation for Semantic Image Segmentationcited by 23
  15. 2021Cross-domain Activity Recognition via Substructural Optimal Transportcited by 21
  16. 2021Unsupervised Domain Adaptation in LiDAR Semantic Segmentation with Self-Supervision and Gated Adapterscited by 21
  17. 2021Unsupervised Domain Adaptation for Semantic Image Segmentation: a Comprehensive Surveycited by 19
  18. 2023Anatomy-aware and acquisition-agnostic joint registration with SynthMorphcited by 19
  19. 2021Domain-Adversarial Training of Self-Attention Based Networks for Land Cover Classification using Multi-temporal Sentinel-2 Satellite Imagerycited by 18
  20. 2021Blind Image Decompositioncited by 18
  21. 2023Domain Re-Modulation for Few-Shot Generative Domain Adaptationcited by 18
  22. 2023Choosing Public Datasets for Private Machine Learning via Gradient Subspace Distancecited by 14
  23. 2021Recent Advances in Leveraging Human Guidance for Sequential Decision-Making Taskscited by 13
  24. 2022Deep transfer learning for image classification: a surveycited by 13
  25. 2022Visuo-Haptic Object Perception for Robots: An Overviewcited by 12
  26. 2022Motion Style Transfer: Modular Low-Rank Adaptation for Deep Motion Forecastingcited by 12
  27. 2021REGRAD: A Large-Scale Relational Grasp Dataset for Safe and Object-Specific Robotic Grasping in Cluttercited by 11
  28. 2022Towards out of distribution generalization for problems in mechanicscited by 11
  29. 2021Transfer Learning for Pose Estimation of Illustrated Characterscited by 10
  30. 2021On the Statistical Benefits of Curriculum Learningcited by 10
  31. 2023Graph Structure and Feature Extrapolation for Out-of-Distribution Generalizationcited by 10
  32. 2021Continual 3D Convolutional Neural Networks for Real-time Processing of Videoscited by 9
  33. 2022Self-Supervised Moving Vehicle Detection from Audio-Visual Cuescited by 8
  34. 2022Explainable, Domain-Adaptive, and Federated Artificial Intelligence in Medicinecited by 8
  35. 2021TraND: Transferable Neighborhood Discovery for Unsupervised Cross-domain Gait Recognitioncited by 7
  36. 2021Randomized Histogram Matching: A Simple Augmentation for Unsupervised Domain Adaptation in Overhead Imagerycited by 7
  37. 2022Neuro-Symbolic Learning: Principles and Applications in Ophthalmologycited by 7
  38. 2023Reverse Engineering Breast MRIs: Predicting Acquisition Parameters Directly from Imagescited by 7

50 most cited of 91 All 91 (JSON)