mlsanityData to 14 Oct 2026

VisDA: The Visual Domain Adaptation Challenge

arXiv 1710.06924 ↗First posted 18 Oct 2017cs.CVcited by 435

Not on the map. Why?

Abstract (arXiv)

We present the 2017 Visual Domain Adaptation (VisDA) dataset and challenge, a large-scale testbed for unsupervised domain adaptation across visual domains. Unsupervised domain adaptation aims to solve the real-world problem of domain shift, where machine learning models trained on one domain must be transferred and adapted to a novel visual domain without additional supervision. The VisDA2017 challenge is focused on the simulation-to-reality shift and has two associated tasks: image classification and image segmentation. The goal in both tracks is to first train a model on simulated, synthetic data in the source domain and then adapt it to perform well on real image data in the unlabeled test domain. Our dataset is the largest one to date for cross-domain object classification, with over 280K images across 12 categories in the combined training, validation and testing domains. The image segmentation dataset is also large-scale with over 30K images across 18 categories in the three domains. We compare VisDA to existing cross-domain adaptation datasets and provide a baseline performance analysis using various domain adaptation models that are currently popular in the field.

Key facts. Cited by 435 papers in the map (data through 14 Oct 2026). First posted on arXiv 18 Oct 2017.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 90; 2022: 97; 2023: 99; 2024: 74; 2025: 47; 2026: 28.

435 papers.

Sort:

By area:

  1. 2021Domain Generalization: A Surveycited by 764
  2. 2021MEMO: Test Time Robustness via Adaptation and Augmentationcited by 377
  3. 2022Is synthetic data from generative models ready for image recognition?cited by 320
  4. 2022Contrastive Test-Time Adaptationcited by 261
  5. 2022MIC: Masked Image Consistency for Context-Enhanced Domain Adaptationcited by 178
  6. 2021Exploiting the Intrinsic Neighborhood Structure for Source-free Domain Adaptationcited by 177
  7. 2021Generalized Source-free Domain Adaptationcited by 175
  8. 2021CDTrans: Cross-domain Transformer for Unsupervised Domain Adaptationcited by 129
  9. 2022Domain Adaptation via Prompt Learningcited by 128
  10. 2021Unbalanced minibatch Optimal Transport; applications to Domain Adaptationcited by 125
  11. 2021Cycle Self-Training for Domain Adaptationcited by 120
  12. 2021Deep Subdomain Adaptation Network for Image Classificationcited by 119
38 more
  1. 2021Predicting with Confidence on Unseen Distributionscited by 116
  2. 2021Open Domain Generalization with Domain-Augmented Meta-Learningcited by 115
  3. 2021Source-free Domain Adaptation via Avatar Prototype Generation and Adaptationcited by 111
  4. 2023A Comprehensive Survey on Source-free Domain Adaptationcited by 104
  5. 2022BigDatasetGAN: Synthesizing ImageNet with Pixel-wise Annotationscited by 99
  6. 2022Test-Time Adaptation via Conjugate Pseudo-labelscited by 98
  7. 2022Deep Unsupervised Domain Adaptation: A Review of Recent Advances and Perspectivescited by 98
  8. 2022Source-Free Domain Adaptation via Distribution Estimationcited by 97
  9. 2022Visual Prompt Tuning for Test-time Domain Adaptationcited by 97
  10. 2022Attracting and Dispersing: A Simple Approach for Source-free Domain Adaptationcited by 94
  11. 2023Improving Multimodal Datasets with Image Captioningcited by 93
  12. 2021OVANet: One-vs-All Network for Universal Domain Adaptationcited by 92
  13. 2021Prototypical Cross-domain Self-supervised Learning for Few-shot Unsupervised Domain Adaptationcited by 83
  14. 2021TVT: Transferable Vision Transformer for Unsupervised Domain Adaptationcited by 81
  15. 2022Source-Free Unsupervised Domain Adaptation: A Surveycited by 80
  16. 2021Cross-domain Contrastive Learning for Unsupervised Domain Adaptationcited by 76
  17. 2021Enhancing Photorealism Enhancementcited by 74
  18. 2023Battle of the Backbones: A Large-Scale Comparison of Pretrained Models across Computer Vision Taskscited by 72
  19. 2022Back to the Source: Diffusion-Driven Test-Time Adaptationcited by 71
  20. 2021Test-Time Adaptation to Distribution Shift by Confidence Maximization and Input Transformationcited by 68
  21. 2021Cross-Domain Gradient Discrepancy Minimization for Unsupervised Domain Adaptationcited by 67
  22. 2022Reusing the Task-specific Classifier as a Discriminator: Discriminator-free Adversarial Domain Adaptationcited by 66
  23. 2023Guiding Pseudo-labels with Uncertainty Estimation for Source-free Unsupervised Domain Adaptationcited by 65
  24. 2021MixStyle Neural Networks for Domain Generalization and Adaptationcited by 64
  25. 2021What Does Rotation Prediction Tell Us about Classifier Accuracy under Varying Testing Environments?cited by 63
  26. 2023AD-CLIP: Adapting Domains in Prompt Space Using CLIPcited by 62
  27. 2022Safe Self-Refinement for Transformer-based Domain Adaptationcited by 61
  28. 2022Confidence Score for Source-Free Unsupervised Domain Adaptationcited by 59
  29. 2022Balancing Discriminability and Transferability for Source-Free Domain Adaptationcited by 58
  30. 2021SPEED+: Next-Generation Dataset for Spacecraft Pose Estimation across Domain Gapcited by 57
  31. 2022Unified Optimal Transport Framework for Universal Domain Adaptationcited by 57
  32. 2021Transferable Semantic Augmentation for Domain Adaptationcited by 56
  33. 2023Label-Free Liver Tumor Segmentationcited by 56
  34. 2023Source-Free Domain Adaptation with Frozen Multimodal Foundation Modelcited by 55
  35. 2023Patch-Mix Transformer for Unsupervised Domain Adaptation: A Game Perspectivecited by 54
  36. 2021Dynamic Weighted Learning for Unsupervised Domain Adaptationcited by 53
  37. 2021Active Learning for Domain Adaptation: An Energy-Based Approachcited by 53
  38. 2022Divide and Contrast: Source-free Domain Adaptation via Adaptive Contrastive Learningcited by 53

50 most cited of 435 All 435 (JSON)