Datasets › VisDA-2017
VisDA-2017
VisDA-2017 is a simulation-to-real dataset for domain adaptation with over 280,000 images across 12 categories in the training, validation and testing domains. The training images are generated from the same object under different circumstances, while the validation images are collected from MSCOCO..
Source: Gradually Vanishing Bridge for Adversarial Domain Adaptation Image Source: http://ai.bu.edu/visda-2017/
Benchmarks archive 2025-07-28
All 6 leaderboards whose dataset resolves to this page shown (sort by any header). "First row" is the archive's own first row at snapshot, in the archive's row order; nothing here re-ranks and metric direction is not asserted.
| First row (archive order) | Paper | Code | ||||
|---|---|---|---|---|---|---|
| Domain Adaptation | VisDA2017 | FFTAT Accuracy 93.8 | Feature Fusion Transferability Aware Transformer for... | Shawey94/NoisyNN +1 | 28 | Compare |
| Universal Domain Adaptation | VisDA2017 | TASC H-score 90.36 | Target Semantics Clustering via Text Representations for... | Sapphire-356/TASC | 13 | Compare |
| Unsupervised Domain Adaptation | VisDA2017 | FFTAT Accuracy 93.8 | Feature Fusion Transferability Aware Transformer for... | Shawey94/NoisyNN +1 | 13 | Compare |
| Source-Free Domain Adaptation | VisDA-2017 | RCL Accuracy 93.2 | Empowering Source-Free Domain Adaptation with... | Dong-Jie-Chen/RCL | 10 | Compare |
| Partial Domain Adaptation | VisDA2017 | SPDA Accuracy (%) 87.69 | Selective Partial Domain Adaptation | Pengxin-Guo/SPDA +1 | 3 | Compare |
| Unsupervised Domain Adaptation | VisDA-2017 | TransAdapter Accuracy 91.2 | TransAdapter: Vision Transformer for Feature-Centric... | enesdoruk/TransAdapter | 1 | Compare |
Papers archive 2025-07-28
30 shown of 53 papers with a leaderboard row on this dataset's benchmarks, newest first. The archive's own "papers using this dataset" list was never published, so this is the benchmark-backed subset; the archive's count for this dataset is 223. The Syntology column is from Syntology's graph (read 2026-09-24), stated per sample; it is not part of any archive number.
The full list of 53 is in the JSON twin.
Dataset loaders archive 2025-07-28
No loader listed in the archive.
Tasks archive 2025-07-28
License archive 2025-07-28
Modalities archive 2025-07-28
Languages archive 2025-07-28
No language tagged.
Variants archive 2025-07-28
- VisDA2017
- VisDA-2017
2 variant names, as the archive lists them.
Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections