Unsupervised Domain Adaptation
Unsupervised Domain Adaptation is a learning framework to transfer knowledge learned from source domains with a large number of annotated training examples to target domains with unlabeled data only.
Source: Domain-Specific Batch Normalization for Unsupervised Domain Adaptation
Papers
Showing 1–10 of 1951 papers
All datasetsDuke to MarketMarket to DukeCityscapes-to-Foggy CityscapesOffice-HomeMarket to MSMTImageNet-CSYNTHIA-to-CityscapesVehicleID to VeRi-776Duke to MSMTSIM10K to CityscapesVeri-776 to VehicleID LargeVeri-776 to VehicleID Medium
Benchmark Results
| # | Model | Metric | Claimed | Verified | Status |
|---|---|---|---|---|---|
| 1 | FFTAT | Accuracy | 91.4 | — | Unverified |
| 2 | TransAdapter-B | Accuracy | 89.4 | — | Unverified |
| 3 | SAMB | Accuracy | 86.2 | — | Unverified |
| 4 | PDA (CLIP, ViT-B/16) | Accuracy | 85.7 | — | Unverified |
| 5 | SSRT-B | Accuracy | 85.43 | — | Unverified |
| 6 | EUDA | Accuracy | 84.9 | — | Unverified |
| 7 | ProDe | Accuracy | 84.5 | — | Unverified |
| 8 | ECB (CNN) | Accuracy | 81.2 | — | Unverified |
| 9 | CDTrans | Accuracy | 80.5 | — | Unverified |
| 10 | JAN [cite:ICML17JAN] | Accuracy | 76.8 | — | Unverified |