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 | CORE-ReID V2 | mAP | 49.5 | — | Unverified |
| 2 | MATNet+DMDU | mAP | 49.25 | — | Unverified |
| 3 | MGR-GCL | mAP | 48.73 | — | Unverified |
| 4 | PLM | mAP | 47.37 | — | Unverified |
| 5 | CSP+FCD | mAP | 45.6 | — | Unverified |
| 6 | PAL | mAP | 42.04 | — | Unverified |
| 7 | CORE-ReID V2 Tiny | mAP | 40.17 | — | Unverified |
| 8 | SPCL | mAP | 38.9 | — | Unverified |
| 9 | UDAR | mAP | 35.8 | — | Unverified |
| 10 | MMT | mAP | 35.3 | — | Unverified |