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 | ALDI++(Resnet50+FPN) | mAP@0.5 | 66.8 | — | Unverified |
| 2 | RT-DATR(640x640, real-time) | mAP@0.5 | 52.7 | — | Unverified |
| 3 | MRT | mAP@0.5 | 51.2 | — | Unverified |
| 4 | DDT | mAP@0.5 | 50 | — | Unverified |
| 5 | MIC | mAP@0.5 | 47.6 | — | Unverified |
| 6 | O2net | mAP@0.5 | 46.8 | — | Unverified |
| 7 | LGCL (supervised) | mAP@0.5 | 46.7 | — | Unverified |
| 8 | LGCL (unsupervised) | mAP@0.5 | 45.3 | — | Unverified |
| 9 | SAD | mAP@0.5 | 45.2 | — | Unverified |
| 10 | AWADA | mAP@0.5 | 44.8 | — | Unverified |