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++ | mAP@0.5 | 77.8 | — | Unverified |
| 2 | ALDI-YOLO | mAP@0.5 | 75 | — | Unverified |
| 3 | MIC(ALDI frame) | mAP@0.5 | 73.1 | — | Unverified |
| 4 | AT(ALDI frame) | mAP@0.5 | 72 | — | Unverified |
| 5 | SADA(ALDI frame) | mAP@0.5 | 71.8 | — | Unverified |
| 6 | PT(ALDI frame) | mAP@0.5 | 70.6 | — | Unverified |
| 7 | RT-DATR(real-time, 640x640) | mAP@0.5 | 67.2 | — | Unverified |
| 8 | DDT | mAP@0.5 | 64 | — | Unverified |
| 9 | MRT | mAP@0.5 | 62 | — | Unverified |
| 10 | MILA | mAP@0.5 | 57.4 | — | Unverified |