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 | MIC+CSI | mIoU (13 classes) | 75.9 | — | Unverified |
| 2 | DCF | mIoU (13 classes) | 75.9 | — | Unverified |
| 3 | DIDA | mIoU (13 classes) | 70.1 | — | Unverified |
| 4 | Sepico + HIAST | mIoU (13 classes) | 68.1 | — | Unverified |
| 5 | CLUDA+HRDA | mIoU | 67.2 | — | Unverified |
| 6 | SePiCo (DeepLabv2 ResNet-101) | mIoU (13 classes) | 66.5 | — | Unverified |
| 7 | G2L | mIoU (13 classes) | 64.4 | — | Unverified |
| 8 | DAFormer+CSI | mIoU | 61.4 | — | Unverified |
| 9 | FAFS | mIoU (13 classes) | 61.4 | — | Unverified |
| 10 | AdaptSeg + HIAST | mIoU (13 classes) | 60.3 | — | Unverified |