Domain Generalization
The idea of Domain Generalization is to learn from one or multiple training domains, to extract a domain-agnostic model which can be applied to an unseen domain
Source: Diagram Image Retrieval using Sketch-Based Deep Learning and Transfer Learning
Papers
Showing 1–10 of 1751 papers
All datasetsPACSVizWiz-ClassificationImageNet-COffice-HomeImageNet-AImageNet-RDomainNetVLCSTerraIncognitaGTA-to-Avg(Cityscapes,BDD,Mapillary)ImageNet-SketchGTA5 to Cityscapes
Benchmark Results
| # | Model | Metric | Claimed | Verified | Status |
|---|---|---|---|---|---|
| 1 | tqdm (EVA02-CLIP-L) | mIoU | 68.88 | — | Unverified |
| 2 | ADSI | mIoU | 67.75 | — | Unverified |
| 3 | Rein | mIoU | 66.4 | — | Unverified |
| 4 | VLTSeg (EVA02-CLIP-L) | mIoU | 65.6 | — | Unverified |
| 5 | DIFF | mIoU | 58.01 | — | Unverified |
| 6 | CMFormer | mIoU | 55.31 | — | Unverified |
| 7 | Self-adaptation (ResNet - 101) | mIoU | 46.99 | — | Unverified |
| 8 | GtA-SFDA Source-Only (DeepLabv2-ResNet101) | mIoU | 43.5 | — | Unverified |