Image Classification on TQ-DuraGel (unseen target)
56.1AccuracyOmniVaT
Evaluation results
| Method | Links | ||
|---|---|---|---|
| OmniVaTBackbone=ViT-B / 16, Pre-trained=CLIP, Source Domain=TAG, Venue=Ours2026.01 | 56.1 | 59.2 | |
| SPGBackbone=ViT-B / 16, Pre-trained=CLIP, Source Domain=TAG, Venue=ECCV-242026.01 | 54.7 | 43 | |
| MMRLBackbone=ViT-B / 16, Pre-trained=CLIP, Source Domain=TAG, Venue=CVPR-252026.01 | 54.4 | 52.5 | |
| LDCBackbone=ViT-B / 16, Pre-trained=CLIP, Source Domain=TAG, Venue=CVPR-252026.01 | 54.2 | 33.6 | |
| PromptStylerBackbone=ViT-B / 16, Pre-trained=CLIP, Source Domain=TAG, Venue=ICCV-232026.01 | 53.6 | 49.3 | |
| CLIPBackbone=ViT-B / 16, Pre-trained=CLIP, Source Domain=TAG, Venue=ICML-212026.01 | 44.4 | 31.8 |