Image Classification on TQ-T3D unseen target
59.3AccuracyOmniVaT
Evaluation results
| Method | Links | ||
|---|---|---|---|
| OmniVaTBackbone=ViT-B / 16, Pre-trained=CLIP, Source Domain=TAG, Venue=Ours2026.01 | 59.3 | 60.5 | |
| PromptStylerBackbone=ViT-B / 16, Pre-trained=CLIP, Source Domain=TAG, Venue=ICCV-232026.01 | 58.4 | 44.4 | |
| SPGBackbone=ViT-B / 16, Pre-trained=CLIP, Source Domain=TAG, Venue=ECCV-242026.01 | 58.2 | 57.8 | |
| MMRLBackbone=ViT-B / 16, Pre-trained=CLIP, Source Domain=TAG, Venue=CVPR-252026.01 | 57.1 | 26.4 | |
| LDCBackbone=ViT-B / 16, Pre-trained=CLIP, Source Domain=TAG, Venue=CVPR-252026.01 | 57.1 | 30.1 | |
| CLIPBackbone=ViT-B / 16, Pre-trained=CLIP, Source Domain=TAG, Venue=ICML-212026.01 | 56.9 | 51.5 |