Visual Grounding on RefPath 40x magnification 1.0 (test)
80.48AccPKNet
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| PKNetVisual/Text Encoder=RN50/BERT-B2025.02 | 80.48 | 76.88 | |
| D-MDETRVenue=TPAMI'24, Visual/Text Encoder=CLIP-B/CLIP-B2025.02 | 76.29 | 73.1 | |
| CLIPVGVenue=TMM'23, Visual/Text Encoder=CLIP-B/CLIP-B2025.02 | 75.52 | 72.14 | |
| SimVGVenue=NeurIPS'24, Visual/Text Encoder=ViT-B/BERT-B2025.02 | 75.36 | 73.18 | |
| TransCPVenue=TPAMI'24, Visual/Text Encoder=RN50/BERT-B2025.02 | 74.27 | 71.92 | |
| LLaVa-MedVenue=NeuIPS'23, Visual/Text Encoder=CLIP-L/LLaMa2025.02 | 73.52 | 70.24 | |
| SeqTRVenue=ECCV'22, Visual/Text Encoder=DN53/BiGRU2025.02 | 72.65 | 71.13 | |
| TransVGVenue=ICCV'21, Visual/Text Encoder=RN50/BERT-B2025.02 | 68.72 | 66.75 |