Visual Grounding on RefPath 20x magnification 1.0 (test)
61.66AccuracyPKNet
Evaluation results
| Method | Links | ||
|---|---|---|---|
| PKNetVisual/Text Encoder=RN50/BERT-B2025.02 | 61.66 | 52.95 | |
| D-MDETRVenue=TPAMI'24, Visual/Text Encoder=CLIP-B/CLIP-B2025.02 | 55.98 | 45.57 | |
| LLaVa-MedVenue=NeuIPS'23, Visual/Text Encoder=CLIP-L/LLaMa2025.02 | 53.51 | 48.31 | |
| SimVGVenue=NeurIPS'24, Visual/Text Encoder=ViT-B/BERT-B2025.02 | 52.52 | 46.92 | |
| TransCPVenue=TPAMI'24, Visual/Text Encoder=RN50/BERT-B2025.02 | 51.87 | 44.93 | |
| TransVGVenue=ICCV'21, Visual/Text Encoder=RN50/BERT-B2025.02 | 50.29 | 41.94 | |
| CLIPVGVenue=TMM'23, Visual/Text Encoder=CLIP-B/CLIP-B2025.02 | 45.81 | 39.67 | |
| SeqTRVenue=ECCV'22, Visual/Text Encoder=DN53/BiGRU2025.02 | 42.57 | 36.78 |