Bounding-box classification on OVCOCO
63.2Top-1 AccuracyFG-CLIP
Evaluation Results
| Method | Links | |
|---|---|---|
| FG-CLIPBackbone=ViT-L/14, Zero-shot=true, Data enhancement=true2025.11 | 63.2 | |
| HarmoCLIPBackbone=ViT-L/14, Zero-shot=true, Data enhancement=false2025.11 | 61.05 | |
| FineCLIPBackbone=ViT-L/14, Zero-shot=true, Data enhancement=true2025.11 | 54.5 | |
| FG-CLIPBackbone=ViT-B/16, Zero-shot=true, Data enhancement=true2025.11 | 52.3 | |
| FineCLIPBackbone=ViT-B/16, Zero-shot=true, Data enhancement=true2025.11 | 48.4 | |
| EVA-CLIPBackbone=ViT-L/14, Zero-shot=true, Data enhancement=false2025.11 | 46.14 | |
| CLIPSelfBackbone=ViT-B/16, Zero-shot=true, Data enhancement=false2025.11 | 43.7 | |
| HarmoCLIPBackbone=ViT-B/16, Zero-shot=true, Data enhancement=false2025.11 | 43.2 | |
| RegionCLIPBackbone=ViT-B/16, Zero-shot=true, Data enhancement=false2025.11 | 40 | |
| CLIPBackbone=ViT-L/14, Zero-shot=true, Data enhancement=false2025.11 | 33.8 | |
| CLIPBackbone=ViT-B/16, Zero-shot=true, Data enhancement=false2025.11 | 31.1 | |
| EVA-CLIPBackbone=ViT-B/16, Zero-shot=true, Data enhancement=false2025.11 | 30.6 |