Box Classification on OVCOCO 2017 (val)
52.3Top-1 AccuracyFG-CLIP
Evaluation Results
| Method | Links | |
|---|---|---|
| FG-CLIPBackbone=ViT-B/16, Data Enhancement=true2025.11 | 52.3 | |
| FineCLIPBackbone=ViT-B/16, Data Enhancement=true2025.11 | 48.4 | |
| CLIPSelfBackbone=ViT-B/16, Data Enhancement=false2025.11 | 43.7 | |
| HarmoCLIPBackbone=ViT-B/16, Data Enhancement=false2025.11 | 43.2 | |
| RegionCLIPBackbone=RN50, Data Enhancement=false2025.11 | 40 | |
| CLIPBackbone=ViT-B/16, Data Enhancement=false2025.11 | 31.1 | |
| EVA-CLIPBackbone=ViT-B/16, Data Enhancement=false2025.11 | 30.6 |