Mask Classification on COCO-Stuff
72Mask AccuracyWOW-Seg
Evaluation Results
| Method | Links | |
|---|---|---|
| WOW-SegTraining Type=Finetuned2026.05 | 72 | |
| MaskCLIP++Architecture=ViT-L/14, Input Resolution=392 (short side), Training Protocol=Finetuned on COCO2024.12 | 67.8 | |
| MaskCLIP++Training Type=Finetuned2026.05 | 67.8 | |
| CAT-SegArchitecture=ViT-L/14, Input Resolution=392 (short side), Training Protocol=Finetuned on COCO2024.12 | 63 | |
| CAT-SegTraining Type=Finetuned2026.05 | 63 | |
| CLIPSelfArchitecture=ViT-L/14, Input Resolution=392 (short side), Training Protocol=Finetuned on COCO2024.12 | 50.6 | |
| CLIPSelfTraining Type=Finetuned2026.05 | 50.6 | |
| OpenAI CLIPArchitecture=ViT-L/14, Input Resolution=392 (short side), Training Protocol=Pretrained2024.12 | 46.2 | |
| OpenAI CLIPTraining Type=Pretrained2026.05 | 46.2 | |
| EVA02 CLIPArchitecture=ViT-L/14, Input Resolution=392 (short side), Training Protocol=Pretrained2024.12 | 45 | |
| EVA02 CLIPTraining Type=Pretrained2026.05 | 45 |