Mask Classification on ADE20K 150
68.5Mask AccuracyWOW-Seg
Evaluation results
| Method | Links | |
|---|---|---|
| WOW-SegTraining Type=Finetuned2026.05 | 68.5 | |
| MaskCLIP++Architecture=ViT-L/14, Input Resolution=392 (short side), Training Protocol=Finetuned on COCO2024.12 | 67 | |
| MaskCLIP++Training Type=Finetuned2026.05 | 67 | |
| CAT-SegArchitecture=ViT-L/14, Input Resolution=392 (short side), Training Protocol=Finetuned on COCO2024.12 | 62.3 | |
| CAT-SegTraining Type=Finetuned2026.05 | 62.3 | |
| CLIPSelfArchitecture=ViT-L/14, Input Resolution=392 (short side), Training Protocol=Finetuned on COCO2024.12 | 56.1 | |
| CLIPSelfTraining Type=Finetuned2026.05 | 56.1 | |
| EVA02 CLIPArchitecture=ViT-L/14, Input Resolution=392 (short side), Training Protocol=Pretrained2024.12 | 52.7 | |
| EVA02 CLIPTraining Type=Pretrained2026.05 | 52.7 | |
| OpenAI CLIPArchitecture=ViT-L/14, Input Resolution=392 (short side), Training Protocol=Pretrained2024.12 | 51 | |
| OpenAI CLIPTraining Type=Pretrained2026.05 | 51 |