| Paper | Code | SAD | MSE | MAD | SAD(E) | MSE(E) | MAD(E) | ModelName | ReleaseDate |
|---|---|---|---|---|---|---|---|---|---|
| Referring Image Matting | ✓ Link | 88.52 | 0.0488 | 0.0510 | 87.92 | 0.0483 | 0.0505 | CLIPMat (ViT-L/14) | 2022-06-10 |
| Referring Image Matting | ✓ Link | 110.66 | 0.0614 | 0.0636 | 110.63 | 0.0612 | 0.0635 | CLIPMat (ViT-B/16) | 2022-06-10 |
| MDETR -- Modulated Detection for End-to-End Multi-Modal Understanding | ✓ Link | 131.58 | 0.0675 | 0.0751 | 136.59 | 0.0700 | 0.0779 | MDETR (ResNet-101) | 2021-04-26 |
| Image Segmentation Using Text and Image Prompts | ✓ Link | 211.86 | 0.1178 | 0.1222 | 222.37 | 0.1236 | 0.1282 | CLIPSeg (ViT-B/16) | 2021-12-18 |