| Paper | Code | SAD | MSE | MAD | SAD(E) | MSE(E) | MAD(E) | ModelName | ReleaseDate |
|---|---|---|---|---|---|---|---|---|---|
| Referring Image Matting | ✓ Link | 42.05 | 0.0212 | 0.0238 | 44.77 | 0.0226 | 0.0254 | CLIPMat (ViT-L/14) | 2022-06-10 |
| Referring Image Matting | ✓ Link | 47.97 | 0.0245 | 0.0273 | 50.84 | 0.0260 | 0.0273 | CLIPMat (ViT-B/16) | 2022-06-10 |
| Image Segmentation Using Text and Image Prompts | ✓ Link | 69.13 | 0.0358 | 0.0394 | 73.53 | 0.0381 | 0.0419 | CLIPSeg (ViT-B/16) | 2021-12-18 |
| MDETR -- Modulated Detection for End-to-End Multi-Modal Understanding | ✓ Link | 84.70 | 0.0434 | 0.0482 | 90.45 | 0.0463 | 0.0515 | MDETR (ResNet-101) | 2021-04-26 |