| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| Semantic Segmentation | ADE20K (val) | mIoU62.9 | 3,069 | |
| Semantic Segmentation | ADE20K | mIoU68.64 | 1,028 | |
| Semantic Segmentation | ADE20K | mIoU64.01 | 559 | |
| Semantic Segmentation | ADE20K A-150 | mIoU3,140 | 224 | |
| Semantic Segmentation | ADE20K 847 | mIoU1,690 | 105 | |
| Panoptic Segmentation | ADE20K (val) | PQ54.5 | 99 | |
| Semantic Segmentation | ADE20K 52 (val) | mIoU52.82 | 96 | |
| Open-vocabulary semantic segmentation | ADE20K | mIoU29.1 | 80 | |
| Open Vocabulary Semantic Segmentation | ADE20K A-150 | mIoU53.99 | 79 | |
| Semantic Segmentation | ADE20K v1 (val) | mIoU55.7 | 76 | |
| Open Vocabulary Semantic Segmentation | ADE20K without background | mIoU2,190 | 72 | |
| Semantic Segmentation | ADE20K | mIoU60.05 | 71 | |
| Semantic Segmentation | ADE20K A-847 (val) | mIoU1,400 | 70 | |
| Semantic Image Synthesis | ADE20K | FID2.84 | 66 | |
| Semantic Segmentation | ADE20K A-150 (val) | mIoU38.9 | 65 | |
| Semantic Grounding | ADE20k | Accuracy57.78 | 64 | |
| Segmentation | ADE20K | mIoU55.3 | 59 | |
| Semantic Segmentation | ADE20K 83 (val) | mIoU54.7 | 56 | |
| Semantic Segmentation | ADE20k (100-5) | mIoU (All Classes)3,890 | 54 | |
| Semantic Segmentation | ADE20K 150 semantic categories (val) | mIoU51.6 | 51 | |
| Panoptic Segmentation | ADE20K | PQ49.4 | 50 | |
| Semantic Segmentation | ADE20K (test) | mIoU56.23 | 50 | |
| Semantic Segmentation | ADE20K | mIoU53.1 | 48 | |
| Semantic Image Synthesis | ADE20K (val) | FID22.3 | 47 | |
| Panoptic Segmentation | ADE20K 150 59 (val) | Panoptic Quality (PQ)41.89 | 35 |