Semantic Segmentation on KITTI 2015
74.65mIoUDINO V2
Evaluation results
| Method | Links | ||
|---|---|---|---|
| DINO V2Publication=ICLR’23, Type=Vision Foundation Models2026.02 | 74.65 | 84.14 | |
| Depth AnythingPublication=CVPR’24, Type=Vision Foundation Models2026.02 | 73.82 | 83.21 | |
| TwInS (Ours)Publication=/, Type=Joint Learning Approaches2026.02 | 72.36 | 82.69 | |
| Vit-CoMerPublication=CVPR’24, Type=Vision Foundation Models2026.02 | 71.99 | 81.81 | |
| RoadFormer+Publication=TIV’24, Type=Feature-Fusion Networks2026.02 | 70.9 | 79.54 | |
| DFormerv2Publication=CVPR’25, Type=Feature-Fusion Networks2026.02 | 70.45 | 78.61 | |
| DFormerPublication=ICLR’24, Type=Feature-Fusion Networks2026.02 | 70.13 | 80.43 | |
| SegFormerPublication=NeurIPS’21, Type=Single-Modal Networks2026.02 | 67.84 | 81.39 | |
| Mask2FormerPublication=CVPR’22, Type=Single-Modal Networks2026.02 | 67.48 | 78.5 | |
| RoadFormerPublication=TIV’24, Type=Feature-Fusion Networks2026.02 | 65.51 | 79.59 | |
| SegmenterPublication=ICCV’21, Type=Single-Modal Networks2026.02 | 61.47 | 79.57 | |
| CMXPublication=TITS’23, Type=Feature-Fusion Networks2026.02 | 60.68 | 71.75 | |
| KNetPublication=NeurIPS’21, Type=Single-Modal Networks2026.02 | 60.13 | 73.82 | |
| TiCoSSPublication=TASE’25, Type=Joint Learning Approaches2026.02 | 47.66 | 54.69 | |
| SemStereoPublication=AAAI’25, Type=Joint Learning Approaches2026.02 | 45.89 | 52.04 | |
| S3M-NetPublication=TIV’24, Type=Joint Learning Approaches2026.02 | 41.54 | 48.02 | |
| BiSeNet V2Publication=IJCV’21, Type=Single-Modal Networks2026.02 | 40.78 | 58.2 | |
| SGDepthPublication=ECCV’20, Type=Joint Learning Approaches2026.02 | 40.2 | 47.51 | |
| DSNetPublication=ICRA’19, Type=Joint Learning Approaches2026.02 | 39.19 | 46.11 | |
| SG-RoadSegPublication=ICRA’24, Type=Joint Learning Approaches2026.02 | 32.89 | 39.49 |