Semantic Segmentation on vKITTI 2
92.37mIoUVit-CoMer
Evaluation results
| Method | Links | ||
|---|---|---|---|
| Vit-CoMerPublication=CVPR’24, Type=Vision Foundation Models2026.02 | 92.37 | 95.93 | |
| Depth AnythingPublication=CVPR’24, Type=Vision Foundation Models2026.02 | 92.1 | 96.27 | |
| TwInS (Ours)Publication=/, Type=Joint Learning Approaches2026.02 | 88.67 | 93.69 | |
| RoadFormer+Publication=TIV’24, Type=Feature-Fusion Networks2026.02 | 88.44 | 93.52 | |
| SegFormerPublication=NeurIPS’21, Type=Single-Modal Networks2026.02 | 88.02 | 93.34 | |
| TiCoSSPublication=TASE’25, Type=Joint Learning Approaches2026.02 | 87.94 | 90.52 | |
| RoadFormerPublication=TIV’24, Type=Feature-Fusion Networks2026.02 | 87.75 | 93.45 | |
| Mask2FormerPublication=CVPR’22, Type=Single-Modal Networks2026.02 | 86.83 | 92.65 | |
| DINO V2Publication=ICLR’23, Type=Vision Foundation Models2026.02 | 86.36 | 92.18 | |
| CMXPublication=TITS’23, Type=Feature-Fusion Networks2026.02 | 86.01 | 92.04 | |
| DFormerPublication=ICLR’24, Type=Feature-Fusion Networks2026.02 | 85.99 | 89.37 | |
| KNetPublication=NeurIPS’21, Type=Single-Modal Networks2026.02 | 85.05 | 91.45 | |
| S3M-NetPublication=TIV’24, Type=Joint Learning Approaches2026.02 | 84 | 88.27 | |
| SemStereoPublication=AAAI’25, Type=Joint Learning Approaches2026.02 | 83.69 | 87.01 | |
| SegmenterPublication=ICCV’21, Type=Single-Modal Networks2026.02 | 83.53 | 90.22 | |
| DFormerv2Publication=CVPR’25, Type=Feature-Fusion Networks2026.02 | 81.99 | 86.98 | |
| SG-RoadSegPublication=ICRA’24, Type=Joint Learning Approaches2026.02 | 81.06 | 86.49 | |
| SGDepthPublication=ECCV’20, Type=Joint Learning Approaches2026.02 | 80.19 | 85.91 | |
| DSNetPublication=ICRA’19, Type=Joint Learning Approaches2026.02 | 76.61 | 85.36 | |
| BiSeNet V2Publication=IJCV’21, Type=Single-Modal Networks2026.02 | 70.41 | 80.83 |