Semantic Segmentation on MESS
1.17General Domain ScoreRandom (LB)
Evaluation results
| Method | Links | ||||||
|---|---|---|---|---|---|---|---|
| Random (LB)2023.03 | 1.17 | 7.11 | 29.51 | 11.71 | 6.14 | 10.27 | |
| ZegFormerVLM=CLIP ViT-B/16, Additional Backbone=ResNet-1012023.03 | 13.57 | 17.25 | 17.47 | 17.92 | 25.78 | 17.57 | |
| ZSSegVLM=CLIP ViT-B/16, Additional Backbone=ResNet-1012023.03 | 19.98 | 17.98 | 41.82 | 14 | 22.32 | 22.73 | |
| X-DecoderVLM=UniCL-T, Additional Backbone=Focal-T2023.03 | 22.01 | 18.92 | 23.28 | 15.31 | 18.17 | 19.8 | |
| OpenSeeDVLM=UniCL-B, Additional Backbone=Swin-T2023.03 | 22.49 | 25.11 | 44.44 | 16.5 | 10.35 | 24.33 | |
| SANVLM=CLIP ViT-B/162023.03 | 29.35 | 30.64 | 29.85 | 23.58 | 15.07 | 26.74 | |
| OVSegVLM=CLIP ViT-L/14, Additional Backbone=Swin-B2023.03 | 29.54 | 29.04 | 31.9 | 14.16 | 28.64 | 26.94 | |
| SANVLM=CLIP ViT-L/142023.03 | 36.18 | 38.83 | 30.27 | 16.95 | 20.41 | 30.06 | |
| CAT-SegVLM=CLIP ViT-B/162023.03 | 38.69 | 35.91 | 28.09 | 20.34 | 32.57 | 31.96 | |
| CAT-SegVLM=CLIP ViT-L/142023.03 | 44.69 | 39.99 | 24.7 | 20.2 | 38.61 | 34.7 | |
| Best supervised (UB)2023.03 | 48.62 | 79.12 | 89.49 | 67.66 | 81.94 | 70.99 |