Semantic Segmentation on PASCAL VOC PAS-20
0.974mIoULoGoSeg
Evaluation results
| Method | Links | |
|---|---|---|
| LoGoSegVLM=ViT-L/14, Feature backbone=-, Training Dataset=COCO-Stuff, Additional Dataset=false2026.02 | 0.974 | |
| LoGoSegVLM=ConvNeXt-L, Feature backbone=-, Training Dataset=COCO-Stuff, Additional Dataset=false2026.02 | 0.97 | |
| CAT-SegVLM=ViT-L/14, Feature backbone=Swin-B, Training Dataset=COCO-Stuff, Additional Dataset=false2026.02 | 0.966 | |
| MAFT+VLM=ConvNeXt-L, Feature backbone=-, Training Dataset=COCO-Stuff, Additional Dataset=false2026.02 | 0.965 | |
| EBSegVLM=ViT-L/14, Feature backbone=-, Training Dataset=COCO-Stuff, Additional Dataset=false2026.02 | 0.964 | |
| SEDVLM=ConvNeXt-L, Feature backbone=-, Training Dataset=COCO-Stuff, Additional Dataset=false2026.02 | 0.961 | |
| SANVLM=ViT-L/14, Feature backbone=-, Training Dataset=COCO-Stuff, Additional Dataset=false2026.02 | 0.955 | |
| LoGoSegVLM=ViT-B/16, Feature backbone=-, Training Dataset=COCO-Stuff, Additional Dataset=false2026.02 | 0.954 | |
| FC-CLIPVLM=ConvNeXt-L, Feature backbone=-, Training Dataset=COCO Panoptic, Additional Dataset=true2026.02 | 0.954 | |
| LoGoSegVLM=ConvNeXt-B, Feature backbone=-, Training Dataset=COCO-Stuff, Additional Dataset=false2026.02 | 0.95 | |
| EBSegVLM=ViT-B/16, Feature backbone=-, Training Dataset=COCO-Stuff, Additional Dataset=false2026.02 | 0.946 | |
| OVSegVLM=ViT-L/14, Feature backbone=Swin-B, Training Dataset=COCO-Stuff+COCO Caption, Additional Dataset=true2026.02 | 0.945 | |
| SEDVLM=ConvNeXt-B, Feature backbone=-, Training Dataset=COCO-Stuff, Additional Dataset=false2026.02 | 0.944 | |
| SANVLM=ViT-B/14, Feature backbone=-, Training Dataset=COCO-Stuff, Additional Dataset=false2026.02 | 0.94 | |
| CAT-SegVLM=ViT-B/16, Feature backbone=ResNet-101, Training Dataset=COCO-Stuff, Additional Dataset=false2026.02 | 0.937 | |
| OVSegVLM=ViT-B/16, Feature backbone=ResNet-101c, Training Dataset=COCO-Stuff+COCO Caption, Additional Dataset=true2026.02 | 0.926 | |
| DeOPVLM=ViT-B/16, Feature backbone=ResNet-101c, Training Dataset=COCO-Stuff-156, Additional Dataset=false2026.02 | 0.917 | |
| ZSsegVLM=ViT-B/16, Feature backbone=ResNet-101, Training Dataset=COCO-Stuff, Additional Dataset=false2026.02 | 0.884 | |
| ZegFormerVLM=ViT-B/16, Feature backbone=ResNet-101, Training Dataset=COCO-Stuff-156, Additional Dataset=false2026.02 | 0.862 | |
| PACLVLM=ViT-B/16, Feature backbone=-, Training Dataset=GCC+YFCC, Additional Dataset=true2026.02 | 0.723 | |
| LSegVLM=ViT-B/32, Feature backbone=ViT-L/16, Training Dataset=PASCAL VOC-15, Additional Dataset=false2026.02 | 0.523 | |
| GroupViTVLM=ViT-S/16, Feature backbone=-, Training Dataset=GCC+YFCC, Additional Dataset=true2026.02 | 0.507 |