Semantic Segmentation on FSS-1000
87.8mIoULSeg
Evaluation results
| Method | Links | |
|---|---|---|
| LSegBackbone=ViT-L/16, Evaluation Protocol=zero-shot2022.01 | 87.8 | |
| HSNetBackbone=ResNet101, Evaluation Protocol=1-shot2022.01 | 86.5 | |
| DANBackbone=ResNet101, Evaluation Protocol=1-shot2022.01 | 85.2 | |
| LSegBackbone=ResNet101, Evaluation Protocol=zero-shot2022.01 | 84.7 | |
| DoG-LSTMBackbone=VGG16, Evaluation Protocol=1-shot2022.01 | 80.8 | |
| MPAsource-training=false2026.02 | 80.2 | |
| APSegSAM-based=true2026.02 | 79.7 | |
| TAVPSAM-based=true2026.02 | 79.1 | |
| FSSBackbone=VGG16, Evaluation Protocol=1-shot2022.01 | 73.5 | |
| GNetBackbone=VGG16, Evaluation Protocol=1-shot2022.01 | 71.9 | |
| PerSAMSAM-based=true2026.02 | 71.2 | |
| OSLSMBackbone=VGG16, Evaluation Protocol=1-shot2022.01 | 70.3 | |
| FRONTBackbone=ResNet-50, Few-shot protocol=5-shot, Source Domain=ImageNet-1K2026.03 | 66.44 | |
| ScratchBackbone=ResNet-50, Few-shot protocol=5-shot, Source Domain=ImageNet-1K2026.03 | 43.06 |