Semantic Segmentation on COCO-Stuff 171 classes (test)
43.3mIoUPSPNet
Evaluation results
| Method | Links | |
|---|---|---|
| PSPNet#params.=68.0M, FLOPs=1028.8G, Multi-scale testing=true, Extra pre-training on ADE20K=false2021.10 | 43.3 | |
| HRFormer-B + OCR#params.=56.2M, FLOPs=1119.9G, Multi-scale testing=true, Extra pre-training on ADE20K=false2021.10 | 43.3 | |
| HRNet-W48 + OCR#params.=74.5M, FLOPs=924.7G, Multi-scale testing=true, Extra pre-training on ADE20K=false2021.10 | 40.5 | |
| CLIP + PACLEncoder=ViT-B/16, External Training Set=GCC3M [44] + GCC12M [6] + YFCC15M [41,46], Annotation Constraint=No, Mask Constraint=No2022.12 | 38.8 | |
| OpenSegEncoder=EfficientNet-B7, External Training Set=COCO [9] + Loc. Narr. [40], Annotation Constraint=Yes, Mask Constraint=No2022.12 | 28.6 | |
| GroupViTEncoder=ViT-S/16, External Training Set=GCC12M [6] + YFCC15M [41,46], Annotation Constraint=No, Mask Constraint=No2022.12 | 24.3 | |
| ViL-SegEncoder=ViT-B/16, External Training Set=GCC12M [6], Annotation Constraint=No, Mask Constraint=No2022.12 | 16.4 | |
| ZS3NetEncoder=ResNet-101, External Training Set=None, Annotation Constraint=Yes, Mask Constraint=No2022.12 | 9.6 | |
| SPNetEncoder=ResNet-101, External Training Set=None, Annotation Constraint=No, Mask Constraint=Yes2022.12 | 8.7 | |
| CLIPEncoder=ViT-B/16, External Training Set=WIT-400M [41], Annotation Constraint=No, Mask Constraint=No2022.12 | 2.6 |