Semantic Segmentation on ImageNet-S50 with background class (val)
55.1mIoUTagAlign
Evaluation Results
| Method | Links | |
|---|---|---|
| TagAlignPost-processing=false, Training Datasets=CC12M, Zero-shot evaluation=true2023.12 | 55.1 | |
| TagAlignPost-processing=true, Training Datasets=CC12M, Zero-shot evaluation=true2023.12 | 52.8 | |
| TCLPost-processing=false, Training Datasets=CC3&12M, Zero-shot evaluation=true2023.12 | 50 | |
| CoCuPost-processing=false, Training Datasets=CC3&12M+YFCC, Zero-shot evaluation=true2023.12 | 48.8 | |
| SegCLIPPost-processing=true, Training Datasets=CC12M+COCO, Zero-shot evaluation=true2023.12 | 47.4 | |
| TCLPost-processing=true, Training Datasets=CC3&12M, Zero-shot evaluation=true2023.12 | 46.9 | |
| CoCuPost-processing=true, Training Datasets=CC3&12M+YFCC, Zero-shot evaluation=true2023.12 | 46.7 | |
| GroupViTPost-processing=true, Training Datasets=CC12M+YFCC, Zero-shot evaluation=true2023.12 | 44.3 | |
| OVSegmentorPost-processing=true, Training Datasets=CC12M*, Zero-shot evaluation=true2023.12 | 38.9 | |
| Dong et al.Post-processing=true, Training Datasets=LAION-20M, Zero-shot evaluation=true2023.12 | 25.9 |