Semantic Segmentation on ImageNet-S300 (val)
35.1mIoUTagAlign
Evaluation Results
| Method | Links | |||
|---|---|---|---|---|
| TagAlignPost-processing=false, Training Datasets=CC12M, Zero-shot evaluation=true2023.12 | 35.1 | — | — | |
| TagAlignPost-processing=true, Training Datasets=CC12M, Zero-shot evaluation=true2023.12 | 34.4 | — | — | |
| TCLPost-processing=false, Training Datasets=CC3&12M, Zero-shot evaluation=true2023.12 | 29.9 | — | — | |
| PASSpLc_component=PixelPro, evaluation_protocol=semi-supervised2021.06 | 29.7 | 56.9 | 68.1 | |
| Supervisedevaluation_protocol=semi-supervised2021.06 | 27.7 | 61.1 | 64.3 | |
| TCLPost-processing=true, Training Datasets=CC3&12M, Zero-shot evaluation=true2023.12 | 26.6 | — | — | |
| PASSsLc_component=SwAV, evaluation_protocol=semi-supervised2021.06 | 25.7 | 52.3 | 65.5 | |
| CoCuPost-processing=false, Training Datasets=CC3&12M+YFCC, Zero-shot evaluation=true2023.12 | 25.5 | — | — | |
| CoCuPost-processing=true, Training Datasets=CC3&12M+YFCC, Zero-shot evaluation=true2023.12 | 24.7 | — | — | |
| SegCLIPPost-processing=true, Training Datasets=CC12M+COCO, Zero-shot evaluation=true2023.12 | 24 | — | — | |
| GroupViTPost-processing=true, Training Datasets=CC12M+YFCC, Zero-shot evaluation=true2023.12 | 23.5 | — | — | |
| PixelProevaluation_protocol=semi-supervised2021.06 | 23.3 | 49 | 66 | |
| SwAVevaluation_protocol=semi-supervised2021.06 | 23 | 51.2 | 64 | |
| AdCoevaluation_protocol=semi-supervised2021.06 | 19.6 | 45.4 | 63.8 | |
| PCLevaluation_protocol=semi-supervised2021.06 | 17.3 | 41.7 | 61.7 | |
| DenseCLevaluation_protocol=semi-supervised2021.06 | 16.2 | 34.9 | 61 | |
| OVSegmentorPost-processing=true, Training Datasets=CC12M*, Zero-shot evaluation=true2023.12 | 14.4 | — | — | |
| SimCLRevaluation_protocol=semi-supervised2021.06 | 12.7 | 34.4 | 59.1 | |
| MoCov2evaluation_protocol=semi-supervised2021.06 | 12.6 | 33 | 59.2 | |
| Dong et al.Post-processing=true, Training Datasets=LAION-20M, Zero-shot evaluation=true2023.12 | 11.7 | — | — | |
| BYOLevaluation_protocol=semi-supervised2021.06 | 10.5 | 30.1 | 58.5 |