Multi-label image recognition on MS COCO
72.5mAP (10% known)DSRB
Evaluation results
| Method | Links | ||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| DSRB2022.05 | 72.5 | 76 | 77.6 | 78.7 | 79.6 | 79.8 | 80 | 80.5 | 80.8 | 78.4 | — | — | |
| DSRBBackbone=ResNet-1012022.05 | 72.5 | 76 | 77.6 | 78.7 | 79.6 | 79.8 | 80 | 80.5 | 80.8 | 78.4 | 76.8 | 72.7 | |
| ASL2022.05 | 69.7 | 74 | 75.1 | 76.8 | 77.5 | 78.1 | 78.7 | 79.1 | 79.7 | 76.5 | — | — | |
| ASLBackbone=ResNet-1012022.05 | 69.7 | 74 | 75.1 | 76.8 | 77.5 | 78.1 | 78.7 | 79.1 | 79.7 | 76.5 | 46.7 | 47.9 | |
| P-GCN2022.05 | 67.5 | 71.6 | 73.8 | 75.5 | 77.4 | 78.4 | 79.5 | 80.7 | 81.5 | 76.2 | — | — | |
| P-GCNBackbone=ResNet-1012022.05 | 67.5 | 71.6 | 73.8 | 75.5 | 77.4 | 78.4 | 79.5 | 80.7 | 81.5 | 76.2 | — | — | |
| KGGR2022.05 | 66.6 | 71.4 | 73.8 | 76.7 | 77.5 | 77.9 | 78.4 | 78.7 | 79.1 | 75.6 | — | — | |
| KGGRBackbone=ResNet-1012022.05 | 66.6 | 71.4 | 73.8 | 76.7 | 77.5 | 77.9 | 78.4 | 78.7 | 79.1 | 75.6 | 73.7 | 69.7 | |
| GCN-ML2022.05 | 63.8 | 70.9 | 72.8 | 74 | 76.7 | 77.1 | 77.3 | 78.3 | 78.6 | 74.4 | — | — | |
| GCN-MLBackbone=ResNet-1012022.05 | 63.8 | 70.9 | 72.8 | 74 | 76.7 | 77.1 | 77.3 | 78.3 | 78.6 | 74.4 | 73.1 | 68.4 | |
| SSGRL2022.05 | 62.5 | 70.5 | 73.2 | 74.5 | 76.3 | 76.5 | 77.1 | 77.9 | 78.4 | 74.1 | — | — | |
| SSGRLBackbone=ResNet-1012022.05 | 62.5 | 70.5 | 73.2 | 74.5 | 76.3 | 76.5 | 77.1 | 77.9 | 78.4 | 74.1 | 73.9 | 68.1 | |
| Partial BCE2022.05 | 61.6 | 70.5 | 74.1 | 76.3 | 77.2 | 77.7 | 78.2 | 78.4 | 78.5 | 74.7 | — | — | |
| Partial BCEBackbone=ResNet-1012022.05 | 61.6 | 70.5 | 74.1 | 76.3 | 77.2 | 77.7 | 78.2 | 78.4 | 78.5 | 74.7 | 74 | 68.8 | |
| CL2022.05 | 26.7 | 31.8 | 51.5 | 65.4 | 70 | 71.9 | 74 | 77.4 | 78 | 60.7 | — | — | |
| CLBackbone=ResNet-1012022.05 | 26.7 | 31.8 | 51.5 | 65.4 | 70 | 71.9 | 74 | 77.4 | 78 | 60.7 | 61.9 | 48.3 |