Audio-Visual Segmentation on AVS-Object-Single
83.9J&F ScoreQDFormer
Evaluation results
| Method | Links | |||
|---|---|---|---|---|
| QDFormerBackbone=Swin-Tiny2023.09 | 83.9 | 79.5 | 88.2 | |
| AVSBackbone=PVT-v2-Base2023.09 | 83.3 | 78.7 | 87.9 | |
| QDFormerBackbone=ResNet-502023.09 | 81.8 | 77.6 | 86 | |
| AVSegFormerBackbone=ResNet-502023.09 | 81.2 | 76.5 | 85.9 | |
| LGVTBackbone=Swin-Tiny2023.09 | 81.1 | 74.9 | 87.3 | |
| CATRBackbone=ResNet-502023.09 | 81 | 74.9 | 87.1 | |
| Bi-GenBackbone=ResNet-502023.09 | 79.8 | 74.1 | 85.4 | |
| AVSBackbone=ResNet-502023.09 | 78.8 | 72.8 | 84.8 | |
| SSTBackbone=SSL2023.09 | 73.2 | 66.3 | 80.1 | |
| iGANBackbone=Swin-Tiny2023.09 | 69.7 | 61.6 | 77.8 | |
| 3DCBackbone=3DC2023.09 | 66.5 | 57.1 | 75.9 | |
| MSSLBackbone=ResNet-182023.09 | 55.6 | 44.9 | 66.3 | |
| LVSBackbone=ResNet-182023.09 | 44.9 | 37.9 | 51.9 |