Sound Target Segmentation on AVSBench-object MS3 1.0 (test)
59.2mIoUCOMBO
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| COMBOBackbone=PVT-v22023.12 | 59.2 | 71.2 | |
| CATRBackbone=PVT-v22023.12 | 59 | 70 | |
| BAVSBackbone=PVT-v22023.12 | 58.6 | 65.5 | |
| AVSegFormerBackbone=PVT-v22023.12 | 58.4 | 69.3 | |
| DiffusionAVSBackbone=PVT-v22023.12 | 58.2 | 70.9 | |
| ECMVAEBackbone=PVT-v22023.12 | 57.8 | 70.8 | |
| AVS-BiGenBackbone=PVT-v22023.12 | 55.1 | 66.8 | |
| COMBOBackbone=ResNet-502023.12 | 54.5 | 66.6 | |
| AVSBenchBackbone=PVT-v22023.12 | 54 | 64.5 | |
| CATRBackbone=ResNet-502023.12 | 52.8 | 65.3 | |
| BAVSBackbone=ResNet-502023.12 | 50.2 | 62.4 | |
| DiffusionAVSBackbone=ResNet-502023.12 | 49.8 | 58.2 | |
| AVSegFormerBackbone=ResNet-502023.12 | 49.5 | 62.8 | |
| ECMVAEBackbone=ResNet-502023.12 | 48.7 | 60.7 | |
| AVSBenchBackbone=ResNet-502023.12 | 47.9 | 57.8 | |
| AVS-BiGenBackbone=ResNet-502023.12 | 45 | 56.8 | |
| IGANBackbone=ResNet-502023.12 | 42.9 | 54.4 | |
| SSTBackbone=ResNet-1012023.12 | 42.6 | 57.2 | |
| LGVTBackbone=Swin-B2023.12 | 40.7 | 59.3 | |
| 3DCBackbone=ResNet-1522023.12 | 36.9 | 50.3 | |
| CSMFBackbone=ViT-B2023.12 | 34 | 44 | |
| LVSBackbone=ResNet-182023.12 | 29.5 | 33 | |
| MSSLBackbone=ResNet-182023.12 | 26.1 | 36.3 |