Audio-Visual Segmentation on AVSBench S4 v1 (test)
86.2MJVCT
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| VCTBackbone=Swin-B, Image Size=384x3842025.06 | 86.2 | 93.4 | |
| VCTBackbone=PVT-v2, Image Size=224x2242025.06 | 84.8 | 92.1 | |
| COMBOBackbone=PVT-v2, Image Size=224x2242025.06 | 84.7 | 91.9 | |
| VCTBackbone=Swin-B, Image Size=224x2242025.06 | 84.7 | 92.3 | |
| COMBOBackbone=PVT-v22023.12 | 84.7 | 91.9 | |
| SelMBackbone=PVT-v2, Image Size=224x2242025.06 | 83.5 | 91.2 | |
| TESOBackbone=Swin-B, Image Size=384x3842025.06 | 83.3 | 93.3 | |
| AVSBiasBackbone=Swin-B, Image Size=384x3842025.06 | 83.3 | 93 | |
| UFEBackbone=PVT-v2, Image Size=224x2242025.06 | 83.2 | 90.4 | |
| BAVSBackbone=Swin-B, Image Size=224x2242025.06 | 82.7 | 89.8 | |
| AVSFBackbone=PVT-v2, Image Size=224x2242025.06 | 82.1 | 89.9 | |
| AVSegFormerBackbone=PVT-v22023.12 | 82.1 | 89.9 | |
| BAVSBackbone=PVT-v2, Image Size=224x2242025.06 | 82 | 88.6 | |
| BAVSBackbone=PVT-v22023.12 | 82 | 88.6 | |
| VCTBackbone=ResNet-50, Image Size=224x2242025.06 | 81.8 | 90.6 | |
| ECMVAEBackbone=PVT-v2, Image Size=224x2242025.06 | 81.7 | 90.1 | |
| AVSBGBackbone=PVT-v2, Image Size=224x2242025.06 | 81.7 | 90.4 | |
| COMBOBackbone=ResNet-50, Image Size=224x2242025.06 | 81.7 | 90.1 | |
| AVS-BiGenBackbone=PVT-v22023.12 | 81.7 | 90.4 | |
| ECMVAEBackbone=PVT-v22023.12 | 81.7 | 90.1 | |
| COMBOBackbone=ResNet-502023.12 | 81.7 | 90.1 | |
| AQFormerBackbone=PVT-v2, Image Size=224x2242025.06 | 81.6 | 89.4 | |
| CATRBackbone=PVT-v2, Image Size=224x2242025.06 | 81.4 | 89.6 | |
| CPMBackbone=ResNet-50, Image Size=224x2242025.06 | 81.4 | 90.5 | |
| CATRBackbone=PVT-v22023.12 | 81.4 | 89.6 | |
| DiffusionAVSBackbone=PVT-v22023.12 | 81.4 | 90.2 | |
| AVSCBackbone=PVT-v2, Image Size=224x2242025.06 | 80.6 | 88.2 | |
| GAVSBackbone=ViT-B, Image Size=224x2242025.06 | 80.1 | 90.2 | |
| UFEBackbone=ResNet-50, Image Size=224x2242025.06 | 79 | 87.5 | |
| CAVPBackbone=ResNet-50, Image Size=224x2242025.06 | 78.8 | 88.9 | |
| TPAVIBackbone=PVT-v2, Image Size=224x2242025.06 | 78.7 | 87.9 | |
| AVSBenchBackbone=PVT-v22023.12 | 78.7 | 87.9 | |
| BAVSBackbone=ResNet-50, Image Size=224x2242025.06 | 78 | 85.3 | |
| BAVSBackbone=ResNet-502023.12 | 78 | 85.3 | |
| AQFormerBackbone=ResNet-50, Image Size=224x2242025.06 | 77 | 86.4 | |
| AVSCBackbone=ResNet-50, Image Size=224x2242025.06 | 77 | 85.2 | |
| SelMBackbone=ResNet-50, Image Size=224x2242025.06 | 76.6 | 86.2 | |
| AVSFBackbone=ResNet-50, Image Size=224x2242025.06 | 76.5 | 85.9 | |
| AVSegFormerBackbone=ResNet-502023.12 | 76.5 | 85.9 | |
| ECMVAEBackbone=ResNet-50, Image Size=224x2242025.06 | 76.3 | 86.5 | |
| ECMVAEBackbone=ResNet-502023.12 | 76.3 | 86.5 | |
| DiffusionAVSBackbone=ResNet-502023.12 | 75.8 | 86.9 | |
| LGVTBackbone=Swin-B2023.12 | 74.9 | 87.3 | |
| CATRBackbone=ResNet-50, Image Size=224x2242025.06 | 74.8 | 86.6 | |
| CATRBackbone=ResNet-502023.12 | 74.8 | 86.6 | |
| AVSBGBackbone=ResNet-50, Image Size=224x2242025.06 | 74.1 | 85.4 | |
| AVS-BiGenBackbone=ResNet-502023.12 | 74.1 | 85.4 | |
| TPAVIBackbone=ResNet-50, Image Size=224x2242025.06 | 72.8 | 84.8 | |
| AVSBenchBackbone=ResNet-502023.12 | 72.8 | 84.8 | |
| SSTBackbone=ResNet-1012023.12 | 66.3 | 80.1 | |
| IGANBackbone=ResNet-502023.12 | 61.6 | 77.8 | |
| CSMFBackbone=ViT-B2023.12 | 58 | 67 | |
| 3DCBackbone=ResNet-1522023.12 | 57.1 | 75.9 | |
| MSSLBackbone=ResNet-182023.12 | 44.9 | 66.3 | |
| LVSBackbone=ResNet-182023.12 | 37.9 | 51 |