Audio-Visual Segmentation on AVSBench-object MS3 v1 (test)
72.3mIoUSSP
Evaluation results
| Method | Links | ||
|---|---|---|---|
| SSPAudio-backbone=VGGish, Visual-backbone=Swin-Base2026.01 | 72.3 | 84.6 | |
| AVS-MambaAudio-backbone=VGGish, Visual-backbone=PVT-v22026.01 | 68.6 | 78.8 | |
| AAVSAudio-backbone=VGGish, Visual-backbone=Swin-Base2026.01 | 67.3 | 77.6 | |
| Save(1024)Audio-backbone=VGGish, Visual-backbone=SAM, Resolution=10242026.01 | 67 | 77.7 | |
| TeSOAudio-backbone=VGGish, Visual-backbone=Swin-Base2026.01 | 66 | 80.1 | |
| MUTRAudio-backbone=VGGish, Visual-backbone=ViT-video-Huge2026.01 | 65 | 73 | |
| Save(256)Audio-backbone=VGGish, Visual-backbone=SAM, Resolution=2562026.01 | 64.1 | 71.2 | |
| GAVSAudio-backbone=VGGish, Visual-backbone=ViT-Base2026.01 | 63.7 | 77.4 | |
| SAMA-AVSAudio-backbone=VGGish, Visual-backbone=ViT-Huge2026.01 | 63.1 | 69.1 | |
| AQFormerAudio-backbone=VGGish, Visual-backbone=PVT-v22026.01 | 61.1 | 72.1 | |
| TPNetAudio-backbone=VGGish, Visual-backbone=PVT-v22026.01 | 59.9 | 70.9 | |
| COMBOAudio-backbone=VGGish, Visual-backbone=PVT-v22026.01 | 59.2 | 71.2 | |
| CatrAudio-backbone=VGGish, Visual-backbone=PVT-v22026.01 | 59 | 70 | |
| AVSegFormerAudio-backbone=VGGish, Visual-backbone=PVT-v22026.01 | 58.4 | 69.3 | |
| AuTRAudio-backbone=VGGish, Visual-backbone=Swin-Base2026.01 | 56.2 | 67.2 | |
| AVSBenchAudio-backbone=VGGish, Visual-backbone=PVT-v22026.01 | 54 | 64.5 |