Audio-Visual Segmentation on AVSBench-object S4 v1s (test)
85.4mIoUSSP
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| SSPAudio-backbone=VGGish, Visual-backbone=Swin-Base2026.01 | 85.4 | 93.3 | |
| Save(1024)Audio-backbone=VGGish, Visual-backbone=SAM, Resolution=10242026.01 | 85.1 | 91.2 | |
| AVS-MambaAudio-backbone=VGGish, Visual-backbone=PVT-v22026.01 | 85 | 92.6 | |
| COMBOAudio-backbone=VGGish, Visual-backbone=PVT-v22026.01 | 84.7 | 91.9 | |
| Save(256)Audio-backbone=VGGish, Visual-backbone=SAM, Resolution=2562026.01 | 84 | 90.5 | |
| AAVSAudio-backbone=VGGish, Visual-backbone=Swin-Base2026.01 | 83.2 | 91.3 | |
| TeSOAudio-backbone=VGGish, Visual-backbone=Swin-Base2026.01 | 83.2 | 93.3 | |
| TPNetAudio-backbone=VGGish, Visual-backbone=PVT-v22026.01 | 82.9 | 90.8 | |
| AVSegFormerAudio-backbone=VGGish, Visual-backbone=PVT-v22026.01 | 82.1 | 89.9 | |
| AQFormerAudio-backbone=VGGish, Visual-backbone=PVT-v22026.01 | 81.6 | 89.4 | |
| SAMA-AVSAudio-backbone=VGGish, Visual-backbone=ViT-Huge2026.01 | 81.5 | 88.6 | |
| MUTRAudio-backbone=VGGish, Visual-backbone=ViT-video-Huge2026.01 | 81.5 | 89.8 | |
| CatrAudio-backbone=VGGish, Visual-backbone=PVT-v22026.01 | 81.4 | 89.6 | |
| AuTRAudio-backbone=VGGish, Visual-backbone=Swin-Base2026.01 | 80.4 | 89.1 | |
| GAVSAudio-backbone=VGGish, Visual-backbone=ViT-Base2026.01 | 80.1 | 90.2 | |
| AVSBenchAudio-backbone=VGGish, Visual-backbone=PVT-v22026.01 | 78.7 | 87.9 |