Audio-visual Segmentation on AVS-Object MS3
77.9J&Fm Combined ScoreDDESEG
Evaluation results
| Method | Links | |||
|---|---|---|---|---|
| DDESEGVisual Backbone=Transformer-based architecture, Audio Backbone=HTSAT2025.03 | 77.9 | 72.3 | 83.4 | |
| DDESEGVisual Backbone=Transformer-based architecture, Audio Backbone=VGGish2025.03 | 75.6 | 70.1 | 81 | |
| DDESEGVisual Backbone=PVT-V2-B5, Audio Backbone=VGGish2025.03 | 74.7 | 69.7 | 79.6 | |
| BiasAVSVisual Backbone=Swin-Base, Audio Backbone=VGGish2025.03 | 74 | 67.2 | 80.8 | |
| CAVPVisual Backbone=PVT-V2-B5, Audio Backbone=VGGish2025.03 | 72.7 | 67.3 | 78.1 | |
| AVSStoneVisual Backbone=Swin-Base, Audio Backbone=VGGish2025.03 | 72.5 | 67.3 | 77.6 | |
| AUTRVisual Backbone=PVT-V2-B5, Audio Backbone=VGGish2025.03 | 72 | 66.2 | 77.7 | |
| GAVSVisual Backbone=ViT-Base, Audio Backbone=VGGish2025.03 | 70.6 | 63.7 | 77.4 | |
| CATRVisual Backbone=PVT-V2-B5, Audio Backbone=VGGish2025.03 | 68.6 | 62.7 | 74.5 | |
| AQFormerVisual Backbone=PVT-V2-B5, Audio Backbone=VGGish2025.03 | 67.5 | 62.2 | 72.7 | |
| AVSegFormerVisual Backbone=PVT-V2-B5, Audio Backbone=VGGish2025.03 | 67.2 | 61.3 | 73 | |
| COMBOVisual Backbone=PVT-V2-B5, Audio Backbone=VGGish2025.03 | 65.2 | 59.2 | 71.2 | |
| DiffusionAVSVisual Backbone=PVT-V2-B5, Audio Backbone=VGGish2025.03 | 64.6 | 58.2 | 70.9 | |
| ECMVAEVisual Backbone=PVT-V2-B5, Audio Backbone=VGGish2025.03 | 64.3 | 57.8 | 70.8 | |
| QDFormerVisual Backbone=Swin-Tiny, Audio Backbone=VGGish2025.03 | 64 | 61.9 | 66.1 | |
| BAVSVisual Backbone=Swin-Base, Audio Backbone=Beats2025.03 | 62.8 | 59.6 | 65.9 | |
| AVSCVisual Backbone=Swin-Base, Audio Backbone=VGGish2025.03 | 62.6 | 59.5 | 65.8 | |
| AVSBGVisual Backbone=PVT-V2-B5, Audio Backbone=VGGish2025.03 | 61 | 55.1 | 66.8 | |
| TPAVIVisual Backbone=PVT-V2-B5, Audio Backbone=VGGish2025.03 | 59.3 | 54 | 64.5 |