ResearchBenchmarksAudio-Visual Semantic Segmentation on AVS-SemanticAudio-Visual Semantic Segmentation on AVS-SemanticFollow53.4mIoUQDFormer15.85625.60335.3545.097Sep 29, 2023Evaluation resultsMethodMethodLinksmIoUQDFormerBackbone=Swin-TinyBackbone=Swin-Tiny2023.0953.4QDFormerBackbone=ResNet-50Backbone=ResNet-502023.0946.6AVSBackbone=PVT-v2-BaseBackbone=PVT-v2-Base2023.0929.8AOTBackbone=ResNet-50Backbone=ResNet-502023.0925.4AVSegFormerBackbone=ResNet-50Backbone=ResNet-502023.0924.9AVSBackbone=ResNet-50Backbone=ResNet-502023.0920.23DCBackbone=3DCBackbone=3DC2023.0917.3