Less is More: Encoder-only Audio-Visual Segmentation
Quick summary
arXiv:2609.29121v1 Announce Type: cross Abstract: Audio-Visual Semantic Segmentation (AVSS) aims to identify, segment, and classify sound-emitting objects in video frames. Previous Transformer-based AVSS approaches largely inherit design principles from image segmentation models. Recent studies show that these image segmentation models contain redundant components that contribute little to the segmentation performance. Following this insight, we propose Encoder-only Audio-Visual Segmentation (EASE). EASE runs at up to 365 FPS, 3x faster than prior State-of-the-Art (SotA) AVS models at comparab
Key takeaways
- arXiv:2609.29121v1 Announce Type: cross Abstract: Audio-Visual Semantic Segmentation (AVSS) aims to identify, segment, and classify sound-emitting objects in video frames.
- Previous Transformer-based AVSS approaches largely inherit design principles from image segmentation models.
- Recent studies show that these image segmentation models contain redundant components that contribute little to the segmentation performance.
Why it matters
The importance of “Less is More: Encoder-only Audio-Visual Segmentation” will be measured by what changes in practice. User behavior, access conditions, verifiable performance and responsible-use outcomes are the signals worth following.
Member comments