AI RESEARCH
LightAVSeg: Lightweight Audio-Visual Segmentation
arXiv CS.CV
•
ArXi:2605.08805v1 Announce Type: new Audio-Visual Segmentation (AVS) targets pixel level localization of sounding emitting objects in videos. However, existing models rely on dense cross-modal attention with quadratic computational cost, limiting their suitability for resource efficient deployment. Most efficiency oriented methods focus on backbone reduction and overlook the interaction module as the primary bottleneck.