Dual Mean-Teacher: An Unbiased Semi-Supervised Framework for Audio-Visual Source Localization

arXiv:2403.03145v1 Announce Type: cross
Abstract: Audio-Visual Source Localization (AVSL) aims to locate sounding objects within video frames given the paired audio clips. Existing methods predominantly rely on self-supervised contrastive learning of audio-visual correspondence. Without any bounding-box annotations, they struggle to achieve precise localization, especially for small objects, and suffer from blurry boundaries and false positives. Moreover, the naive semi-supervised method is poor in fully leveraging the information of abundant unlabeled data. In this paper, we propose a novel semi-supervised learning …

abstract annotations arxiv audio box cs.cv cs.lg cs.mm cs.sd eess.as framework localization mean objects semi-supervised small struggle type unbiased video visual