Learning from Silence and Noise for Visual Sound Source Localization
This work addresses a fundamental perception task for video analysis, but it is incremental as it builds on existing methods by handling negative audio cases more effectively.
The paper tackles the problem of visual sound source localization by addressing poor performance in cases with low audio-visual correspondence, such as silence and noise, and introduces a training strategy that improves robustness and achieves state-of-the-art results in self-supervised models, with specific gains in sound localization and cross-modal retrieval.
Visual sound source localization is a fundamental perception task that aims to detect the location of sounding sources in a video given its audio. Despite recent progress, we identify two shortcomings in current methods: 1) most approaches perform poorly in cases with low audio-visual semantic correspondence such as silence, noise, and offscreen sounds, i.e. in the presence of negative audio; and 2) most prior evaluations are limited to positive cases, where both datasets and metrics convey scenarios with a single visible sound source in the scene. To address this, we introduce three key contributions. First, we propose a new training strategy that incorporates silence and noise, which improves performance in positive cases, while being more robust against negative sounds. Our resulting self-supervised model, SSL-SaN, achieves state-of-the-art performance compared to other self-supervised models, both in sound localization and cross-modal retrieval. Second, we propose a new metric that quantifies the trade-off between alignment and separability of auditory and visual features across positive and negative audio-visual pairs. Third, we present IS3+, an extended and improved version of the IS3 synthetic dataset with negative audio. Our data, metrics and code are available on the https://xavijuanola.github.io/SSL-SaN/.