Weakly-Supervised Audio-Visual Segmentation
This work addresses the challenge of reducing annotation costs for sound source segmentation in videos, which is incremental as it builds on existing fully-supervised methods.
The paper tackles the problem of audio-visual segmentation by simplifying supervision from expensive pixel-level masks to instance-level annotations, achieving effective results in single-source and multi-source scenarios on the AVSBench dataset.
Audio-visual segmentation is a challenging task that aims to predict pixel-level masks for sound sources in a video. Previous work applied a comprehensive manually designed architecture with countless pixel-wise accurate masks as supervision. However, these pixel-level masks are expensive and not available in all cases. In this work, we aim to simplify the supervision as the instance-level annotation, i.e., weakly-supervised audio-visual segmentation. We present a novel Weakly-Supervised Audio-Visual Segmentation framework, namely WS-AVS, that can learn multi-scale audio-visual alignment with multi-scale multiple-instance contrastive learning for audio-visual segmentation. Extensive experiments on AVSBench demonstrate the effectiveness of our WS-AVS in the weakly-supervised audio-visual segmentation of single-source and multi-source scenarios.