Audiovisual segmentation (AVS) is a challenging task that aims to segment visual objects in videos according to their associated acoustic cues. With multiple sound sources and background disturbances involved, establishing robust correspondences between audio and visual contents poses unique challenges due to (1) complex entanglement across sound sources and (2) frequent changes in the occurrence of distinct sound events. Assuming sound events occur independently, the multi-source semantic space can be represented as the Cartesian product of single-source sub-spaces. We are motivated to decompose the multi-source audio semantics into single-source semantics for more effective interactions with visual content. We propose a semantic decomposition method based on product quantization, where the multi-source semantics can be decomposed and represented by several disentangled and noise-suppressed single-source semantics. Furthermore, we introduce a global-to-local quantization mechanism, which distills knowledge from stable global (clip-level) features into local (frame-level) ones, to handle frequent changes in audio semantics. Extensive experiments demonstrate that our semantically decomposed audio representation significantly improves AVS performance, e.g., +21.2% mIoU on the challenging AVS-Semantic benchmark with ResNet50 backbone. https://github.com/lxa9867/QSD.

翻译：视听分割（AVS）是一项具有挑战性的任务，旨在根据视频中的视觉对象及其关联的声学线索对其进行分割。面对多声源和背景干扰，建立稳健的视听对应关系面临独特挑战，原因包括：（1）声源间的复杂纠缠，（2）不同声音事件发生频率的频繁变化。假设声音事件独立发生，多源语义空间可表示为单源子空间的笛卡尔积。受此启发，我们将多源音频语义分解为单源语义，以实现与视觉内容更有效的交互。提出基于乘积量化的语义分解方法，可将多源语义分解并表示为若干解耦且抑制噪声的单源语义。进一步引入全局到局部的量化机制，将稳定的全局（片段级）特征知识蒸馏至局部（帧级）特征，以应对音频语义的频繁变化。大量实验表明，本方法通过语义分解的音频表示显著提升了AVS性能：在基于ResNet50骨干网络的AVS-Semantic基准测试中，mIoU指标提升21.2%。代码开源地址：https://github.com/lxa9867/QSD。