Selective Noise Suppression and Discriminative Mutual Interaction for Robust Audio-Visual Segmentation

TL;DR

This paper introduces SDAVS, a novel approach for robust audio-visual segmentation that effectively suppresses noise and enhances the interaction between audio and visual data, leading to improved performance in complex scenes.

Contribution

The paper proposes the SNRP and DAMF modules, which together improve noise suppression and discriminative interaction in AVS models, a novel combination for this task.

Findings

Achieves state-of-the-art results on AVS benchmarks.

Effective noise suppression in multi-source scenes.

Enhanced audio-visual representation consistency.

Abstract

The ability to capture and segment sounding objects in dynamic visual scenes is crucial for the development of Audio-Visual Segmentation (AVS) tasks. While significant progress has been made in this area, the interaction between audio and visual modalities still requires further exploration. In this work, we aim to answer the following questions: How can a model effectively suppress audio noise while enhancing relevant audio information? How can we achieve discriminative interaction between the audio and visual modalities? To this end, we propose SDAVS, equipped with the Selective Noise-Resilient Processor (SNRP) module and the Discriminative Audio-Visual Mutual Fusion (DAMF) strategy. The proposed SNRP mitigates audio noise interference by selectively emphasizing relevant auditory cues, while DAMF ensures more consistent audio-visual representations. Experimental results demonstrate that our proposed method achieves state-of-the-art performance on benchmark AVS datasets, especially in multi-source and complex scenes. \textit{The code and model are available at https://github.com/happylife-pk/SDAVS}.