Progressive Confident Masking Attention Network for Audio-Visual Segmentation
This addresses the challenge of segmenting sounding objects in scenes for applications in multimedia and robotics, but it appears incremental as it builds on existing AVS methods with improvements in integration and efficiency.
The paper tackles the Audio-Visual Segmentation (AVS) problem by proposing the Progressive Confident Masking Attention Network (PMCANet), which integrates audio and visual information more effectively and reduces computational costs, outperforming other AVS methods.
Audio and visual signals typically occur simultaneously, and humans possess an innate ability to correlate and synchronize information from these two modalities. Recently, a challenging problem known as Audio-Visual Segmentation (AVS) has emerged, intending to produce segmentation maps for sounding objects within a scene. However, the methods proposed so far have not sufficiently integrated audio and visual information, and the computational costs have been extremely high. Additionally, the outputs of different stages have not been fully utilized. To facilitate this research, we introduce a novel Progressive Confident Masking Attention Network (PMCANet). It leverages attention mechanisms to uncover the intrinsic correlations between audio signals and visual frames. Furthermore, we design an efficient and effective cross-attention module to enhance semantic perception by selecting query tokens. This selection is determined through confidence-driven units based on the network's multi-stage predictive outputs. Experiments demonstrate that our network outperforms other AVS methods while requiring less computational resources. The code is available at: https://github.com/PrettyPlate/PCMANet.