.png){kind=icon}
.png){kind=icon}
Return
Complementary and Contrastive Learning for Audio-Visual Segmentation
.png){kind=icon}
PRE
AI
DOI：10.1109/TMM.2025.3599048.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Audio-Visual Segmentation (AVS) aims to generate pixel-wise segmentation maps that correlate with the auditory signals of objects. This field has seen significant progress with numerous CNN and Transformer-based methods enhancing the segmentation accuracy and robustness. Traditional CNN approaches manage audio-visual interactions through basic operations like padding and multiplications but are restricted by CNNs’ limited local receptive field. More recently, Transformer-based methods treat auditory cues as queries, utilizing attention mechanisms to enhance audio-visual cooperation within frames. Nevertheless, they typically struggle to extract multimodal coefficients and temporal dynamics adequately. To overcome these limitations, we present the Complementary and Contrastive Transformer (CCFormer), a novel framework adept at processing both local and global information and capturing spatial-temporal context comprehensively. Our CCFormer initiates with the Early Integration Module (EIM) that employs a parallel bilateral architecture, merging multi-scale visual features with audio data to boost cross-modal complementarity. To extract the intra-frame spatial features and facilitate the perception of temporal coherence, we introduce the Multi-query Transformer Module (MTM), which dynamically endows audio queries with learning capabilities and models the frame and video-level relations simultaneously. Furthermore, we propose the Bi-modal Contrastive Learning (BCL) to promote the alignment across both modalities in the unified feature space. Through the effective combination of those designs, our method sets new state-of-the-art benchmarks across the S4, MS3 and AVSS datasets.
Keywords:
Audio-visual segmentation (AVS)
complementary learning
contrastive learning
multimodal transformer
Journal
IF:
9.7
Papers:
4.4K
Citations:
2.4W