Selective Noise Suppression and Discriminative Mutual Interaction for Robust Audio-Visual Segmentation
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866915885587890176 |
|---|---|
| author | Peng, Kai Shen, Yunzhe Zhang, Miao Liu, Leiye Han, Yidong Ji, Wei Li, Jingjing Piao, Yongri Lu, Huchuan |
| author_facet | Peng, Kai Shen, Yunzhe Zhang, Miao Liu, Leiye Han, Yidong Ji, Wei Li, Jingjing Piao, Yongri Lu, Huchuan |
| contents | 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}. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2603_14203 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Selective Noise Suppression and Discriminative Mutual Interaction for Robust Audio-Visual Segmentation Peng, Kai Shen, Yunzhe Zhang, Miao Liu, Leiye Han, Yidong Ji, Wei Li, Jingjing Piao, Yongri Lu, Huchuan Computer Vision and Pattern Recognition 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}. |
| title | Selective Noise Suppression and Discriminative Mutual Interaction for Robust Audio-Visual Segmentation |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2603.14203 |