DDAVS: Disentangled Audio Semantics and Delayed Bidirectional Alignment for Audio-Visual Segmentation

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Tian, Jingqi, Du, Yiheng, Zhang, Haoji, Wang, Yuji, Lee, Isaac Ning, Bai, Xulong, Zhu, Tianrui, Niu, Jingxuan, Tang, Yansong
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866909974554214400
author Tian, Jingqi
Du, Yiheng
Zhang, Haoji
Wang, Yuji
Lee, Isaac Ning
Bai, Xulong
Zhu, Tianrui
Niu, Jingxuan
Tang, Yansong
author_facet Tian, Jingqi
Du, Yiheng
Zhang, Haoji
Wang, Yuji
Lee, Isaac Ning
Bai, Xulong
Zhu, Tianrui
Niu, Jingxuan
Tang, Yansong
contents Audio-Visual Segmentation (AVS) aims to localize sound-producing objects at the pixel level by jointly leveraging auditory and visual information. However, existing methods often suffer from multi-source entanglement and audio-visual misalignment, which lead to biases toward louder or larger objects while overlooking weaker, smaller, or co-occurring sources. To address these challenges, we propose DDAVS, a Disentangled Audio Semantics and Delayed Bidirectional Alignment framework. To mitigate multi-source entanglement, DDAVS employs learnable queries to extract audio semantics and anchor them within a structured semantic space derived from an audio prototype memory bank. This is further optimized through contrastive learning to enhance discriminability and robustness. To alleviate audio-visual misalignment, DDAVS introduces dual cross-attention with delayed modality interaction, improving the robustness of multimodal alignment. Extensive experiments on the AVS-Objects and VPO benchmarks demonstrate that DDAVS consistently outperforms existing approaches, exhibiting strong performance across single-source, multi-source, and multi-instance scenarios. These results validate the effectiveness and generalization ability of our framework under challenging real-world audio-visual segmentation conditions. Project page: https://trilarflagz.github.io/DDAVS-page/
format Preprint
id arxiv_https___arxiv_org_abs_2512_20117
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle DDAVS: Disentangled Audio Semantics and Delayed Bidirectional Alignment for Audio-Visual Segmentation
Tian, Jingqi
Du, Yiheng
Zhang, Haoji
Wang, Yuji
Lee, Isaac Ning
Bai, Xulong
Zhu, Tianrui
Niu, Jingxuan
Tang, Yansong
Computer Vision and Pattern Recognition
Sound
Audio and Speech Processing
Audio-Visual Segmentation (AVS) aims to localize sound-producing objects at the pixel level by jointly leveraging auditory and visual information. However, existing methods often suffer from multi-source entanglement and audio-visual misalignment, which lead to biases toward louder or larger objects while overlooking weaker, smaller, or co-occurring sources. To address these challenges, we propose DDAVS, a Disentangled Audio Semantics and Delayed Bidirectional Alignment framework. To mitigate multi-source entanglement, DDAVS employs learnable queries to extract audio semantics and anchor them within a structured semantic space derived from an audio prototype memory bank. This is further optimized through contrastive learning to enhance discriminability and robustness. To alleviate audio-visual misalignment, DDAVS introduces dual cross-attention with delayed modality interaction, improving the robustness of multimodal alignment. Extensive experiments on the AVS-Objects and VPO benchmarks demonstrate that DDAVS consistently outperforms existing approaches, exhibiting strong performance across single-source, multi-source, and multi-instance scenarios. These results validate the effectiveness and generalization ability of our framework under challenging real-world audio-visual segmentation conditions. Project page: https://trilarflagz.github.io/DDAVS-page/
title DDAVS: Disentangled Audio Semantics and Delayed Bidirectional Alignment for Audio-Visual Segmentation
topic Computer Vision and Pattern Recognition
Sound
Audio and Speech Processing
url https://arxiv.org/abs/2512.20117