{"ID":2825719,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2512.20117","arxiv_id":"2512.20117","title":"DDAVS: Disentangled Audio Semantics and Delayed Bidirectional Alignment for Audio-Visual Segmentation","abstract":"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/","short_abstract":"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 w...","url_abs":"https://arxiv.org/abs/2512.20117","url_pdf":"https://arxiv.org/pdf/2512.20117v1","authors":"[\"Jingqi Tian\",\"Yiheng Du\",\"Haoji Zhang\",\"Yuji Wang\",\"Isaac Ning Lee\",\"Xulong Bai\",\"Tianrui Zhu\",\"Jingxuan Niu\",\"Yansong Tang\"]","published":"2025-12-23T07:21:21Z","proceeding":"cs.CV","tasks":"[\"cs.CV\",\"cs.SD\",\"eess.AS\"]","methods":"[]","has_code":false}