Delayed Commitment for Representation Readiness in Stage-wise Audio-Visual Learning
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_ | 1866914526521196544 |
|---|---|
| author | Xu, Xinmeng Xie, Haoran Qin, S. Joe Li, Lin Tao, Xiaohui Wang, Fu Lee |
| author_facet | Xu, Xinmeng Xie, Haoran Qin, S. Joe Li, Lin Tao, Xiaohui Wang, Fu Lee |
| contents | Stage-wise audio-visual encoders propagate fused intermediate states across layers, making the formation of later representations depend on the readiness of earlier fusion states. Strong local audio-visual agreement provides useful correspondence evidence, yet a fused state also needs sufficient cross-layer and cross-modal support before it can reliably guide later fusion. This paper studies this issue through propagation-aware representation readiness and formulates premature perceptual commitment as a readiness-deficiency problem, where local plausibility, propagation influence, and support insufficiency jointly appear at an intermediate stage. We propose the Delayed Perceptual Commitment Network (DPC-Net), an encoder-level framework that estimates an observable readiness-deficiency surrogate, localizes the intervention-sensitive bottleneck, and applies support-aware correction with cross-layer and cross-modal evidence. DPC-Net preserves task-specific heads, losses, decoding modules, and evaluation protocols, making it applicable to different audio-visual tasks through encoder-side intervention. Experiments on audio-visual speech separation, audio-visual event localization, and audio-visual speech recognition show consistent improvements across reconstruction, localization, and recognition regimes. Further analyses on component contribution, selection criteria, counterfactual intervention, and readiness trajectories support the effectiveness of readiness-guided bottleneck correction. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2605_01673 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Delayed Commitment for Representation Readiness in Stage-wise Audio-Visual Learning Xu, Xinmeng Xie, Haoran Qin, S. Joe Li, Lin Tao, Xiaohui Wang, Fu Lee Sound Multimedia Stage-wise audio-visual encoders propagate fused intermediate states across layers, making the formation of later representations depend on the readiness of earlier fusion states. Strong local audio-visual agreement provides useful correspondence evidence, yet a fused state also needs sufficient cross-layer and cross-modal support before it can reliably guide later fusion. This paper studies this issue through propagation-aware representation readiness and formulates premature perceptual commitment as a readiness-deficiency problem, where local plausibility, propagation influence, and support insufficiency jointly appear at an intermediate stage. We propose the Delayed Perceptual Commitment Network (DPC-Net), an encoder-level framework that estimates an observable readiness-deficiency surrogate, localizes the intervention-sensitive bottleneck, and applies support-aware correction with cross-layer and cross-modal evidence. DPC-Net preserves task-specific heads, losses, decoding modules, and evaluation protocols, making it applicable to different audio-visual tasks through encoder-side intervention. Experiments on audio-visual speech separation, audio-visual event localization, and audio-visual speech recognition show consistent improvements across reconstruction, localization, and recognition regimes. Further analyses on component contribution, selection criteria, counterfactual intervention, and readiness trajectories support the effectiveness of readiness-guided bottleneck correction. |
| title | Delayed Commitment for Representation Readiness in Stage-wise Audio-Visual Learning |
| topic | Sound Multimedia |
| url | https://arxiv.org/abs/2605.01673 |