DiffGAP: A Lightweight Diffusion Module in Contrastive Space for Bridging Cross-Model Gap
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2025
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866909538466136064 |
|---|---|
| author | Mo, Shentong Chen, Zehua Bao, Fan Zhu, Jun |
| author_facet | Mo, Shentong Chen, Zehua Bao, Fan Zhu, Jun |
| contents | Recent works in cross-modal understanding and generation, notably through models like CLAP (Contrastive Language-Audio Pretraining) and CAVP (Contrastive Audio-Visual Pretraining), have significantly enhanced the alignment of text, video, and audio embeddings via a single contrastive loss. However, these methods often overlook the bidirectional interactions and inherent noises present in each modality, which can crucially impact the quality and efficacy of cross-modal integration. To address this limitation, we introduce DiffGAP, a novel approach incorporating a lightweight generative module within the contrastive space. Specifically, our DiffGAP employs a bidirectional diffusion process tailored to bridge the cross-modal gap more effectively. This involves a denoising process on text and video embeddings conditioned on audio embeddings and vice versa, thus facilitating a more nuanced and robust cross-modal interaction. Our experimental results on VGGSound and AudioCaps datasets demonstrate that DiffGAP significantly improves performance in video/text-audio generation and retrieval tasks, confirming its effectiveness in enhancing cross-modal understanding and generation capabilities. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2503_12131 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | DiffGAP: A Lightweight Diffusion Module in Contrastive Space for Bridging Cross-Model Gap Mo, Shentong Chen, Zehua Bao, Fan Zhu, Jun Computer Vision and Pattern Recognition Artificial Intelligence Machine Learning Sound Audio and Speech Processing Recent works in cross-modal understanding and generation, notably through models like CLAP (Contrastive Language-Audio Pretraining) and CAVP (Contrastive Audio-Visual Pretraining), have significantly enhanced the alignment of text, video, and audio embeddings via a single contrastive loss. However, these methods often overlook the bidirectional interactions and inherent noises present in each modality, which can crucially impact the quality and efficacy of cross-modal integration. To address this limitation, we introduce DiffGAP, a novel approach incorporating a lightweight generative module within the contrastive space. Specifically, our DiffGAP employs a bidirectional diffusion process tailored to bridge the cross-modal gap more effectively. This involves a denoising process on text and video embeddings conditioned on audio embeddings and vice versa, thus facilitating a more nuanced and robust cross-modal interaction. Our experimental results on VGGSound and AudioCaps datasets demonstrate that DiffGAP significantly improves performance in video/text-audio generation and retrieval tasks, confirming its effectiveness in enhancing cross-modal understanding and generation capabilities. |
| title | DiffGAP: A Lightweight Diffusion Module in Contrastive Space for Bridging Cross-Model Gap |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence Machine Learning Sound Audio and Speech Processing |
| url | https://arxiv.org/abs/2503.12131 |