Guardado en:
| Autores principales: | , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | https://arxiv.org/abs/2504.21375 |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866910922785685504 |
|---|---|
| author | Cho, Sangyeon Jeon, Jangyeong Kim, Mingi Kim, Junyeong |
| author_facet | Cho, Sangyeon Jeon, Jangyeong Kim, Mingi Kim, Junyeong |
| contents | Multi-modal representation learning has become a pivotal area in artificial intelligence, enabling the integration of diverse modalities such as vision, text, and audio to solve complex problems. However, existing approaches predominantly focus on bimodal interactions, such as image-text pairs, which limits their ability to fully exploit the richness of multi-modal data. Furthermore, the integration of modalities in equal-scale environments remains underexplored due to the challenges of constructing large-scale, balanced datasets. In this study, we propose Synergy-CLIP, a novel framework that extends the contrastive language-image pre-training (CLIP) architecture to enhance multi-modal representation learning by integrating visual, textual, and audio modalities. Unlike existing methods that focus on adapting individual modalities to vanilla-CLIP, Synergy-CLIP aligns and captures latent information across three modalities equally. To address the high cost of constructing large-scale multi-modal datasets, we introduce VGG-sound+, a triple-modal dataset designed to provide equal-scale representation of visual, textual, and audio data. Synergy-CLIP is validated on various downstream tasks, including zero-shot classification, where it outperforms existing baselines. Additionally, we introduce a missing modality reconstruction task, demonstrating Synergy-CLIP's ability to extract synergy among modalities in realistic application scenarios. These contributions provide a robust foundation for advancing multi-modal representation learning and exploring new research directions. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2504_21375 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Synergy-CLIP: Extending CLIP with Multi-modal Integration for Robust Representation Learning Cho, Sangyeon Jeon, Jangyeong Kim, Mingi Kim, Junyeong Machine Learning Multi-modal representation learning has become a pivotal area in artificial intelligence, enabling the integration of diverse modalities such as vision, text, and audio to solve complex problems. However, existing approaches predominantly focus on bimodal interactions, such as image-text pairs, which limits their ability to fully exploit the richness of multi-modal data. Furthermore, the integration of modalities in equal-scale environments remains underexplored due to the challenges of constructing large-scale, balanced datasets. In this study, we propose Synergy-CLIP, a novel framework that extends the contrastive language-image pre-training (CLIP) architecture to enhance multi-modal representation learning by integrating visual, textual, and audio modalities. Unlike existing methods that focus on adapting individual modalities to vanilla-CLIP, Synergy-CLIP aligns and captures latent information across three modalities equally. To address the high cost of constructing large-scale multi-modal datasets, we introduce VGG-sound+, a triple-modal dataset designed to provide equal-scale representation of visual, textual, and audio data. Synergy-CLIP is validated on various downstream tasks, including zero-shot classification, where it outperforms existing baselines. Additionally, we introduce a missing modality reconstruction task, demonstrating Synergy-CLIP's ability to extract synergy among modalities in realistic application scenarios. These contributions provide a robust foundation for advancing multi-modal representation learning and exploring new research directions. |
| title | Synergy-CLIP: Extending CLIP with Multi-modal Integration for Robust Representation Learning |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2504.21375 |