Cross-Modal Adapter: Parameter-Efficient Transfer Learning Approach for Vision-Language Models
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2024
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866916213882355712 |
|---|---|
| author | Yang, Juncheng Li, Zuchao Xie, Shuai Zhu, Weiping Yu, Wei Li, Shijun |
| author_facet | Yang, Juncheng Li, Zuchao Xie, Shuai Zhu, Weiping Yu, Wei Li, Shijun |
| contents | Adapter-based parameter-efficient transfer learning has achieved exciting results in vision-language models. Traditional adapter methods often require training or fine-tuning, facing challenges such as insufficient samples or resource limitations. While some methods overcome the need for training by leveraging image modality cache and retrieval, they overlook the text modality's importance and cross-modal cues for the efficient adaptation of parameters in visual-language models. This work introduces a cross-modal parameter-efficient approach named XMAdapter. XMAdapter establishes cache models for both text and image modalities. It then leverages retrieval through visual-language bimodal information to gather clues for inference. By dynamically adjusting the affinity ratio, it achieves cross-modal fusion, decoupling different modal similarities to assess their respective contributions. Additionally, it explores hard samples based on differences in cross-modal affinity and enhances model performance through adaptive adjustment of sample learning intensity. Extensive experimental results on benchmark datasets demonstrate that XMAdapter outperforms previous adapter-based methods significantly regarding accuracy, generalization, and efficiency. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2404_12588 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Cross-Modal Adapter: Parameter-Efficient Transfer Learning Approach for Vision-Language Models Yang, Juncheng Li, Zuchao Xie, Shuai Zhu, Weiping Yu, Wei Li, Shijun Computer Vision and Pattern Recognition Machine Learning Adapter-based parameter-efficient transfer learning has achieved exciting results in vision-language models. Traditional adapter methods often require training or fine-tuning, facing challenges such as insufficient samples or resource limitations. While some methods overcome the need for training by leveraging image modality cache and retrieval, they overlook the text modality's importance and cross-modal cues for the efficient adaptation of parameters in visual-language models. This work introduces a cross-modal parameter-efficient approach named XMAdapter. XMAdapter establishes cache models for both text and image modalities. It then leverages retrieval through visual-language bimodal information to gather clues for inference. By dynamically adjusting the affinity ratio, it achieves cross-modal fusion, decoupling different modal similarities to assess their respective contributions. Additionally, it explores hard samples based on differences in cross-modal affinity and enhances model performance through adaptive adjustment of sample learning intensity. Extensive experimental results on benchmark datasets demonstrate that XMAdapter outperforms previous adapter-based methods significantly regarding accuracy, generalization, and efficiency. |
| title | Cross-Modal Adapter: Parameter-Efficient Transfer Learning Approach for Vision-Language Models |
| topic | Computer Vision and Pattern Recognition Machine Learning |
| url | https://arxiv.org/abs/2404.12588 |