BMIP: Bi-directional Modality Interaction Prompt Learning for VLM
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866913647858548736 |
|---|---|
| author | Lv, Song-Lin Chen, Yu-Yang Zhou, Zhi Yang, Ming Guo, Lan-Zhe |
| author_facet | Lv, Song-Lin Chen, Yu-Yang Zhou, Zhi Yang, Ming Guo, Lan-Zhe |
| contents | Vision-language models (VLMs) have exhibited remarkable generalization capabilities, and prompt learning for VLMs has attracted great attention for the ability to adapt pre-trained VLMs to specific downstream tasks. However, existing studies mainly focus on single-modal prompts or uni-directional modality interaction, overlooking the powerful alignment effects resulting from the interaction between the vision and language modalities. To this end, we propose a novel prompt learning method called $\underline{\textbf{B}}i-directional \underline{\textbf{M}}odality \underline{\textbf{I}}nteraction \underline{\textbf{P}}rompt (BMIP)$, which dynamically weights bi-modal information through learning the information of the attention layer, enhancing trainability and inter-modal consistency compared to simple information aggregation methods. To evaluate the effectiveness of prompt learning methods, we propose a more realistic evaluation paradigm called open-world generalization complementing the widely adopted cross-dataset transfer and domain generalization tasks. Comprehensive experiments on various datasets reveal that BMIP not only outperforms current state-of-the-art methods across all three evaluation paradigms but is also flexible enough to be combined with other prompt-based methods for consistent performance enhancement. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2501_07769 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | BMIP: Bi-directional Modality Interaction Prompt Learning for VLM Lv, Song-Lin Chen, Yu-Yang Zhou, Zhi Yang, Ming Guo, Lan-Zhe Machine Learning Computer Vision and Pattern Recognition Vision-language models (VLMs) have exhibited remarkable generalization capabilities, and prompt learning for VLMs has attracted great attention for the ability to adapt pre-trained VLMs to specific downstream tasks. However, existing studies mainly focus on single-modal prompts or uni-directional modality interaction, overlooking the powerful alignment effects resulting from the interaction between the vision and language modalities. To this end, we propose a novel prompt learning method called $\underline{\textbf{B}}i-directional \underline{\textbf{M}}odality \underline{\textbf{I}}nteraction \underline{\textbf{P}}rompt (BMIP)$, which dynamically weights bi-modal information through learning the information of the attention layer, enhancing trainability and inter-modal consistency compared to simple information aggregation methods. To evaluate the effectiveness of prompt learning methods, we propose a more realistic evaluation paradigm called open-world generalization complementing the widely adopted cross-dataset transfer and domain generalization tasks. Comprehensive experiments on various datasets reveal that BMIP not only outperforms current state-of-the-art methods across all three evaluation paradigms but is also flexible enough to be combined with other prompt-based methods for consistent performance enhancement. |
| title | BMIP: Bi-directional Modality Interaction Prompt Learning for VLM |
| topic | Machine Learning Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2501.07769 |