Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2507.08410 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866915383152214016 |
|---|---|
| author | Yang, Shijun Zhang, Xiang Zhao, Wanqing Luo, Hangzai Zhong, Sheng Peng, Jinye Fan, Jianping |
| author_facet | Yang, Shijun Zhang, Xiang Zhao, Wanqing Luo, Hangzai Zhong, Sheng Peng, Jinye Fan, Jianping |
| contents | Prompt learning facilitates the efficient adaptation of Vision-Language Models (VLMs) to various downstream tasks. However, it faces two significant challenges: (1) inadequate modeling of class embedding distributions for unseen instances, leading to suboptimal generalization on novel classes; (2) prevailing methodologies predominantly confine cross-modal alignment to the final output layer of vision and text encoders, which fundamentally limits their capacity to preserve topological consistency with pre-trained multi-modal embedding spaces. To this end, we introduce MuGCP (Multi-modal Mutual-Guidance Conditional Prompt Learning), a novel paradigm designed for conditional prompt generation. MuGCP leverages Multi-modal Large Language Models (MLLMs) as conditional prompt learners to adaptively generate Semantic Conditional Prompts (SCP) that incorporate rich, fine-grained high-level semantic knowledge for image instances. To ensure effective alignment and interaction across the multi-modal space of Vision-Language Models (VLMs), we introduce the Attention Mutual-Guidance (AMG) module, which facilitates interactions between visual and semantic information. Through mutual guidance, the AMG module generates Visual Conditional Prompts (VCP), enhancing the model's performance in multi-modal tasks. Additionally, we present a Multi-Prompt Fusion (MPF) mechanism that integrates SCP and VCP with contextual prompts, ensuring seamless coordination among the different prompts and enhancing the modeling of class embeddings and instance-specific knowledge. Our MuGCP outperforms existing state-of-the-art methods on 14 different datasets. The code will be made available after publication. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2507_08410 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Multi-modal Mutual-Guidance Conditional Prompt Learning for Vision-Language Models Yang, Shijun Zhang, Xiang Zhao, Wanqing Luo, Hangzai Zhong, Sheng Peng, Jinye Fan, Jianping Computer Vision and Pattern Recognition Prompt learning facilitates the efficient adaptation of Vision-Language Models (VLMs) to various downstream tasks. However, it faces two significant challenges: (1) inadequate modeling of class embedding distributions for unseen instances, leading to suboptimal generalization on novel classes; (2) prevailing methodologies predominantly confine cross-modal alignment to the final output layer of vision and text encoders, which fundamentally limits their capacity to preserve topological consistency with pre-trained multi-modal embedding spaces. To this end, we introduce MuGCP (Multi-modal Mutual-Guidance Conditional Prompt Learning), a novel paradigm designed for conditional prompt generation. MuGCP leverages Multi-modal Large Language Models (MLLMs) as conditional prompt learners to adaptively generate Semantic Conditional Prompts (SCP) that incorporate rich, fine-grained high-level semantic knowledge for image instances. To ensure effective alignment and interaction across the multi-modal space of Vision-Language Models (VLMs), we introduce the Attention Mutual-Guidance (AMG) module, which facilitates interactions between visual and semantic information. Through mutual guidance, the AMG module generates Visual Conditional Prompts (VCP), enhancing the model's performance in multi-modal tasks. Additionally, we present a Multi-Prompt Fusion (MPF) mechanism that integrates SCP and VCP with contextual prompts, ensuring seamless coordination among the different prompts and enhancing the modeling of class embeddings and instance-specific knowledge. Our MuGCP outperforms existing state-of-the-art methods on 14 different datasets. The code will be made available after publication. |
| title | Multi-modal Mutual-Guidance Conditional Prompt Learning for Vision-Language Models |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2507.08410 |