Saved in:
Bibliographic Details
Main Authors: Zheng, Hao, Yang, Shunzhi, He, Zhuoxin, Yang, Jinfeng, Huang, Zhenhua
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2507.14976
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915445735424000
author Zheng, Hao
Yang, Shunzhi
He, Zhuoxin
Yang, Jinfeng
Huang, Zhenhua
author_facet Zheng, Hao
Yang, Shunzhi
He, Zhuoxin
Yang, Jinfeng
Huang, Zhenhua
contents Pre-trained Vision-Language Models (VLMs) such as CLIP have shown excellent generalization abilities. However, adapting these large-scale models to downstream tasks while preserving their generalization capabilities remains challenging. Although prompt learning methods have shown promise, they suffer from two fundamental bottlenecks that limit generalization: (a) modality isolation, and (b) hierarchical semantic decay. To address these limitations, we propose HiCroPL, a Hierarchical Cross-modal Prompt Learning framework that establishes bidirectional knowledge flow between text and vision modalities, enabling them to refine their semantics mutually. HiCroPL routes knowledge flows by leveraging the complementary strengths of text and vision. In early layers, text prompts inject relatively clear semantics into visual prompts through a hierarchical knowledge mapper, enhancing the representation of low-level visual semantics. In later layers, visual prompts encoding specific task-relevant objects flow back to refine text prompts, enabling deeper alignment. Crucially, our hierarchical knowledge mapper allows representations at multi-scales to be fused, ensuring that deeper representations retain transferable shallow semantics thereby enhancing generalization. We further introduce a lightweight layer-specific knowledge proxy to enable efficient cross-modal interactions. Extensive evaluations across four tasks demonstrate HiCroPL's superior performance, achieving state-of-the-art results on 11 benchmarks with significant improvements. Code is available at: https://github.com/zzeoZheng/HiCroPL.
format Preprint
id arxiv_https___arxiv_org_abs_2507_14976
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Hierarchical Cross-modal Prompt Learning for Vision-Language Models
Zheng, Hao
Yang, Shunzhi
He, Zhuoxin
Yang, Jinfeng
Huang, Zhenhua
Computer Vision and Pattern Recognition
Pre-trained Vision-Language Models (VLMs) such as CLIP have shown excellent generalization abilities. However, adapting these large-scale models to downstream tasks while preserving their generalization capabilities remains challenging. Although prompt learning methods have shown promise, they suffer from two fundamental bottlenecks that limit generalization: (a) modality isolation, and (b) hierarchical semantic decay. To address these limitations, we propose HiCroPL, a Hierarchical Cross-modal Prompt Learning framework that establishes bidirectional knowledge flow between text and vision modalities, enabling them to refine their semantics mutually. HiCroPL routes knowledge flows by leveraging the complementary strengths of text and vision. In early layers, text prompts inject relatively clear semantics into visual prompts through a hierarchical knowledge mapper, enhancing the representation of low-level visual semantics. In later layers, visual prompts encoding specific task-relevant objects flow back to refine text prompts, enabling deeper alignment. Crucially, our hierarchical knowledge mapper allows representations at multi-scales to be fused, ensuring that deeper representations retain transferable shallow semantics thereby enhancing generalization. We further introduce a lightweight layer-specific knowledge proxy to enable efficient cross-modal interactions. Extensive evaluations across four tasks demonstrate HiCroPL's superior performance, achieving state-of-the-art results on 11 benchmarks with significant improvements. Code is available at: https://github.com/zzeoZheng/HiCroPL.
title Hierarchical Cross-modal Prompt Learning for Vision-Language Models
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2507.14976