Learning Hierarchical Prompt with Structured Linguistic Knowledge for Vision-Language Models

TL;DR

This paper introduces Hierarchical Prompt Tuning (HPT), a novel method that leverages structured linguistic knowledge and hierarchical modeling to improve prompt learning for vision-language models, outperforming existing methods.

Contribution

It proposes a hierarchical prompt tuning framework that models both structured and conventional knowledge using a relationship-guided attention module and multi-level prompts.

Findings

HPT outperforms state-of-the-art methods in experiments.

HPT effectively models complex entity-attribute relationships.

HPT demonstrates strong generalization across tasks.

Abstract

Prompt learning has become a prevalent strategy for adapting vision-language foundation models to downstream tasks. As large language models (LLMs) have emerged, recent studies have explored the use of category-related descriptions as input to enhance prompt effectiveness. Nevertheless, conventional descriptions fall short of structured information that effectively represents the interconnections among entities or attributes linked to a particular category. To address this limitation and prioritize harnessing structured knowledge, this paper advocates for leveraging LLMs to build a graph for each description to model the entities and attributes describing the category, as well as their correlations. Preexisting prompt tuning methods exhibit inadequacies in managing this structured knowledge. Consequently, we propose a novel approach called Hierarchical Prompt Tuning (HPT), which enables simultaneous modeling of both structured and conventional linguistic knowledge. Specifically, we introduce a relationship-guided attention module to capture pair-wise associations among entities and attributes for low-level prompt learning. In addition, by incorporating high-level and global-level prompts modeling overall semantics, the proposed hierarchical structure forges cross-level interlinks and empowers the model to handle more complex and long-term relationships. Extensive experiments demonstrate that our HPT shows strong effectiveness and generalizes much better than existing SOTA methods. Our code is available at https://github.com/Vill-Lab/2024-AAAI-HPT.