Hierarchical Prompt Learning for Image- and Text-Based Person Re-Identification

TL;DR

This paper introduces Hierarchical Prompt Learning, a unified framework that improves person re-identification across image and text modalities by jointly optimizing discriminative and semantic alignment tasks using task-aware prompts.

Contribution

It proposes a novel hierarchical prompt generation scheme with a Task-Routed Transformer and cross-modal prompt regularization for improved cross-modal person re-identification.

Findings

Achieves state-of-the-art results on multiple ReID benchmarks.

Effectively models both discriminative identity features and cross-modal semantic alignment.

Demonstrates the superiority of the hierarchical prompt approach over existing methods.

Abstract

Person re-identification (ReID) aims to retrieve target pedestrian images given either visual queries (image-to-image, I2I) or textual descriptions (text-to-image, T2I). Although both tasks share a common retrieval objective, they pose distinct challenges: I2I emphasizes discriminative identity learning, while T2I requires accurate cross-modal semantic alignment. Existing methods often treat these tasks separately, which may lead to representation entanglement and suboptimal performance. To address this, we propose a unified framework named Hierarchical Prompt Learning (HPL), which leverages task-aware prompt modeling to jointly optimize both tasks. Specifically, we first introduce a Task-Routed Transformer, which incorporates dual classification tokens into a shared visual encoder to route features for I2I and T2I branches respectively. On top of this, we develop a hierarchical prompt generation scheme that integrates identity-level learnable tokens with instance-level pseudo-text tokens. These pseudo-tokens are derived from image or text features via modality-specific inversion networks, injecting fine-grained, instance-specific semantics into the prompts. Furthermore, we propose a Cross-Modal Prompt Regularization strategy to enforce semantic alignment in the prompt token space, ensuring that pseudo-prompts preserve source-modality characteristics while enhancing cross-modal transferability. Extensive experiments on multiple ReID benchmarks validate the effectiveness of our method, achieving state-of-the-art performance on both I2I and T2I tasks.