arXiv 2503.237222025-10-30cs.CV

LATex：利用基于属性的文本知识实现空地行人重识别

LATex: Leveraging Attribute-based Text Knowledge for Aerial-Ground Person Re-Identification

School of Future Technology, School of Artificial Intelligence, Dalian University of Technology（未来技术学院、人工智能学院、大连理工大学）

Pingping Zhang, Xiang Hu, Yuhao Wang, Huchuan Lu

备注：: More modifications may be performed

阅读 PDF

arXiv 页面 ↗HTML 原文 ↗

AI总结：

针对空地行人重识别中属性语义利用不足、全量微调成本高的问题，提出基于CLIP的LATex框架，通过提示调优结合属性文本知识提升重识别性能，经三个基准实验验证有效。

摘要：

作为智能交通系统中的一项重要任务，空地行人重识别（AG-ReID）旨在跨不同视角的异构摄像头检索特定行人。现有方法通常采用基于深度学习的模型，重点提取视角不变特征，但往往忽略了行人属性中的语义信息。此外，现有训练策略常依赖大规模模型的全量微调，大幅增加了训练成本。针对这些问题，我们提出了一种名为LATex的新型AG-ReID框架，采用提示调优策略来利用基于属性的文本知识。具体而言，我们基于对比语言-图像预训练（CLIP）模型，首先提出属性感知图像编码器（AIE），从输入图像中同时提取全局语义特征和属性感知特征；接着利用这些特征，提出提示属性分类器组（PACG）以预测行人属性并获取属性表示；最后设计耦合提示模板（CPT），将属性表示与视角信息转化为结构化语句，这些语句经CLIP的文本编码器处理后生成更具判别性的特征。由此，本框架可充分利用基于属性的文本知识提升AG-ReID性能。在三个AG-ReID基准上的大量实验验证了所提方法的有效性，源代码可在https://github.com/kevinhu314/LATex获取。

英文摘要：

As an important task in intelligent transportation systems, Aerial-Ground person Re-IDentification (AG-ReID) aims to retrieve specific persons across heterogeneous cameras in different viewpoints. Previous methods typically adopt deep learning-based models, focusing on extracting view-invariant features. However, they usually overlook the semantic information in person attributes. In addition, existing training strategies often rely on full fine-tuning large-scale models, which significantly increases training costs. To address these issues, we propose a novel framework named LATex for AG-ReID, which adopts prompt-tuning strategies to leverage attribute-based text knowledge. Specifically, with the Contrastive Language-Image Pre-training (CLIP) model, we first propose an Attribute-aware Image Encoder (AIE) to extract both global semantic features and attribute-aware features from input images. Then, with these features, we propose a Prompted Attribute Classifier Group (PACG) to predict person attributes and obtain attribute representations. Finally, we design a Coupled Prompt Template (CPT) to transform attribute representations and view information into structured sentences. These sentences are processed by the text encoder of CLIP to generate more discriminative features. As a result, our framework can fully leverage attribute-based text knowledge to improve AG-ReID performance. Extensive experiments on three AG-ReID benchmarks demonstrate the effectiveness of our proposed methods. The source code is available at https://github.com/kevinhu314/LATex.

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。