面向换衣行人重识别的多信息提示学习
Multiple Information Prompt Learning for Cloth-Changing Person Re-Identification
AI总结：
针对换衣行人重识别中现有方法受图像质量和辅助模型限制的问题，提出多信息提示学习方案，通过三个模块提取身份鲁棒特征，在多个基准数据集上取得优于现有最优方法的性能。
摘要：
换衣行人重识别是一项更贴近现实场景的研究课题，聚焦于解决行人更换衣物后的行人重识别问题。该领域的核心挑战在于克服类内与类间差异的复杂相互作用，并提取不受外观变化影响的特征。收集充足的数据用于模型训练将极大助力解决这一问题，但实际中很难采集到多样化的数据集。现有方法主要侧重于从原始图像中隐式学习身份信息，或引入额外的辅助模型，这些方法在很大程度上受限于图像质量和额外模型的性能。\n为解决上述问题，受提示学习启发，我们提出了一种新颖的多信息提示学习（MIPL）方案用于换衣行人重识别，该方案通过多信息的共同提示引导学习身份鲁棒特征。具体而言，我们设计了衣物信息剥离（CIS）模块，将衣物信息从原始RGB图像特征中解耦出来，以抵消衣物外观的影响；提出了生物引导注意力（BGA）模块，以增强模型对关键信息的学习强度；采用双长度混合补丁（DHP）模块，使特征具备多样化覆盖范围，从而最大程度降低特征偏差的影响。\n大量实验表明，所提方法在LTCC、Celeb-reID、Celeb-reID-light和CSCC数据集上的表现均优于所有现有最优方法，rank-1准确率分别达到74.8%、73.3%、66.0%和88.1%。在PRCC数据集上，与AIM（CVPR23）、ACID（TIP23）和SCNet（MM23）相比，MIPL的rank-1准确率分别提升了11.3%、13.8%和7.9%。
英文摘要：
Cloth-changing person re-identification is a subject closer to the real world, which focuses on solving the problem of person re-identification after pedestrians change clothes. The primary challenge in this field is to overcome the complex interplay between intra-class and inter-class variations and to identify features that remain unaffected by changes in appearance. Sufficient data collection for model training would significantly aid in addressing this problem. However, it is challenging to gather diverse datasets in practice. Current methods focus on implicitly learning identity information from the original image or introducing additional auxiliary models, which are largely limited by the quality of the image and the performance of the additional model. To address these issues, inspired by prompt learning, we propose a novel multiple information prompt learning (MIPL) scheme for cloth-changing person ReID, which learns identity robust features through the common prompt guidance of multiple messages. Specifically, the clothing information stripping (CIS) module is designed to decouple the clothing information from the original RGB image features to counteract the influence of clothing appearance. The Bio-guided attention (BGA) module is proposed to increase the learning intensity of the model for key information. A dual-length hybrid patch (DHP) module is employed to make the features have diverse coverage to minimize the impact of feature bias. Extensive experiments demonstrate that the proposed method outperforms all state-of-the-art methods on the LTCC, Celeb-reID, Celeb-reID-light, and CSCC datasets, achieving rank-1 scores of 74.8%, 73.3%, 66.0%, and 88.1%, respectively. When compared to AIM (CVPR23), ACID (TIP23), and SCNet (MM23), MIPL achieves rank-1 improvements of 11.3%, 13.8%, and 7.9%, respectively, on the PRCC dataset.
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。
