Abstract
Clothes-changing person re-identification (CC-ReID) aims to recognize individuals under different clothing scenarios. Current CC-ReID approaches either concentrate on modeling body shape using additional modalities including silhouette, pose, and body mesh, potentially causing the model to overlook other critical biometric traits such as gender, age, and style, or they incorporate supervision through additional labels that the model tries to disregard or emphasize, such as clothing or personal attributes. However, these annotations are discrete in nature and do not capture comprehensive descriptions. In this work, we propose DIFFER: Disentangle Identity Features From Entangled Representations, a novel adversarial learning method that leverages textual descriptions to disentangle identity features. Recognizing that image features inherently mix inseparable information, DIFFER introduces NBDetach, a mechanism designed for feature disentanglement by leveraging the separable nature of text descriptions as supervision. It partitions the feature space into distinct subspaces and, through gradient reversal layers, effectively separates identity-related features from non-biometric features. We evaluate DIFFER on 4 different benchmark datasets (LTCC, PRCC, CelebreID-Light, and CCVID) to demonstrate its effectiveness and provide state-of-the-art performance across all the benchmarks. DIFFER consistently outperforms the baseline method, with improvements in top-1 accuracy of 3.6% on LTCC, 3.4% on PRCC, 2.5% on CelebReID-Light, and 1% on CCVID. Our code can be found here.
Abstract (translated)
衣物变化人物再识别（CC-ReID）的目标是在不同的穿着场景下识别人体。当前的CC-ReID方法要么专注于使用额外模态如轮廓、姿态和身体网格来建模人体形状，这可能导致模型忽略性别、年龄和风格等其他关键生物特征；要么通过引入附加标签（例如衣物或个人属性）进行监督，这些标签可能被模型试图忽略或强调。然而，这些注释本质上是离散的，并不能捕捉全面描述。 为此，我们提出了DIFFER：从缠结表示中分离身份特征的一种新颖对抗学习方法，该方法利用文本描述来分离身份特征。认识到图像特征内在地混合了不可分割的信息，DIFFER引入了NBDetach机制，这是一种通过利用文本描述作为监督的可分性质来进行特征解纠缠的设计。它将特征空间划分为不同的子空间，并通过使用梯度反转层有效地区分与身份相关的特征和非生物识别特征。 我们在4个不同基准数据集（LTCC、PRCC、CelebreID-Light 和 CCVID）上评估了DIFFER，以证明其有效性并提供所有基准上的最新性能。与基线方法相比，DIFFER在LTCC上提高了3.6%的top-1准确率，在PRCC上提高了3.4%，在CelebReID-Light上提高了2.5%，在CCVID上提高了1%。 我们的代码可以在这里找到：[此处提供链接]。
URL
https://arxiv.org/abs/2503.22912
