IEEE Trans Image Process. 2023;32:2985-2999. doi: 10.1109/TIP.2023.3277389. Epub 2023 May 26.
Recent person Re-IDentification (ReID) systems have been challenged by changes in personnel clothing, leading to the study of Cloth-Changing person ReID (CC-ReID). Commonly used techniques involve incorporating auxiliary information (e.g., body masks, gait, skeleton, and keypoints) to accurately identify the target pedestrian. However, the effectiveness of these methods heavily relies on the quality of auxiliary information and comes at the cost of additional computational resources, ultimately increasing system complexity. This paper focuses on achieving CC-ReID by effectively leveraging the information concealed within the image. To this end, we introduce an Auxiliary-free Competitive IDentification (ACID) model. It achieves a win-win situation by enriching the identity (ID)-preserving information conveyed by the appearance and structure features while maintaining holistic efficiency. In detail, we build a hierarchical competitive strategy that progressively accumulates meticulous ID cues with discriminating feature extraction at the global, channel, and pixel levels during model inference. After mining the hierarchical discriminative clues for appearance and structure features, these enhanced ID-relevant features are crosswise integrated to reconstruct images for reducing intra-class variations. Finally, by combing with self- and cross-ID penalties, the ACID is trained under a generative adversarial learning framework to effectively minimize the distribution discrepancy between the generated data and real-world data. Experimental results on four public cloth-changing datasets (i.e., PRCC-ReID, VC-Cloth, LTCC-ReID, and Celeb-ReID) demonstrate the proposed ACID can achieve superior performance over state-of-the-art methods. The code is available soon at: https://github.com/BoomShakaY/Win-CCReID.
近期的人员重识别（ReID）系统受到人员衣着变化的挑战，因此研究了换装人员重识别（CC-ReID）。常用的技术涉及引入辅助信息（例如，人体蒙版、步态、骨骼和关键点）来准确识别目标行人。然而，这些方法的有效性严重依赖于辅助信息的质量，并且需要额外的计算资源，最终增加了系统的复杂性。本文专注于通过有效利用图像中隐藏的信息来实现 CC-ReID。为此，我们引入了一种无辅助竞争识别（ACID）模型。它通过丰富外观和结构特征所传达的身份（ID）保留信息，同时保持整体效率，实现了双赢。具体来说，我们构建了一个分层竞争策略，在模型推断过程中，在全局、通道和像素级别逐步积累细致的 ID 线索，并进行具有判别力的特征提取。在挖掘外观和结构特征的分层判别线索后，这些增强的 ID 相关特征被交叉整合，以重建图像，从而减少类内变化。最后，通过结合自 ID 和互 ID 惩罚项，在生成对抗学习框架下对 ACID 进行训练，以有效减小生成数据与真实世界数据之间的分布差异。在四个公共换装数据集（即 PRCC-ReID、VC-Cloth、LTCC-ReID 和 Celeb-ReID）上的实验结果表明，所提出的 ACID 可以优于最先进的方法。代码将很快在：https://github.com/BoomShakaY/Win-CCReID 上提供。
