论文标题
通过重新识别的人的部分分辨率学习多样的功能
Learning Diverse Features with Part-Level Resolution for Person Re-Identification
论文作者
论文摘要
学习多样化的功能是重新识别成功的关键。已经广泛提出了用于学习本地表示的各种基于零件的方法，但是，这些方法仍然不如对人重新识别的表现最佳的方法。本文提出，基于OMNI级网络（OSNET）的零件级特征分辨率（以实现特征多样性）的想法，构建了一个强大的轻型网络体系结构，称为PLR-OSNET。拟议的PLR-OSNET有两个分支，一个分支用于全局特征表示，另一个用于本地特征表示的分支。本地分支采用零件级特征分辨率的统一分区策略，但仅产生单个身份预测损失，这与现有的基于零件的方法形成了鲜明的对比。经验证据表明，拟议的PLR-OSNET在流行人士Re-ID数据集上取得了最先进的性能，包括Market1501，Dukemtmc-Reid和Cuhk03，尽管模型尺寸很小。
Learning diverse features is key to the success of person re-identification. Various part-based methods have been extensively proposed for learning local representations, which, however, are still inferior to the best-performing methods for person re-identification. This paper proposes to construct a strong lightweight network architecture, termed PLR-OSNet, based on the idea of Part-Level feature Resolution over the Omni-Scale Network (OSNet) for achieving feature diversity. The proposed PLR-OSNet has two branches, one branch for global feature representation and the other branch for local feature representation. The local branch employs a uniform partition strategy for part-level feature resolution but produces only a single identity-prediction loss, which is in sharp contrast to the existing part-based methods. Empirical evidence demonstrates that the proposed PLR-OSNet achieves state-of-the-art performance on popular person Re-ID datasets, including Market1501, DukeMTMC-reID and CUHK03, despite its small model size.
