Abstract
Person re-identification (person Re-Id) aims to retrieve the pedestrian images of a same person that captured by disjoint and non-overlapping cameras. Lots of researchers recently focuse on this hot issue and propose deep learning based methods to enhance the recognition rate in a supervised or unsupervised manner. However, two limitations that cannot be ignored: firstly, compared with other image retrieval benchmarks, the size of existing person Re-Id datasets are far from meeting the requirement, which cannot provide sufficient pedestrian samples for the training of deep model; secondly, the samples in existing datasets do not have sufficient human motions or postures coverage to provide more priori knowledges for learning. In this paper, we introduce a novel unsupervised pose augmentation cross-view person Re-Id scheme called PAC-GAN to overcome these limitations. We firstly present the formal definition of cross-view pose augmentation and then propose the framework of PAC-GAN that is a novel conditional generative adversarial network (CGAN) based approach to improve the performance of unsupervised corss-view person Re-Id. Specifically, The pose generation model in PAC-GAN called CPG-Net is to generate enough quantity of pose-rich samples from original image and skeleton samples. The pose augmentation dataset is produced by combining the synthesized pose-rich samples with the original samples, which is fed into the corss-view person Re-Id model named Cross-GAN. Besides, we use weight-sharing strategy in the CPG-Net to improve the quality of new generated samples. To the best of our knowledge, we are the first try to enhance the unsupervised cross-view person Re-Id by pose augmentation, and the results of extensive experiments show that the proposed scheme can combat the state-of-the-arts.
Abstract (translated)
人员重新识别（PersonReID）的目的是检索由不相交和不重叠的摄像头捕获的同一个人的行人图像。近年来，许多研究者关注这一热点问题，并提出了基于深度学习的方法，以有监督或无监督的方式提高识别率。然而，存在两个不容忽视的局限性：一是与其他图像检索基准相比，现有人脸识别数据集的大小远远不能满足要求，不能为深度模型的训练提供足够的行人样本；二是现有数据集的样本没有足够的人体运动。或姿势覆盖，为学习提供更多先验知识。为了克服这些局限性，本文提出了一种新的无监督姿态增强人眼识别方案PAC-GAN。首先给出了交叉视点姿态增强的形式定义，然后提出了一种新的基于条件生成对抗网络（CGAN）的PAC-GAN框架，以提高无监督CORSS视点人脸识别的性能，具体地说，PAC-GAN中称为CPG网的姿态生成模型是生成ENOU。从原始图像和骨架样本中获取的姿势丰富样本量。将合成的多姿态样本与原始样本相结合，生成姿态增强数据集，并将其输入到名为CrossGan的CorssView-PersonReID模型中。此外，我们在CPG网中使用重量分担策略来提高新生成样本的质量。据我们所知，我们是第一个尝试通过姿势增强来增强无监督的跨视野人的真实身份，大量实验的结果表明，所提出的方案可以对抗艺术的现状。
URL
https://arxiv.org/abs/1906.01792
