Yao Hantao, Zhang Shiliang, Hong Richang, Zhang Yongdong, Xu Changsheng, Tian Qi
IEEE Trans Image Process. 2019 Jan 10. doi: 10.1109/TIP.2019.2891888.
Learning discriminative representations for unseen person images is critical for person Re-Identification (ReID). Most of current approaches learn deep representations in classification tasks, which essentially minimizes the empirical classification risk on the training set. As shown in our experiments, such representations easily get over-fitted on a discriminative human body part on the training set. To gain the discriminative power on unseen person images, we propose a deep representation learning procedure named Part Loss Network (PL-Net), to minimize both the empirical classification risk on training person images and the representation learning risk on unseen person images. The representation learning risk is evaluated by the proposed part loss, which automatically detects human body parts, and computes the person classification loss on each part separately. Compared with traditional global classification loss, simultaneously considering part loss enforces the deep network to learn representations for different body parts and gain the discriminative power on unseen persons. Experimental results on three person ReID datasets, i.e., Market1501, CUHK03, VIPeR, show that our representation outperforms existing deep representations.
学习针对未见人物图像的判别表示对于人物重识别（ReID）至关重要。当前大多数方法在分类任务中学习深度表示，这本质上是将训练集上的经验分类风险最小化。如我们的实验所示，这样的表示很容易在训练集上的一个有判别力的人体部位上过度拟合。为了在未见人物图像上获得判别力，我们提出了一种名为部分损失网络（PL-Net）的深度表示学习过程，以最小化训练人物图像上的经验分类风险和未见人物图像上的表示学习风险。表示学习风险通过所提出的部分损失来评估，该部分损失会自动检测人体部位，并分别计算每个部位上的人物分类损失。与传统的全局分类损失相比，同时考虑部分损失会促使深度网络学习不同身体部位的表示，并在未见人物上获得判别力。在三个人物ReID数据集，即Market1501、CUHK03、VIPeR上的实验结果表明，我们的表示优于现有的深度表示。
