Abstract This paper addresses the person search task, which is a computer vision technology that finds the location of a pedestrian and retrieves it in a video taken by a single camera or multiple cameras. This task is much more challenging than the conventional settings for person re-identification or pedestrian detection since the search is susceptible to factors such as different resolutions, similar pedestrians, lighting, viewing angles and occlusion. Moreover, the person search task is a typical big data-small sample problem because each pedestrian only has a few images. It is difficult for the model to learn the discriminant features of pedestrians with a small quantity of pedestrian data. This paper proposes a framework for person search that uses the original training set without collecting extra data by implementing a generative adversarial network (GAN) to generate unlabeled samples. We propose a deep complementary classifier for pedestrian detection to leverage complementary object regions for pedestrian/non-pedestrian classification. In the re-identification section, we propose a center-constrained triplet loss that avoids the complicated triplet selection of the triplet loss and simultaneously pushes away all the distances of rather similar negative centers and the positive center. Experiments show that the GAN-generated data can effectively help to improve the discriminating ability of the CNN model. On the two large-scale datasets, CUHK-SYSU and PRW, we achieve a performance improvement over the baseline CNN. We additionally apply the proposed center-constrained triplet loss and complementary classifiers in the training model, and we achieve mAP improvements over the original method of +1.9% on CUHK-SYSU and +2.5% on PRW.

中文翻译：

---

通过具有中心约束三重损失的深度互补分类器进行基于 GAN 的人员搜索

摘要 本文解决了人员搜索任务，这是一种计算机视觉技术，可以找到行人的位置并在由单个或多个摄像头拍摄的视频中检索它。这项任务比传统的人员重新识别或行人检测设置更具挑战性，因为搜索容易受到不同分辨率、相似行人、照明、视角和遮挡等因素的影响。此外，人物搜索任务是一个典型的大数据小样本问题，因为每个行人只有几张图像。模型很难用少量的行人数据来学习行人的判别特征。本文提出了一种人员搜索框架，该框架通过实现生成对抗网络 (GAN) 来生成未标记的样本，从而使用原始训练集而不收集额外数据。我们提出了一种用于行人检测的深度互补分类器，以利用互补对象区域进行行人/非行人分类。在重新识别部分，我们提出了一种中心约束的三元组损失，它避免了三元组损失的复杂三元组选择，同时推开相当相似的负中心和正中心的所有距离。实验表明，GAN 生成的数据可以有效地帮助提高 CNN 模型的判别能力。在两个大型数据集 CUHK-SYSU 和 PRW 上，我们实现了对基线 CNN 的性能提升。