Abstract Effective person re-identification (Re-ID) is often required in real applications. While most exiting approaches either assume the detected pedestrian bounding box well-aligned or utilize limited human structural information (pose, attention, segmentation) to calibrate the misalignment. However, the value of utilizing attributes for pedestrian alignment is still under explored. Furthermore, the hierarchy of attributes in previous works has been largely ignored, appearance feature and attribute feature are often fused in a rigid way. This directly limits the discriminatory and robustness of feature representation. In this paper, we propose a Refined Attribute-aligned Network (RAN), which consists of a coarse-alignment and a fine-alignment module. First, the pre-trained part and attribute predictor are used to generate body parts and candidate attributes. Then the body parts are used for coarse alignment and the attributes are selected by an agent. The agent is optimized with policy gradient algorithm, which can maximize the accumulative reward to increase the probability of proper attribute selection. Finally, for the fine-alignment, the attribute maps and body part features are aggregated by a bilinear-pooling layer to support accurate Re-ID. Extensive experimental results based on multiple datasets including CUHK03, DukeMTMC and Market-1501 demonstrate the superiority of our method over state-of-the-art methods.

中文翻译：

---

使用属性选择学习改进的属性对齐网络以进行人员重新识别

摘要 实际应用中经常需要有效人员重新识别（Re-ID）。虽然大多数现有方法要么假设检测到的行人边界框对齐良好，要么利用有限的人体结构信息（姿势、注意力、分割）来校准错位。然而，利用属性进行行人对齐的价值仍在探索中。此外，以前的作品中的属性层次结构在很大程度上被忽略了，外观特征和属性特征往往以僵化的方式融合。这直接限制了特征表示的判别性和鲁棒性。在本文中，我们提出了一个精细的属性对齐网络（RAN），它由一个粗对齐和一个精细对齐模块组成。第一的，预训练的部位和属性预测器用于生成身体部位和候选属性。然后使用身体部位进行粗略对齐，并由代理选择属性。代理通过策略梯度算法进行优化，可以最大化累积奖励，增加正确选择属性的概率。最后，对于精细对齐，属性图和身体部位特征由双线性池层聚合以支持准确的 Re-ID。基于包括 CUHK03、DukeMTMC 和 Market-1501 在内的多个数据集的大量实验结果证明了我们的方法优于最先进的方法。这可以最大化累积奖励以增加正确选择属性的概率。最后，对于精细对齐，属性图和身体部位特征由双线性池层聚合以支持准确的 Re-ID。基于包括 CUHK03、DukeMTMC 和 Market-1501 在内的多个数据集的大量实验结果证明了我们的方法优于最先进的方法。这可以最大化累积奖励以增加正确选择属性的概率。最后，对于精细对齐，属性图和身体部位特征由双线性池层聚合以支持准确的 Re-ID。基于包括 CUHK03、DukeMTMC 和 Market-1501 在内的多个数据集的大量实验结果证明了我们的方法优于最先进的方法。