Multi-label pedestrian attribute recognition in surveillance is inherently a challenging task due to poor imaging quality, large pose variations, and so on. In this paper, we improve its performance from the following two aspects: (1) We propose a cascaded Split-and-Aggregate Learning (SAL) to capture both the individuality and commonality for all attributes, with one at the feature map level and the other at the feature vector level. For the former, we split the features of each attribute by using a designed attribute-specific attention module (ASAM). For the later, the split features for each attribute are learned by using constrained losses. In both modules, the split features are aggregated by using several convolutional or fully connected layers. (2) We propose a Feature Recombination (FR) that conducts a random shuffle based on the split features over a batch of samples to synthesize more training samples, which spans the potential samples’ variability. To the end, we formulate a unified framework, named CAScaded Split-and-Aggregate Learning with Feature Recombination (CAS-SAL-FR), to learn the above modules jointly and concurrently. Experiments on five popular benchmarks, including RAP, PA-100K, PETA, Market-1501 and Duke attribute datasets, show the proposed CAS-SAL-FR achieves new state-of-the-art performance.

由于成像质量差、姿态变化大等，监控中的多标签行人属性识别本质上是一项具有挑战性的任务。在本文中，我们从以下两个方面改进其性能：（1）我们提出了一种级联拆分和聚合学习（SAL）来捕获所有属性的个性和共性，一个在特征图级别，一个在其他在特征向量级别。对于前者，我们通过使用设计的特定于属性的注意力模块（ASAM）来分割每个属性的特征。对于后者，每个属性的分割特征是通过使用约束损失来学习的。在这两个模块中，分割特征是通过使用几个卷积层或全连接层来聚合的。(2) 我们提出了一种特征重组 (FR)，它基于一批样本上的分割特征进行随机洗牌，以合成更多的训练样本，从而跨越潜在样本的可变性。最后，我们制定了一个统一的框架，名为 CAScaded Split-and-Aggregate Learning with Feature Recombination (CAS-SAL-FR)，以共同和并发地学习上述模块。在五个流行的基准测试（包括 RAP、PA-100K、PETA、Market-1501 和 Duke 属性数据集）上的实验表明，所提出的 CAS-SAL-FR 实现了新的最先进性能。共同学习以上模块。在五个流行的基准测试（包括 RAP、PA-100K、PETA、Market-1501 和 Duke 属性数据集）上的实验表明，所提出的 CAS-SAL-FR 实现了新的最先进性能。共同学习以上模块。在五个流行的基准测试（包括 RAP、PA-100K、PETA、Market-1501 和 Duke 属性数据集）上的实验表明，所提出的 CAS-SAL-FR 实现了新的最先进性能。