Attention mechanism is a simple and effective method to enhance discriminative performance of person re-identification (Re-ID). Most of previous attention-based works have difficulty in eliminating the negative effects of meaningless information. In this paper, a universal module, named Cross-level Reinforced Attention (CLRA), is proposed to alleviate this issue. Firstly, we fuse features of different semantic levels using adaptive weights. The fused features, containing richer spatial and semantic information, can better guide the generation of subsequent attention module. Then, we combine hard and soft attention to improve the ability to extract important information in spatial and channel domains. Through the CLRA, the network can aggregate and propagate more discriminative semantic information. Finally, we integrate the CLRA with Harmonious Attention CNN (HA-CNN) and form a novel Cross-level Reinforced Attention CNN (CLRA-CNN) to optimize person Re-ID. Experiment results on several public benchmarks show that the proposed method achieves state-of-the-art performance.

注意机制是一种增强人员重新识别（Re-ID）判别性能的简单有效的方法。以前大多数基于注意力的作品都难以消除无意义的信息的负面影响。在本文中，提出了一个通用模块，称为跨级别强化注意（CLRA），以缓解此问题。首先，我们使用自适应权重融合不同语义级别的特征。包含更丰富的空间和语义信息的融合特征可以更好地指导后续关注模块的生成。然后，我们将软硬注意力集中在一起，以提高在空间和通道域中提取重要信息的能力。通过CLRA，网络可以聚合和传播更多的区分性语义信息。最后，我们将CLRA与和谐注意CNN（HA-CNN）集成在一起，形成了一种新颖的跨级别增强注意CNN（CLRA-CNN），以优化人员Re-ID。在多个公共基准上的实验结果表明，该方法达到了最先进的性能。