Recently, the attention mechanism and part-based architectures have greatly boosted the research of person re-identification (Re-ID). However, most attention-based works extract first-order information and lack diversity. Meanwhile, the classic part-based works are not able to make use of cross-part information because of the unified partitions. These two kinds of methods ignore visual relationships in the global scope. Accordingly, we propose multi-subspace non-local attention (MSNA) and reinforced loss (R-Loss) to alleviate the issues above. MSNA is an improved attention module. It can be integrated into existing networks to utilize rich low-level information and extract the global relationships from different subspaces. R-Loss module is motivated to reinforce the capability of extracting fine-grained features by making full use of intra-part and cross-part information. We combine them and provide a global-locally reinforced feature extraction strategy. In addition, we design a feature fusion module to combine features from different branches. Equipped with the modules above, our model can extract important local and fine-grained features by identifying diverse visual relationships in the global scope. The models with our proposed modules achieve significant improvements over the baselines on four public datasets and establish new state-of-the-art results.

中文翻译：

---

用于局部重新识别的全局局部增强特征提取

最近，注意力机制和基于部分的体系结构极大地促进了人员重新识别（Re-ID）的研究。但是，大多数基于注意力的作品都提取了一阶信息，并且缺乏多样性。同时，由于基于统一的分区，基于零件的经典作品无法利用跨零件的信息。这两种方法会忽略全局范围内的视觉关系。因此，我们提出了多子空间非本地关注（MSNA）和增强损失（R-Loss）来缓解上述问题。MSNA是改进的注意力模块。可以将其集成到现有网络中，以利用丰富的低层信息并从不同的子空间中提取全局关系。R-Loss模块旨在通过充分利用零件内和零件间的信息来增强提取细粒度特征的能力。我们将它们结合起来，并提供了一种在全球局部增强的特征提取策略。此外，我们设计了一个特征融合模块，以合并来自不同分支的特征。配备了上述模块，我们的模型可以通过识别全局范围内的各种视觉关系来提取重要的局部和细粒度特征。带有我们提出的模块的模型在四个公共数据集的基线上取得了显着改善，并建立了最新的结果。配备了上述模块，我们的模型可以通过识别全局范围内的各种视觉关系来提取重要的局部和细粒度特征。带有我们提出的模块的模型在四个公共数据集的基线上取得了显着改善，并建立了最新的结果。配备了上述模块，我们的模型可以通过识别全局范围内的各种视觉关系来提取重要的局部和细粒度特征。带有我们提出的模块的模型在四个公共数据集的基线上取得了显着改善，并建立了最新的结果。