The research of part-based methods has been proven as an effective way in person re-identification (Re-ID) task. However, in existing part-based Re-ID methods, the informative interactions and potential associations among parts are neglected, which demands further study. To fill this gap, we propose a novel Part-relation-aware Feature Fusion Network (PFFN) which achieves a part-level feature fusion and enhances the discrimination of part features by fully employing helpful information from associations among parts. More specifically, a Dual-stage Attention (DA) module, consisting of spatial and part-based channel attention, is proposed to exploit complementary benefits of two kinds of attention information, thereby facilitating model with learning more discriminative features. Furthermore, Part-relation Exploitation (PE) module is proposed to learn relation-aware part features where correlative information among parts are fully employed, thereby bringing a noticeable improvement in performance. Extensive experiments are conducted on four mainstream Re-ID datasets to verify the superiority of PFFN. Compared with baseline model, PFFN has gained rank-1 accuracy improvement of 18.2% on MSMT17-v2, 12.1% on the CUHK03-Labeled, 5.6% on DukeMTMC-reid and 1.3% on Market1501, compellingly validating its effectiveness.

中文翻译：

---

用于人员重新识别的部分关系感知特征融合网络


基于部分的方法的研究已被证明是行人重新识别（Re-ID）任务中的有效方法。然而，现有的基于部件的Re-ID方法忽略了部件之间的信息交互和潜在关联，这需要进一步研究。为了填补这一空白，我们提出了一种新颖的零件关系感知特征融合网络（PFFN），它实现了零件级特征融合，并通过充分利用零件之间关联的有用信息来增强零件特征的辨别力。更具体地说，提出了由空间和基于部分的通道注意力组成的双阶段注意力（DA）模块，以利用两种注意力信息的互补优势，从而促进模型学习更多判别性特征。此外，提出了部件关系开发（PE）模块来学习关系感知部件特征，充分利用部件之间的相关信息，从而带来性能的显着提高。在四个主流Re-ID数据集上进行了大量的实验来验证PFFN的优越性。与基线模型相比，PFFN 在 MSMT17-v2 上获得了 18.2% 的 1 级准确率提升，在 CUHK03-Labeled 上提升了 12.1%，在 DukeMTMC-reid 上提升了 5.6%，在 Market1501 上提升了 1.3%，有力地验证了其有效性。