Global average pooling (GAP) allows to localize discriminative information
for recognition [40]. While GAP helps the convolution neural network to attend
to the most discriminative features of an object, it may suffer if that
information is missing e.g. due to camera viewpoint changes. To circumvent this
issue, we argue that it is advantageous to attend to the global configuration
of the object by modeling spatial relations among high-level features. We
propose a novel architecture for Person Re-Identification, based on a novel
parameter-free spatial attention layer introducing spatial relations among the
feature map activations back to the model. Our spatial attention layer
consistently improves the performance over the model without it. Results on
four benchmarks demonstrate a superiority of our model over the
state-of-the-art achieving rank-1 accuracy of 94.7% on Market-1501, 89.0% on
DukeMTMC-ReID, 74.9% on CUHK03-labeled and 69.7% on CUHK03-detected.

本研究提出了一种新的参数 - free 的空间注意力层来建模高层特征之间的空间关系，该层相比于没有该层的模型有显著的性能改进，并在四个基准测试中实现了最先进的结果，其中 Market-1501 的 rank-1 准确度为 94.7％，DukeMTMC-ReID 的 rank-1 准确度为 89.0％，CUHK03-labeled 和 CUHK03-detected 的 rank-1 准确度分别为 74.9％和 69.7％。