Exploring Spatial Significance via Hybrid Pyramidal Graph Network for Vehicle Re-identification

05/29/2020

∙

by   Fei Shen, et al.

∙

2

∙

share

Existing vehicle re-identification methods commonly use spatial pooling operations to aggregate feature maps extracted via off-the-shelf backbone networks. They ignore exploring the spatial significance of feature maps, eventually degrading the vehicle re-identification performance.