16 code implementations • 4 Apr 2018 • Guanshuo Wang, Yufeng Yuan, Xiong Chen, Jiwei Li, Xi Zhou
Instead of learning on semantic regions, we uniformly partition the images into several stripes, and vary the number of parts in different local branches to obtain local feature representations with multiple granularities.
Ranked #3 on Person Re-Identification on SYSU-30k (using extra training data)