A Fine-grained Network for Person Re-identification
To solve the problem that the recognition efficiency of different types of attention mechanisms is too low in the person re-identification task,and the focus is too much on extracting single-granularity information,which makes it difficult to extend to real-world application scenarios,a fine-grained module based on local attention is proposed.The obtained coarse-grained feature repre-sentation is divided into multiple parts,guiding the network to extract finer-grained local clues.In addition,considering the short-comings of a single branch in extracting multi-granularity clues,a multi-branch fine-grained network is designed to further extract richer clues.Experimental results on mainstream datasets verify the effectiveness of the network proposed in this article.
person re-identificationattention mechanismfine grained clues
NETL
NSTL
万方数据
