期刊
KNOWLEDGE-BASED SYSTEMS
卷 220, 期 -, 页码 -出版社
ELSEVIER
DOI: 10.1016/j.knosys.2021.106941
关键词
Person re-identification; Feature fusion; Parallel training; Joint learning
This paper proposed an efficient joint SIR and CIR learning strategy called CFFS, which fuses cross-image information through parallel training to improve the performance of Re-ID. Experimental results on various datasets show that the proposed method can achieve favorable accuracy compared with state-of-the-arts.
The single-image representation (SIR) matching and cross-image representation (CIR) classification are two significant solutions in the person re-identification (Re-ID) task. Combining the two categories of methods has been regarded as an effective solution to improve discriminative performances in Re-ID. Previous combination methods mainly focus on fusing the SIR learning and CIR learning losses, representing the cross-image features with limitations and not available to different network structures for feature learning. This paper proposed an efficient joint SIR and CIR learning strategy - cross image features fusion strategy (CFFS), which fuses cross-image information through parallel training. Precisely, CFFS consists of one shared sub-network and two branches, one branch for learning single image feature and the other for fusing cross-image features. CFFS requires pairwise data parallelism training for each identity to learn the CIR, applied to metric learning. Therefore, the cross-image features would be fused better, and the performance of Re-ID would be improved. Experiments on Market-1501, DukeMTMC-reid, and CUHK03 datasets show that the proposed method can achieve favorable accuracy while compared with state-of-the-arts. (c) 2021 Elsevier B.V. All rights reserved.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据