期刊
IEEE SIGNAL PROCESSING LETTERS
卷 28, 期 -, 页码 653-657出版社
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/LSP.2021.3065903
关键词
Training; Three-dimensional displays; Measurement; Testing; Organizations; Neck; Focusing; Dual-granularity triplet loss; fine to coarse granularity; visible-thermal person re-identification
资金
- National Natural Science Foundation of China [62001063, U20A20157, 61971072, 61971075]
- China Postdoctoral Science Foundation [2020M673135]
A new dual-granularity triplet loss method for visible-thermal person re-identification is proposed, which organizes sample-based and center-based losses in a hierarchical manner, significantly improving performance using only global features, serving as a strong baseline for future research.
This letter presents a conceptually simple and effective dual-granularity triplet loss for visible-thermal person re-identification (VT-ReID). Generally, ReID models are always trained with the sample-based triplet loss and identification loss from the fine granularity level. Further, center-based loss could be introduced to encourage the intra-class compactness and inter-class discrimination from the coarse granularity level. Our proposed dual-granularity triplet loss well organizes the sample-based triplet loss and center-based triplet loss in a hierarchical fine to coarse granularity manner, just with some simple configurations of typical operations, such as pooling and batch normalization. Experiments on RegDB and SYSU-MM01 datasets show that with only the global features our dual-granularity triplet loss can improve the VT-ReID performance by a significant margin. It can be a strong VT-ReID baseline to boost future research with high quality.
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