Taichi Distance For Person Re-Identification
Keywords
metric learning; person re-identification; TAICHI distance
Abstract
Metric learning is an important issue in person re-identification, and Mahalanobis-distance based metric learning methods prevail in this field. All of these approaches can be considered as equivalently projecting all samples to a new metric space and calculating the Euclidean distance there. However, the performance of distinguishing similar samples from dissimilar ones via absolute distance is limited. In this paper, we suggest using relative distance instead. We adopt a bi-target perspective. The core idea is to construct a virtual opposite target for each original target. Then, the similarity between a sample and the others is judged by using both the original and opposite targets of the sample. In this way, we propose a bi-target metric method, named TAICHI distance. Considering simplicity and efficiency, we follow the KISSME metric in this paper. Extensive evaluations on challenging datasets confirm the effectiveness of the proposed method.
Publication Date
6-16-2017
Publication Title
ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings
Number of Pages
2052-2056
Document Type
Article; Proceedings Paper
Personal Identifier
scopus
DOI Link
https://doi.org/10.1109/ICASSP.2017.7952517
Copyright Status
Unknown
Socpus ID
85023758877 (Scopus)
Source API URL
https://api.elsevier.com/content/abstract/scopus_id/85023758877
STARS Citation
Wang, Zheng; Hu, Ruimin; Yu, Yi; Liang, Chao; and Chen, Chen, "Taichi Distance For Person Re-Identification" (2017). Scopus Export 2015-2019. 7064.
https://stars.library.ucf.edu/scopus2015/7064