The search functionality is under construction.
The search functionality is under construction.

Gray Augmentation Exploration with All-Modality Center-Triplet Loss for Visible-Infrared Person Re-Identification

Xiaozhou CHENG, Rui LI, Yanjing SUN, Yu ZHOU, Kaiwen DONG

  • Full Text Views

    0

  • Cite this

Summary :

Visible-Infrared Person Re-identification (VI-ReID) is a challenging pedestrian retrieval task due to the huge modality discrepancy and appearance discrepancy. To address this tough task, this letter proposes a novel gray augmentation exploration (GAE) method to increase the diversity of training data and seek the best ratio of gray augmentation for learning a more focused model. Additionally, we also propose a strong all-modality center-triplet (AMCT) loss to push the features extracted from the same pedestrian more compact but those from different persons more separate. Experiments conducted on the public dataset SYSU-MM01 demonstrate the superiority of the proposed method in the VI-ReID task.

Publication
IEICE TRANSACTIONS on Information Vol.E105-D No.7 pp.1356-1360
Publication Date
2022/07/01
Publicized
2022/04/06
Online ISSN
1745-1361
DOI
10.1587/transinf.2021EDL8101
Type of Manuscript
LETTER
Category
Image Recognition, Computer Vision

Authors

Xiaozhou CHENG
  China University of Mining and Technology,Sinostell Maanshan General Institute of Mining Research Co., Ltd.
Rui LI
  China University of Mining and Technology
Yanjing SUN
  China University of Mining and Technology
Yu ZHOU
  China University of Mining and Technology
Kaiwen DONG
  China University of Mining and Technology

Keyword