Data augmented multi-loss hybrid learning for cross-modality person re-identification

Tao Yan; Fengsui Wang; Yue Xu; Yaping Qian

doi:10.1117/12.2662675

9 December 2022 Data augmented multi-loss hybrid learning for cross-modality person re-identification

Tao Yan, Fengsui Wang, Yue Xu, Yaping Qian

Proceedings Volume 12492, International Workshop on Automation, Control, and Communication Engineering (IWACCE 2022); 124920Y (2022) https://doi.org/10.1117/12.2662675
Event: International Workshop on Automation, Control, and Communication Engineering (IWACCE 2022), 2022, Wuhan, China

Abstract

The main challenges are the intra-class differences of person images and the cross-modal differences between visible and infrared images for cross-modal person re-identification. How to reduce the cross-modal differences becomes the key to cross-modal person re-identification. In this paper, we propose a hybrid learning strategy using Cross-Entropy loss and weighted squared triplet loss as identity (ID) loss to solve the intra-modal and inter-modal person identity classification problem, while supervising the network to extract more effective modal shared features to form specific feature descriptors. Besides, for cross-modal person image attributes, a data augmentation method of channel-swapped random erasure is used to improve the robustness of the model to color changes, simulating different degrees of image occlusion, reducing the risk of overfitting and further enriching the image diversity. Experimental results on the public dataset SYSU-MM01 demonstrate the effectiveness of the proposed method, with an average accuracy mAP of 60.08% even in the most difficult full-search single-shot mode.

Citation Download Citation

Tao Yan, Fengsui Wang, Yue Xu, and Yaping Qian "Data augmented multi-loss hybrid learning for cross-modality person re-identification", Proc. SPIE 12492, International Workshop on Automation, Control, and Communication Engineering (IWACCE 2022), 124920Y (9 December 2022); https://doi.org/10.1117/12.2662675

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available