Staged encoder training for cross-camera person re-identification

As a cross-camera retrieval problem, person re-identification (ReID) suffers from image style variations caused by camera parameters, lighting and other reasons, which will seriously affect the model recognition accuracy. To address this problem, this paper proposes a two-stage contrastive learning...

Full description

Saved in:
Bibliographic Details
Published in:Signal, image and video processing Vol. 18; no. 3; pp. 2323 - 2331
Main Authors: Xu, Zhi, Yang, Jiawei, Liu, Yuxuan, Zhao, Longyang, Liu, Jiajia
Format: Journal Article
Language:English
Published: London Springer London 01.04.2024
Springer Nature B.V
Subjects:
Accuracy
Cameras
Classification
Coders
Computer Imaging
Computer Science
Computer vision
Datasets
Dictionaries
Image coding
Image Processing and Computer Vision
Methods
Multimedia Information Systems
Original Paper
Parameter identification
Pattern recognition
Pattern Recognition and Graphics
Signal,Image and Speech Processing
Vision
Unsupervised
Person re-identification
Camera variation
Contrastive learning
ISSN:1863-1703, 1863-1711
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:As a cross-camera retrieval problem, person re-identification (ReID) suffers from image style variations caused by camera parameters, lighting and other reasons, which will seriously affect the model recognition accuracy. To address this problem, this paper proposes a two-stage contrastive learning method to gradually reduce the impact of camera variations. In the first stage, we train an encoder for each camera using only images from the respective camera. This ensures that each encoder has better recognition performance on images from its respective camera while being unaffected by camera variations. In the second stage, we encode the same image using all trained encoders to generate a new combination code that is robust against camera variations. We also use Cross-Camera Encouragement (Lin et al., in: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, 2020) distance that complements the advantages of combined encoding to further mitigate the impact of camera variations. Our method achieves high accuracy on several commonly used person ReID datasets, e.g., on the Market-1501, achieves 90.8% rank-1 accuracy and 85.2% mAP, outperforming the recent unsupervised works by 12+% in terms of mAP. Code is available at https://github.com/yjwyuanwu/SET.
Bibliography:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:1863-1703
1863-1711
DOI:10.1007/s11760-023-02909-0