Person re-identification method based on attention mechanism and CondConv

被引：0
|
作者：
Ji G. [1 ]
Wang R. [1 ]
Peng S. [1 ]
机构：
[1] Police Information Engineering and Network Secuvity College, People’s Public Security University of China, Beijing
来源：
Beijing Hangkong Hangtian Daxue Xuebao/Journal of Beijing University of Aeronautics and Astronautics | 2024年 / 50卷 / 02期
基金：
中国国家自然科学基金;
关键词：
attention mechanism; CondConv; deep learning; person re-identification; ResNet50;
D O I：
10.13700/j.bh.1001-5965.2022.0454
中图分类号：
学科分类号：
摘要：
Person Re-identification is an important part of the field of computer vision, but it is easily affected by the actual collection environment of person images, resulting in insufficient expression of person features and further leading to low model accuracy. An improved person re-identification method based on attention mechanism and CondConv is proposed to fully express pedestrian features. The attention mechanism is introduced into the feature extraction network ResNet50, and the key information in the input image space and channel is weighted, while suppressing possible noise. The CondConv is introduced into the backbone network and the convolution kernel parameters are dynamically adjusted to improve the capacity and performance of the model while maintaining efficient reasoning. Mainstream data sets such as Market1501, MSMT17 and DukeMTMC-ReID are used to evaluate the improved method. Rank-1 is increased by 1.1%, 2.4% and 1.3% respectively, and mAP is increased by 0.5%, 2.3% and 1.3%; respectively. The results show that the improved method can better express person features and improve recognition accuracy. © 2024 Beijing University of Aeronautics and Astronautics (BUAA). All rights reserved.
引用
收藏
页码：655 / 662
页数：7
相关论文
共 17 条
  • [1] MING Z Q, ZHU M K, WANG X K, Et al., Deep learning-based person re-identification methods: A survey and outlook of recent works, Image and Vision Computing, 119, (2022)
  • [2] SUN Y B, ZHANG W J, WANG R, Et al., Pedestrian re-identification method based on channel attention mechanism, Journal of Beijing University of Aeronautics and Astronautics, 48, 5, pp. 881-889, (2022)
  • [3] WIECZOREK M, RYCHALSKA B, DaBROWSKI J., On the unreasonable effectiveness of centroids in image retrieval, Neural Information Processing: 28th International Conference, pp. 212-223, (2021)
  • [4] LI H J, WU G J, ZHENG W S., Combined depth space based architecture search for person re-identification, Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 6729-6738, (2021)
  • [5] YAN C, PANG G S, BAI X, Et al., Beyond triplet loss: Person re-identification with fine-grained difference-aware pairwise loss, IEEE Transactions on Multimedia, 24, pp. 1665-1677, (2021)
  • [6] ZHOU K Y, YANG Y X, CAVALLARO A, Et al., Learning gene-ralisable omni-scale representations for person re-identification, IEEE Transactions on Pattern Analysis and Machine Intelligence, 44, 9, pp. 5056-5069, (2021)
  • [7] ZHANG X W, LYU M Q, LI H., Cross-domain person re-identification based on partial semantic feature invariance, Journal of Beijing University of Aeronautics and Astronautics, 46, 9, pp. 1682-1690, (2020)
  • [8] LIU J W, ZHA Z J, WU W, Et al., Spatial-temporal correlation and topology learning for person re-identification in videos, Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 4370-4379, (2021)
  • [9] WOO S, PARK J, LEE J Y, Et al., Cbam: Convolutional block attention module, Proceedings of the European conference on computer vision, pp. 3-19, (2018)
  • [10] YANG B, BENDER G, LE Q V, Et al., Condconv: Conditionally parameterized convolutions for efficient inference
12