skip to main content
10.1145/3590003.3590089acmotherconferencesArticle/Chapter ViewAbstractPublication PagescacmlConference Proceedingsconference-collections
research-article

KRE: A Key-retained Random Erasing Method for Occluded Person Re-identification

Published: 29 May 2023 Publication History

Abstract

Occluded person re-identification (ReID) is a challenging task in the field of computer vision, facing the problem that the target pedestrians in probe images are obscured by various occlusions. Random Erasing in data augmentation techniques is one of the effective methods used to deal with the occlusion problem, but it may introduce noise into the training process, which affects the training of the model. In order to solve this problem, we propose an novel data augmentation method named Key-retained Random Erasing (KRE) which preserves the critical parts in images for occluded person ReID. Based on the regular Random Erasing, we utilize the naturally generated attention map in Vision Transformers and introduce an adaptive threshold selection method to detect the key areas of the image to be augmented. The complexity of the training samples can be improved without losing the key information of the images by reserving the key areas in Random Erasing process, which can finally alleviate the occluded person ReID problem. Validating the proposed method on occluded, partial and holistic ReID datasets, extensive experimental results demonstrate that our method performs favorably against state-of-the-art methods on ViT-based models.

References

[1]
Jie-Neng Chen, Shuyang Sun, Ju He, Philip HS Torr, Alan Yuille, and Song Bai. 2022. Transmix: Attend to mix for vision transformers. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 12135–12144.
[2]
Alexey Dosovitskiy, Lucas Beyer, Alexander Kolesnikov, Dirk Weissenborn, Xiaohua Zhai, Thomas Unterthiner, Mostafa Dehghani, Matthias Minderer, Georg Heigold, Sylvain Gelly, 2020. An image is worth 16x16 words: Transformers for image recognition at scale. arXiv preprint arXiv:2010.11929 (2020).
[3]
Xing Fan, Hao Luo, Xuan Zhang, Lingxiao He, Chi Zhang, and Wei Jiang. 2019. Scpnet: Spatial-channel parallelism network for joint holistic and partial person re-identification. In Computer Vision–ACCV 2018: 14th Asian Conference on Computer Vision, Perth, Australia, December 2–6, 2018, Revised Selected Papers, Part II 14. Springer, 19–34.
[4]
Shang Gao, Jingya Wang, Huchuan Lu, and Zimo Liu. 2020. Pose-guided visible part matching for occluded person ReID. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition. 11744–11752.
[5]
Yixiao Ge, Zhuowan Li, Haiyu Zhao, Guojun Yin, Shuai Yi, Xiaogang Wang, 2018. Fd-gan: Pose-guided feature distilling gan for robust person re-identification. Advances in neural information processing systems 31 (2018).
[6]
Chengyue Gong, Dilin Wang, Meng Li, Vikas Chandra, and Qiang Liu. 2021. Keepaugment: A simple information-preserving data augmentation approach. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition. 1055–1064.
[7]
Raphael Gontijo-Lopes, Sylvia J Smullin, Ekin D Cubuk, and Ethan Dyer. 2020. Affinity and diversity: Quantifying mechanisms of data augmentation. arXiv preprint arXiv:2002.08973 (2020).
[8]
Douglas Gray, Shane Brennan, and Hai Tao. 2007. Evaluating appearance models for recognition, reacquisition, and tracking. In Proc. IEEE international workshop on performance evaluation for tracking and surveillance (PETS), Vol. 3. 1–7.
[9]
Jianyuan Guo, Yuhui Yuan, Lang Huang, Chao Zhang, Jin-Ge Yao, and Kai Han. 2019. Beyond human parts: Dual part-aligned representations for person re-identification. In Proceedings of the IEEE/CVF International Conference on Computer Vision. 3642–3651.
[10]
Lingxiao He, Jian Liang, Haiqing Li, and Zhenan Sun. 2018. Deep spatial feature reconstruction for partial person re-identification: Alignment-free approach. In Proceedings of the IEEE conference on computer vision and pattern recognition. 7073–7082.
[11]
Lingxiao He, Zhenan Sun, Yuhao Zhu, and Yunbo Wang. 2018. Recognizing partial biometric patterns. arXiv preprint arXiv:1810.07399 (2018).
[12]
Lingxiao He, Yinggang Wang, Wu Liu, He Zhao, Zhenan Sun, and Jiashi Feng. 2019. Foreground-aware pyramid reconstruction for alignment-free occluded person re-identification. In Proceedings of the IEEE/CVF international conference on computer vision. 8450–8459.
[13]
Shuting He, Hao Luo, Pichao Wang, Fan Wang, Hao Li, and Wei Jiang. 2021. Transreid: Transformer-based object re-identification. In Proceedings of the IEEE/CVF international conference on computer vision. 15013–15022.
[14]
Alexander Hermans, Lucas Beyer, and Bastian Leibe. 2017. In defense of the triplet loss for person re-identification. arXiv preprint arXiv:1703.07737 (2017).
[15]
Houjing Huang, Dangwei Li, Zhang Zhang, Xiaotang Chen, and Kaiqi Huang. 2018. Adversarially occluded samples for person re-identification. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 5098–5107.
[16]
Mengxi Jia, Xinhua Cheng, Yunpeng Zhai, Shijian Lu, Siwei Ma, Yonghong Tian, and Jian Zhang. 2021. Matching on sets: Conquer occluded person re-identification without alignment. In Proceedings of the AAAI Conference on Artificial Intelligence, Vol. 35. 1673–1681.
[17]
Mahdi M Kalayeh, Emrah Basaran, Muhittin Gökmen, Mustafa E Kamasak, and Mubarak Shah. 2018. Human semantic parsing for person re-identification. In Proceedings of the IEEE conference on computer vision and pattern recognition. 1062–1071.
[18]
Wei Li, Xiatian Zhu, and Shaogang Gong. 2018. Harmonious attention network for person re-identification. In Proceedings of the IEEE conference on computer vision and pattern recognition. 2285–2294.
[19]
Yulin Li, Jianfeng He, Tianzhu Zhang, Xiang Liu, Yongdong Zhang, and Feng Wu. 2021. Diverse part discovery: Occluded person re-identification with part-aware transformer. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 2898–2907.
[20]
Shengcai Liao, Yang Hu, Xiangyu Zhu, and Stan Z Li. 2015. Person re-identification by local maximal occurrence representation and metric learning. In Proceedings of the IEEE conference on computer vision and pattern recognition. 2197–2206.
[21]
Shengcai Liao, Anil K Jain, and Stan Z Li. 2012. Partial face recognition: Alignment-free approach. IEEE Transactions on pattern analysis and machine intelligence 35, 5 (2012), 1193–1205.
[22]
Hao Luo, Youzhi Gu, Xingyu Liao, Shenqi Lai, and Wei Jiang. 2019. Bag of tricks and a strong baseline for deep person re-identification. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition workshops. 0–0.
[23]
Jiaxu Miao, Yu Wu, Ping Liu, Yuhang Ding, and Yi Yang. 2019. Pose-guided feature alignment for occluded person re-identification. In Proceedings of the IEEE/CVF international conference on computer vision. 542–551.
[24]
Ergys Ristani, Francesco Solera, Roger Zou, Rita Cucchiara, and Carlo Tomasi. 2016. Performance measures and a data set for multi-target, multi-camera tracking. In Computer Vision–ECCV 2016 Workshops: Amsterdam, The Netherlands, October 8-10 and 15-16, 2016, Proceedings, Part II. Springer, 17–35.
[25]
Yumin Suh, Jingdong Wang, Siyu Tang, Tao Mei, and Kyoung Mu Lee. 2018. Part-aligned bilinear representations for person re-identification. In Proceedings of the European conference on computer vision (ECCV). 402–419.
[26]
Yifan Sun, Qin Xu, Yali Li, Chi Zhang, Yikang Li, Shengjin Wang, and Jian Sun. 2019. Perceive where to focus: Learning visibility-aware part-level features for partial person re-identification. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition. 393–402.
[27]
Yifan Sun, Liang Zheng, Yi Yang, Qi Tian, and Shengjin Wang. 2018. Beyond part models: Person retrieval with refined part pooling (and a strong convolutional baseline). In Proceedings of the European conference on computer vision (ECCV). 480–496.
[28]
Hugo Touvron, Matthieu Cord, Matthijs Douze, Francisco Massa, Alexandre Sablayrolles, and Hervé Jégou. 2021. Training data-efficient image transformers & distillation through attention. In International conference on machine learning. PMLR, 10347–10357.
[29]
Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N Gomez, Łukasz Kaiser, and Illia Polosukhin. 2017. Attention is all you need. Advances in neural information processing systems 30 (2017).
[30]
Guan’an Wang, Shuo Yang, Huanyu Liu, Zhicheng Wang, Yang Yang, Shuliang Wang, Gang Yu, Erjin Zhou, and Jian Sun. 2020. High-order information matters: Learning relation and topology for occluded person re-identification. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition. 6449–6458.
[31]
Guanshuo Wang, Yufeng Yuan, Xiong Chen, Jiwei Li, and Xi Zhou. 2018. Learning discriminative features with multiple granularities for person re-identification. In Proceedings of the 26th ACM international conference on Multimedia. 274–282.
[32]
HongXia Wang, Xiang Chen, and Chun Liu. 2021. Pose-guided part matching network via shrinking and reweighting for occluded person re-identification. Image and Vision Computing 111 (2021), 104186.
[33]
Longhui Wei, An Xiao, Lingxi Xie, Xiaopeng Zhang, Xin Chen, and Qi Tian. 2020. Circumventing outliers of autoaugment with knowledge distillation. In Computer Vision–ECCV 2020: 16th European Conference, Glasgow, UK, August 23–28, 2020, Proceedings, Part III. Springer, 608–625.
[34]
Mang Ye, Jianbing Shen, Gaojie Lin, Tao Xiang, Ling Shao, and Steven CH Hoi. 2021. Deep learning for person re-identification: A survey and outlook. IEEE transactions on pattern analysis and machine intelligence 44, 6 (2021), 2872–2893.
[35]
Liming Zhao, Xi Li, Yueting Zhuang, and Jingdong Wang. 2017. Deeply-learned part-aligned representations for person re-identification. In Proceedings of the IEEE international conference on computer vision. 3219–3228.
[36]
Liang Zheng, Liyue Shen, Lu Tian, Shengjin Wang, Jingdong Wang, and Qi Tian. 2015. Scalable person re-identification: A benchmark. In Proceedings of the IEEE international conference on computer vision. 1116–1124.
[37]
Liang Zheng, Yi Yang, and Alexander G Hauptmann. 2016. Person re-identification: Past, present and future. arXiv preprint arXiv:1610.02984 (2016).
[38]
Wei-Shi Zheng, Xiang Li, Tao Xiang, Shengcai Liao, Jianhuang Lai, and Shaogang Gong. 2015. Partial person re-identification. In Proceedings of the IEEE international conference on computer vision. 4678–4686.
[39]
Zhedong Zheng, Liang Zheng, and Yi Yang. 2018. Pedestrian alignment network for large-scale person re-identification. IEEE Transactions on Circuits and Systems for Video Technology 29, 10 (2018), 3037–3045.
[40]
Zhun Zhong, Liang Zheng, Guoliang Kang, Shaozi Li, and Yi Yang. 2020. Random erasing data augmentation. In Proceedings of the AAAI conference on artificial intelligence, Vol. 34. 13001–13008.
[41]
Jiaxuan Zhuo, Zeyu Chen, Jianhuang Lai, and Guangcong Wang. 2018. Occluded person re-identification. In 2018 IEEE International Conference on Multimedia and Expo (ICME). IEEE, 1–6.

Cited By

View all
  • (2025)Label-guided diversified learning model for occluded person re-identificationExpert Systems with Applications10.1016/j.eswa.2025.126745272(126745)Online publication date: May-2025

Index Terms

  1. KRE: A Key-retained Random Erasing Method for Occluded Person Re-identification

    Recommendations

    Comments

    Information & Contributors

    Information

    Published In

    cover image ACM Other conferences
    CACML '23: Proceedings of the 2023 2nd Asia Conference on Algorithms, Computing and Machine Learning
    March 2023
    598 pages
    ISBN:9781450399449
    DOI:10.1145/3590003
    Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for components of this work owned by others than the author(s) must be honored. Abstracting with credit is permitted. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specific permission and/or a fee. Request permissions from [email protected].

    Publisher

    Association for Computing Machinery

    New York, NY, United States

    Publication History

    Published: 29 May 2023

    Permissions

    Request permissions for this article.

    Check for updates

    Author Tags

    1. data augmentation
    2. occluded person re-identification
    3. self attention
    4. vision transformer

    Qualifiers

    • Research-article
    • Research
    • Refereed limited

    Conference

    CACML 2023

    Acceptance Rates

    CACML '23 Paper Acceptance Rate 93 of 241 submissions, 39%;
    Overall Acceptance Rate 93 of 241 submissions, 39%

    Contributors

    Other Metrics

    Bibliometrics & Citations

    Bibliometrics

    Article Metrics

    • Downloads (Last 12 months)9
    • Downloads (Last 6 weeks)2
    Reflects downloads up to 16 Feb 2025

    Other Metrics

    Citations

    Cited By

    View all
    • (2025)Label-guided diversified learning model for occluded person re-identificationExpert Systems with Applications10.1016/j.eswa.2025.126745272(126745)Online publication date: May-2025

    View Options

    Login options

    View options

    PDF

    View or Download as a PDF file.

    PDF

    eReader

    View online with eReader.

    eReader

    HTML Format

    View this article in HTML Format.

    HTML Format

    Figures

    Tables

    Media

    Share

    Share

    Share this Publication link

    Share on social media