Person Re-Identification Using Maintain Translation Invariance and F-triplet Loss
Pages 293 - 298
Abstract
Pedestrian re-identification involves matching pedestrian images or videos across different cameras. The goal is to retrieve the same pedestrian given a query image from a gallery of images captured by various surveillance devices. As a cross-view task, the spatial position of individuals in images often changes for pedestrian re-identification. Maintaining spatial position invariance is crucial for pedestrian re-identification. Besides, focusing on pedestrians and minimizing the influence of background noise remain unresolved issues in pedestrian re-identification. Deep learning models are often used, however, there is a low-frequency preference phenomenon. Deep learning models tend to learn low-frequency features during the training process, neglecting high-frequency features. Hence, simultaneously learning high and low-frequency features is particularly important in pedestrian re-identification tasks. This paper proposes the design of a novel module to maintain translational invariance in the network architecture. The original loss function is modified using the Fourier transform to better learn high-frequency and low-frequency features. By concurrently learning high and low-frequency features, the specific region of the pedestrian in the image can be accurately determined, thereby improving the accuracy of pedestrian re-identification. In this way, we can improve robustness of pedestrian re-identification in complex cross-view scenarios. Superior experimental performance is achieved on two large-scale Market-1501 and DukeMTMC datasets.
References
[1]
Jin Chen, Xijun Wang, Zichao Guo, Xiangyu Zhang, and Jian Sun. 2021. Dynamic region-aware convolution. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition. 8064–8073.
[2]
Xuesong Chen, Canmiao Fu, Yong Zhao, Feng Zheng, Jingkuan Song, Rongrong Ji, and Yi Yang. 2020. Salience-guided cascaded suppression network for person re-identification. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition. 3300–3310.
[3]
De Cheng, Yihong Gong, Sanping Zhou, Jinjun Wang, and Nanning Zheng. 2016. Person re-identification by multi-channel parts-based cnn with improved triplet loss function. In Proceedings of the iEEE conference on computer vision and pattern recognition. 1335–1344.
[4]
Lionel Gueguen, Alex Sergeev, Ben Kadlec, Rosanne Liu, and Jason Yosinski. 2018. Faster neural networks straight from jpeg. Advances in Neural Information Processing Systems 31 (2018).
[5]
Xin Hu, Zhenyu Wu, Hao-Yu Miao, Siqi Fan, Taiyu Long, Zhenyu Hu, Pengcheng Pi, Yi Wu, Zhou Ren, Zhangyang Wang, 2022. E⌃2TAD: An Energy-Efficient Tracking-based Action Detector. arXiv preprint arXiv:2204.04416 (2022).
[6]
Liming Jiang, Bo Dai, Wayne Wu, and Chen Change Loy. 2021. Focal frequency loss for image reconstruction and synthesis. In Proceedings of the IEEE/CVF International Conference on Computer Vision. 13919–13929.
[7]
Xin Jin, Cuiling Lan, Wenjun Zeng, Guoqiang Wei, and Zhibo Chen. 2020. Semantics-aligned representation learning for person re-identification. In Proceedings of the AAAI Conference on Artificial Intelligence, Vol. 34. 11173–11180.
[8]
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.
[9]
Dangwei Li, Xiaotang Chen, Zhang Zhang, and Kaiqi Huang. 2017. Learning deep context-aware features over body and latent parts for person re-identification. In Proceedings of the IEEE conference on computer vision and pattern recognition. 384–393.
[10]
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.
[11]
Jinxian Liu, Bingbing Ni, Yichao Yan, Peng Zhou, Shuo Cheng, and Jianguo Hu. 2018. Pose transferrable person re-identification. In Proceedings of the IEEE conference on computer vision and pattern recognition. 4099–4108.
[12]
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.
[13]
Ben Mildenhall, Pratul P Srinivasan, Matthew Tancik, Jonathan T Barron, Ravi Ramamoorthi, and Ren Ng. 2021. Nerf: Representing scenes as neural radiance fields for view synthesis. Commun. ACM 65, 1 (2021), 99–106.
[14]
Allan Pinkus. 1999. Approximation theory of the MLP model in neural networks. Acta numerica 8 (1999), 143–195.
[15]
Xuelin Qian, Yanwei Fu, Tao Xiang, Wenxuan Wang, Jie Qiu, Yang Wu, Yu-Gang Jiang, and Xiangyang Xue. 2018. Pose-normalized image generation for person re-identification. In Proceedings of the European conference on computer vision (ECCV). 650–667.
[16]
Nasim Rahaman, Aristide Baratin, Devansh Arpit, Felix Draxler, Min Lin, Fred Hamprecht, Yoshua Bengio, and Aaron Courville. 2019. On the spectral bias of neural networks. In International Conference on Machine Learning. PMLR, 5301–5310.
[17]
Nasim Rahaman, Muhammad Waleed Gondal, Shruti Joshi, Peter Gehler, Yoshua Bengio, Francesco Locatello, and Bernhard Schölkopf. 2021. Dynamic inference with neural interpreters. Advances in Neural Information Processing Systems 34 (2021), 10985–10998.
[18]
Ali Rahimi and Benjamin Recht. 2007. Random features for large-scale kernel machines. Advances in neural information processing systems 20 (2007).
[19]
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 European conference on computer vision. Springer, 17–35.
[20]
Yantao Shen, Tong Xiao, Hongsheng Li, Shuai Yi, and Xiaogang Wang. 2018. End-to-end deep kronecker-product matching for person re-identification. In Proceedings of the IEEE conference on computer vision and pattern recognition. 6886–6895.
[21]
Jifei Song, Yongxin Yang, Yi-Zhe Song, Tao Xiang, and Timothy M Hospedales. 2019. Generalizable person re-identification by domain-invariant mapping network. In Proceedings of the IEEE/CVF conference on Computer Vision and Pattern Recognition. 719–728.
[22]
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.
[23]
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.
[24]
Matthew Tancik, Pratul Srinivasan, Ben Mildenhall, Sara Fridovich-Keil, Nithin Raghavan, Utkarsh Singhal, Ravi Ramamoorthi, Jonathan Barron, and Ren Ng. 2020. Fourier features let networks learn high frequency functions in low dimensional domains. Advances in Neural Information Processing Systems 33 (2020), 7537–7547.
[25]
Rahul Rama Varior, Bing Shuai, Jiwen Lu, Dong Xu, and Gang Wang. 2016. A siamese long short-term memory architecture for human re-identification. In Computer Vision–ECCV 2016: 14th European Conference, Amsterdam, The Netherlands, October 11–14, 2016, Proceedings, Part VII 14. Springer, 135–153.
[26]
Fangbin Wan, Yang Wu, Xuelin Qian, Yixiong Chen, and Yanwei Fu. 2020. When person re-identification meets changing clothes. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops. 830–831.
[27]
Cheng Wang, Qian Zhang, Chang Huang, Wenyu Liu, and Xinggang Wang. 2018. Mancs: A multi-task attentional network with curriculum sampling for person re-identification. In Proceedings of the European conference on computer vision (ECCV). 365–381.
[28]
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.
[29]
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.
[30]
Xiaogang Wang, Gianfranco Doretto, Thomas Sebastian, Jens Rittscher, and Peter Tu. 2007. Shape and appearance context modeling. In 2007 ieee 11th international conference on computer vision. Ieee, 1–8.
[31]
Yicheng Wang, Zhenzhong Chen, Feng Wu, and Gang Wang. 2018. Person re-identification with cascaded pairwise convolutions. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 1470–1478.
[32]
Kai Xu, Minghai Qin, Fei Sun, Yuhao Wang, Yen-Kuang Chen, and Fengbo Ren. 2020. Learning in the frequency domain. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition. 1740–1749.
[33]
Zhi-Qin John Xu, Yaoyu Zhang, Tao Luo, Yanyang Xiao, and Zheng Ma. 2019. Frequency principle: Fourier analysis sheds light on deep neural networks. arXiv preprint arXiv:1901.06523 (2019).
[34]
Jia Xue, Zibo Meng, Karthik Katipally, Haibo Wang, and Kees Van Zon. 2018. Clothing change aware person identification. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops. 2112–2120.
[35]
Fan Yang, Ke Yan, Shijian Lu, Huizhu Jia, Xiaodong Xie, and Wen Gao. 2019. Attention driven person re-identification. Pattern Recognition 86 (2019), 143–155.
[36]
Qize Yang, Ancong Wu, and Wei-Shi Zheng. 2019. Person re-identification by contour sketch under moderate clothing change. IEEE transactions on pattern analysis and machine intelligence 43, 6 (2019), 2029–2046.
[37]
Jaejun Yoo, Youngjung Uh, Sanghyuk Chun, Byeongkyu Kang, and Jung-Woo Ha. 2019. Photorealistic style transfer via wavelet transforms. In Proceedings of the IEEE/CVF International Conference on Computer Vision. 9036–9045.
[38]
Zhizheng Zhang, Cuiling Lan, Wenjun Zeng, Xin Jin, and Zhibo Chen. 2020. Relation-aware global attention for person re-identification. In Proceedings of the ieee/cvf conference on computer vision and pattern recognition. 3186–3195.
[39]
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.
[40]
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.
[41]
Zhedong Zheng, Liang Zheng, and Yi Yang. 2017. Unlabeled samples generated by gan improve the person re-identification baseline in vitro. In Proceedings of the IEEE international conference on computer vision. 3754–3762.
[42]
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.
[43]
Kaiyang Zhou, Yongxin Yang, Andrea Cavallaro, and Tao Xiang. 2019. Omni-scale feature learning for person re-identification. In Proceedings of the IEEE/CVF international conference on computer vision. 3702–3712.
[44]
Kuan Zhu, Haiyun Guo, Zhiwei Liu, Ming Tang, and Jinqiao Wang. 2020. Identity-guided human semantic parsing for person re-identification. In Computer Vision–ECCV 2020: 16th European Conference, Glasgow, UK, August 23–28, 2020, Proceedings, Part III 16. Springer, 346–363.
[45]
Zijie Zhuang, Longhui Wei, Lingxi Xie, Tianyu Zhang, Hengheng Zhang, Haozhe Wu, Haizhou Ai, and Qi Tian. 2020. Rethinking the distribution gap of person re-identification with camera-based batch normalization. In Computer Vision–ECCV 2020: 16th European Conference, Glasgow, UK, August 23–28, 2020, Proceedings, Part XII 16. Springer, 140–157.
Index Terms
- Person Re-Identification Using Maintain Translation Invariance and F-triplet Loss
Index terms have been assigned to the content through auto-classification.
Recommendations
A loss combination based deep model for person re-identification
The Convolutional Neural Network (CNN) has significantly improved the state-of-the-art in person re-identification (re-ID). In the existing available identification CNN model, the softmax loss function is employed as the supervision signal to train the ...
Deep feature embedding learning for person re-identification based on lifted structured loss
Person re-identification (re-id) aims at matching the same individual in videos captured by multiple cameras, and much progress has been made in recent years due to large scale pedestrian data sets and deep learning-based techniques. In this paper, we ...
Person re-identification by the asymmetric triplet and identification loss function
Person re-identification(re-id) aims to match the same individuals across different non-overlapping camera views. In this paper, we analyze the effectiveness of two widely used triplet loss and softmax loss on person re-id task. We conclude that the ...
Comments
Please enable JavaScript to view thecomments powered by Disqus.Information & Contributors
Information
Published In
October 2023
589 pages
ISBN:9798400707988
DOI:10.1145/3633637
Copyright © 2023 ACM.
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: 28 February 2024
Check for updates
Author Tags
Qualifiers
- Research-article
- Research
- Refereed limited
Funding Sources
- National Natural Science Foundation of China
- Beijing Natural Science Foundation
Conference
ICCPR 2023
ICCPR 2023: 2023 12th International Conference on Computing and Pattern Recognition
October 27 - 29, 2023
Qingdao, China
Contributors
Other Metrics
Bibliometrics & Citations
Bibliometrics
Article Metrics
- 0Total Citations
- 11Total Downloads
- Downloads (Last 12 months)11
- Downloads (Last 6 weeks)3
Reflects downloads up to 11 Dec 2024
Other Metrics
Citations
View Options
Login options
Check if you have access through your login credentials or your institution to get full access on this article.
Sign inFull Access
View options
View or Download as a PDF file.
PDFeReader
View online with eReader.
eReaderHTML Format
View this article in HTML Format.
HTML Format