Yanan Wang
ABSTRACT
Person re-identification has seen significant advancement in recent years. However, the ability of learned models to generalize to unknown target domains still remains limited. One possible reason for this is the lack of large-scale and diverse source training data, since manually labeling such a dataset is very expensive and privacy sensitive. To address this, we propose to automatically synthesize a large-scale person re-identification dataset following a set-up similar to real surveillance but with virtual environments, and then use the synthesized person images to train a generalizable person re-identification model. Specifically, we design a method to generate a large number of random UV texture maps and use them to create different 3D clothing models. Then, an automatic code is developed to randomly generate various different 3D characters with diverse clothes, races and attributes. Next, we simulate a number of different virtual environments using Unity3D, with customized camera networks similar to real surveillance systems, and import multiple 3D characters at the same time, with various movements and interactions along different paths through the camera networks. As a result, we obtain a virtual dataset, called RandPerson, with 1,801,816 person images of 8,000 identities. By training person re-identification models on these synthesized person images, we demonstrate, for the first time, that models trained on virtual data can generalize well to unseen target images, surpassing the models trained on various real-world datasets, including CUHK03, Market-1501, DukeMTMC-reID, and almost MSMT17. The RandPerson dataset is available at https://github.com/VideoObjectSearch/RandPerson.
Supplemental Material
Available for Download
The supplemental material contains a PDF for the appendix of the paper, where additional experimental results are provided.
- Slawomir Bak, Peter Carr, and Jean-Francois Lalonde. 2018. Domain adaptation through synthesis for unsupervised person re-identification. In Proceedings of the European Conference on Computer Vision (ECCV). 189--205.Google Scholar
- Igor Barros Barbosa, Marco Cristani, Barbara Caputo, Aleksander Rognhaugen, and Theoharis Theoharis. 2018. Looking beyond appearances: Synthetic training data for deep cnns in re-identification. Computer Vision and Image Understanding, Vol. 167 (2018), 50--62.Google ScholarDigital Library
- Christopher M Bishop. 2006. Pattern recognition and machine learning. Springer.Google Scholar
- Christian Chang. 2006. Modeling, UV Mapping, and Texturing 3D Game Weapons. Wordware Publishing, Inc.Google Scholar
- MakeHuman Community. 2020 a. MakeHuman: Open Source Tool for Making 3D Characters. http://www.makehumancommunity.org.Google Scholar
- PyTorch Community. 2020 b. PyTorch: An open-source Python machine learning library. https://pytorch.org/.Google Scholar
- Hehe Fan, Liang Zheng, Chenggang Yan, and Yi Yang. 2018. Unsupervised person re-identification: Clustering and fine-tuning. ACM Transactions on Multimedia Computing, Communications, and Applications (TOMM), Vol. 14, 4 (2018), 1--18.Google ScholarDigital Library
- Michela Farenzena, Loris Bazzani, Alessandro Perina, Vittorio Murino, and Marco Cristani. 2010. Person re-identification by symmetry-driven accumulation of local features. In 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. IEEE, 2360--2367.Google ScholarCross Ref
- Shaogang Gong, Marco Cristani, Chen Change Loy, and Timothy M Hospedales. 2014. The re-identification challenge. In Person re-identification. Springer, 1--20.Google Scholar
- Ian Goodfellow, Yoshua Bengio, and Aaron Courville. 2016. Deep learning .MIT press.Google Scholar
- Mengran Gou, Ziyan Wu, Angels Rates-Borras, Octavia Camps, Richard J Radke, et al. 2018. A systematic evaluation and benchmark for person re-identification: Features, metrics, and datasets. IEEE transactions on pattern analysis and machine intelligence, Vol. 41, 3 (2018), 523--536.Google Scholar
- Douglas Gray and Hai Tao. 2008. Viewpoint invariant pedestrian recognition with an ensemble of localized features. In European conference on computer vision. Springer, 262--275.Google ScholarDigital Library
- Kaiming He, Xiangyu Zhang, Shaoqing Ren, and Jian Sun. 2016. Deep residual learning for image recognition. In Proceedings of the IEEE conference on computer vision and pattern recognition. 770--778.Google ScholarCross Ref
- Martin Hirzer, Csaba Beleznai, Peter M Roth, and Horst Bischof. 2011. Person re-identification by descriptive and discriminative classification. In Scandinavian conference on Image analysis. Springer, 91--102.Google ScholarCross Ref
- Yang Hu, Dong Yi, Shengcai Liao, Zhen Lei, and Stan Z Li. 2014. Cross dataset person re-identification. In Asian Conference on Computer Vision. Springer, 650--664.Google Scholar
- Wei Li and Xiaogang Wang. 2013. Locally aligned feature transforms across views. In Proceedings of the IEEE conference on computer vision and pattern recognition. 3594--3601.Google ScholarDigital Library
- Wei Li, Rui Zhao, and Xiaogang Wang. 2012. Human reidentification with transferred metric learning. In Asian conference on computer vision. Springer, 31--44.Google Scholar
- Wei Li, Rui Zhao, Tong Xiao, and Xiaogang Wang. 2014. Deepreid: Deep filter pairing neural network for person re-identification. In Proceedings of the IEEE conference on computer vision and pattern recognition. 152--159.Google ScholarDigital Library
- Shengcai Liao and Ling Shao. 2020. Interpretable and Generalizable Person Re-Identification with Query-Adaptive Convolution and Temporal Lifting. In European Conference on Computer Vision (ECCV) .Google Scholar
- Jiawei Liu, Zheng-Jun Zha, QI Tian, Dong Liu, Ting Yao, Qiang Ling, and Tao Mei. 2016. Multi-scale triplet cnn for person re-identification. In Proceedings of the 24th ACM international conference on Multimedia. 192--196.Google ScholarDigital Library
- Chen Change Loy, Chunxiao Liu, and Shaogang Gong. 2013. Person re-identification by manifold ranking. In 2013 IEEE International Conference on Image Processing. IEEE, 3567--3571.Google ScholarCross Ref
- Open-ReID. 2020. Open-Source Person Re-Identification Library. https://cysu.github.io/open-reid.Google Scholar
- P. Jonathon Phillips, Patrick Grother, and Ross Micheals. Sep. 2011. Evaluation Methods in Face Recognition. In Handbook of Face Recognition 2nd ed.), S. Z. Li and A. K. Jain (Eds.). Springer, Chapter 21, 551--574.Google Scholar
- T. Sobh and K. Elleithy. 2010. Innovations in Computing Sciences and Software Engineering .Springer Netherlands. 2010927601 https://books.google.ae/books?id=IQ8h_d5rR0MCGoogle Scholar
- Xiaoxiao Sun and Liang Zheng. 2019. Dissecting person re-identification from the viewpoint of viewpoint. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 608--617.Google ScholarCross Ref
- Unity Technologies. 2020. Unity3D: Cross-platform game engine. https://unity.com.Google Scholar
- 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.Google ScholarDigital Library
- Longhui Wei, Shiliang Zhang, Wen Gao, and Qi Tian. 2018. Person transfer gan to bridge domain gap for person re-identification. In Proceedings of the IEEE conference on computer vision and pattern recognition. 79--88.Google ScholarCross Ref
- Mang Ye, Jianbing Shen, Gaojie Lin, Tao Xiang, Ling Shao, and Steven CH Hoi. 2020. Deep Learning for Person Re-identification: A Survey and Outlook. arXiv preprint arXiv:2001.04193 (2020).Google Scholar
- Dong Yi, Zhen Lei, Shengcai Liao, and Stan Z Li. 2014. Deep metric learning for person re-identification. In 2014 22nd International Conference on Pattern Recognition. IEEE, 34--39.Google ScholarDigital Library
- 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.Google ScholarDigital Library
- Liang Zheng, Yi Yang, and Alexander G Hauptmann. 2016. Person re-identification: Past, present and future. arXiv preprint arXiv:1610.02984 (2016).Google Scholar
- Wei-Shi Zheng, Shaogang Gong, and Tao Xiang. 2009. Associating Groups of People.. In BMVC, Vol. 2.Google ScholarCross Ref
- 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.Google ScholarCross Ref
- Zhun Zhong, Liang Zheng, Donglin Cao, and Shaozi Li. 2017. Re-ranking person re-identification with k-reciprocal encoding. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 1318--1327.Google ScholarCross Ref
- Zhun Zhong, Liang Zheng, Zhedong Zheng, Shaozi Li, and Yi Yang. 2018. Camstyle: A novel data augmentation method for person re-identification. IEEE Transactions on Image Processing, Vol. 28, 3 (2018), 1176--1190.Google ScholarDigital Library
Index Terms
- Surpassing Real-World Source Training Data: Random 3D Characters for Generalizable Person Re-Identification
Recommendations
A Framework for Jointly Training GAN with Person Re-Identification Model
Pattern Recognition. ICPR International Workshops and ChallengesAbstractTo cope with the problem caused by inadequate training data, many person re-identification (re-id) methods exploited generative adversarial networks (GAN) for data augmentation, where the training of GAN is typically independent of that of the re-...
Enhancing Person Re-identification in a Self-Trained Subspace
Despite the promising progress made in recent years, person re-identification (re-ID) remains a challenging task due to the complex variations in human appearances from different camera views. For this challenging problem, a large variety of algorithms ...
Deep multi-instance learning for end-to-end person re-identification
In this paper, we introduce a deep multi-instance learning framework to boost the instance-level person re-identification performance. Motivated by the observation of considerably dramatic and complex varieties of visual appearances in many current ...
Comments