skip to main content
research-article

Less Is More: Learning from Synthetic Data with Fine-Grained Attributes for Person Re-Identification

Published:07 June 2023Publication History
Skip Abstract Section

Abstract

Person re-identification (ReID) plays an important role in applications such as public security and video surveillance. Recently, learning from synthetic data [9], which benefits from the popularity of the synthetic data engine, has attracted great attention from the public. However, existing datasets are limited in quantity, diversity, and realisticity, and cannot be efficiently used for the ReID problem. To address this challenge, we manually construct a large-scale person dataset named FineGPR with fine-grained attribute annotations. Moreover, aiming to fully exploit the potential of FineGPR and promote the efficient training from millions of synthetic data, we propose an attribute analysis pipeline called AOST based on the traditional machine learning algorithm, which dynamically learns attribute distribution in a real domain, then eliminates the gap between synthetic and real-world data and thus is freely deployed to new scenarios. Experiments conducted on benchmarks demonstrate that FineGPR with AOST outperforms (or is on par with) existing real and synthetic datasets, which suggests its feasibility for the ReID task and proves the proverbial less-is-more principle. Our synthetic FineGPR dataset is publicly available at https://github.com/JeremyXSC/FineGPR.

REFERENCES

  1. [1] Bak Slawomir, Carr Peter, and Lalonde Jean-Francois. 2018. Domain adaptation through synthesis for unsupervised person re-identification. In Proceedings of the European Conference on Computer Vision. 189205.Google ScholarGoogle Scholar
  2. [2] Barbosa Igor Barros, Cristani Marco, Caputo Barbara, Rognhaugen Aleksander, and Theoharis Theoharis. 2018. Looking beyond appearances: Synthetic training data for deep CNNs in re-identification. Computer Vision and Image Understanding 167 (2018), 5062.Google ScholarGoogle ScholarDigital LibraryDigital Library
  3. [3] Buolamwini Joy and Gebru Timnit. 2018. Gender shades: Intersectional accuracy disparities in commercial gender classification. In Proceedings of the Conference on Fairness, Accountability, and Transparency. 7791.Google ScholarGoogle Scholar
  4. [4] Chen Tianqi and Guestrin Carlos. 2016. XGBoost: A scalable tree boosting system. In Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. 785794.Google ScholarGoogle ScholarDigital LibraryDigital Library
  5. [5] Chen Yuhua, Li Wen, Chen Xiaoran, and Gool Luc Van. 2019. Learning semantic segmentation from synthetic data: A geometrically guided input-output adaptation approach. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 18411850.Google ScholarGoogle ScholarCross RefCross Ref
  6. [6] Das Abir, Chakraborty Anirban, and Roy-Chowdhury Amit K.. 2014. Consistent re-identification in a camera network. In Proceedings of the European Conference on Computer Vision. 330345.Google ScholarGoogle ScholarCross RefCross Ref
  7. [7] Deng Jia, Dong Wei, Socher Richard, Li Li-Jia, Li Kai, and Fei-Fei Li. 2009. ImageNet: A large-scale hierarchical image database. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. IEEE, Los Alamitos, CA, 248255.Google ScholarGoogle ScholarCross RefCross Ref
  8. [8] Deng Weijian, Zheng Liang, Ye Qixiang, Kang Guoliang, Yang Yi, and Jiao Jianbin. 2018. Image-image domain adaptation with preserved self-similarity and domain-dissimilarity for person re-identification. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 9941003.Google ScholarGoogle ScholarCross RefCross Ref
  9. [9] Fabbri Matteo, Brasó Guillem, Maugeri Gianluca, Cetintas Orcun, Gasparini Riccardo, Osep Aljosa, Calderara Simone, Leal-Taixe Laura, and Cucchiara Rita. 2021. MOTSynth: How can synthetic data help pedestrian detection and tracking? In Proceedings of the IEEE/CVF International Conference on Computer Vision. 1084910859.Google ScholarGoogle ScholarCross RefCross Ref
  10. [10] Gatys Leon A., Ecker Alexander S., and Bethge Matthias. 2016. Image style transfer using convolutional neural networks. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 24142423.Google ScholarGoogle ScholarCross RefCross Ref
  11. [11] Goddard Michelle. 2017. The EU General Data Protection Regulation (GDPR): European regulation that has a global impact. International Journal of Market Research 59, 6 (2017), 703705.Google ScholarGoogle ScholarCross RefCross Ref
  12. [12] Goodfellow Ian, Pouget-Abadie Jean, Mirza Mehdi, Xu Bing, Warde-Farley David, Ozair Sherjil, Courville Aaron, and Bengio Yoshua. 2014. Generative adversarial nets. In Advances in Neural Information Processing Systems 27.Google ScholarGoogle ScholarDigital LibraryDigital Library
  13. [13] Gray Douglas, Brennan Shane, and Tao Hai. 2007. Evaluating appearance models for recognition, reacquisition, and tracking. In Proceedings of the IEEE International Workshop on Performance Evaluation for Tracking and Surveillance, Vol. 3. 17.Google ScholarGoogle Scholar
  14. [14] He Kaiming, Zhang Xiangyu, Ren Shaoqing, and Sun Jian. 2016. Deep residual learning for image recognition. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 770778.Google ScholarGoogle ScholarCross RefCross Ref
  15. [15] Hermans Alexander, Beyer Lucas, and Leibe Bastian. 2017. In defense of the triplet loss for person re-identification. arXiv preprint arXiv:1703.07737 (2017).Google ScholarGoogle Scholar
  16. [16] Heusel Martin, Ramsauer Hubert, Unterthiner Thomas, Nessler Bernhard, and Hochreiter Sepp. 2017. GANs trained by a two time-scale update rule converge to a local Nash equilibrium. In Advances in Neural Information Processing Systems 30.Google ScholarGoogle Scholar
  17. [17] Kennedy James and Eberhart Russell. 1995. Particle swarm optimization. In Proceedings of the International Conference on Neural Networks (ICNN’95), Vol. 4. IEEE, Los Alamitos, CA, 19421948.Google ScholarGoogle ScholarCross RefCross Ref
  18. [18] Kingma Diederik P. and Ba Jimmy. 2014. Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014).Google ScholarGoogle Scholar
  19. [19] Li Wei, Zhao Rui, Xiao Tong, and Wang Xiaogang. 2014. DeepReid: Deep filter pairing neural network for person re-identification. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 152159.Google ScholarGoogle ScholarDigital LibraryDigital Library
  20. [20] Li Zhaoju, Zhou Zongwei, Jiang Nan, Han Zhenjun, Xing Junliang, and Jiao Jianbin. 2020. Spatial preserved graph convolution networks for person re-identification. ACM Transactions on Multimedia Computing, Communications, and Applications 16, 1s (2020), 114.Google ScholarGoogle ScholarDigital LibraryDigital Library
  21. [21] Liao Shengcai, Hu Yang, Zhu Xiangyu, and Li Stan Z.. 2015. Person re-identification by local maximal occurrence representation and metric learning. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 21972206.Google ScholarGoogle ScholarCross RefCross Ref
  22. [22] Lin Tsung-Yi, Maire Michael, Belongie Serge, Hays James, Perona Pietro, Ramanan Deva, Dollár Piotr, and Zitnick C. Lawrence. 2014. Microsoft COCO: Common objects in context. In Proceedings of the European Conference on Computer Vision. 740755.Google ScholarGoogle ScholarCross RefCross Ref
  23. [23] Liu Chong, Chang Xiaojun, and Shen Yi-Dong. 2020. Unity style transfer for person re-identification. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 68876896.Google ScholarGoogle ScholarCross RefCross Ref
  24. [24] Luo Hao, Gu Youzhi, Liao Xingyu, Lai Shenqi, and Jiang Wei. 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.Google ScholarGoogle ScholarCross RefCross Ref
  25. [25] Pan Xingang, Luo Ping, Shi Jianping, and Tang Xiaoou. 2018. Two at once: Enhancing learning and generalization capacities via IBN-Net. In Proceedings of the European Conference on Computer Vision. 464479.Google ScholarGoogle ScholarDigital LibraryDigital Library
  26. [26] Pepik Bojan, Stark Michael, Gehler Peter, and Schiele Bernt. 2012. Teaching 3D geometry to deformable part models. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. IEEE, Los Alamitos, CA, 33623369.Google ScholarGoogle ScholarCross RefCross Ref
  27. [27] Ristani Ergys, Solera Francesco, Zou Roger, Cucchiara Rita, and Tomasi Carlo. 2016. Performance measures and a data set for multi-target, multi-camera tracking. In Proceedings of the European Conference on Computer Vision. 1735.Google ScholarGoogle ScholarCross RefCross Ref
  28. [28] Ruiz Nataniel, Schulter Samuel, and Chandraker Manmohan. 2018. Learning to simulate. arXiv preprint arXiv:1810.02513 (2018).Google ScholarGoogle Scholar
  29. [29] Schwartz William Robson and Davis Larry S.. 2009. Learning discriminative appearance-based models using partial least squares. In Proceedings of the XXII Brazilian Symposium on Computer Graphics and Image Processing. IEEE, Los Alamitos, CA, 322329.Google ScholarGoogle ScholarDigital LibraryDigital Library
  30. [30] Simonyan Karen and Zisserman Andrew. 2014. Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556 (2014).Google ScholarGoogle Scholar
  31. [31] Sun Xiaoxiao and Zheng Liang. 2019. Dissecting person re-identification from the viewpoint of viewpoint. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 608617.Google ScholarGoogle ScholarCross RefCross Ref
  32. [32] Torralba Antonio and Efros Alexei A.. 2011. Unbiased look at dataset bias. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. IEEE, Los Alamitos, CA, 15211528.Google ScholarGoogle ScholarDigital LibraryDigital Library
  33. [33] Varior Rahul Rama, Shuai Bing, Lu Jiwen, Xu Dong, and Wang Gang. 2016. A Siamese long short-term memory architecture for human re-identification. In Proceedings of the European Conference on Computer Vision. 135153.Google ScholarGoogle ScholarCross RefCross Ref
  34. [34] Wang Qi, Gao Junyu, Lin Wei, and Yuan Yuan. 2019. Learning from synthetic data for crowd counting in the wild. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 81988207.Google ScholarGoogle ScholarCross RefCross Ref
  35. [35] Wang Yanan, Liao Shengcai, and Shao Ling. 2020. Surpassing real-world source training data: Random 3D characters for generalizable person re-identification. In Proceedings of the 28th ACM International Conference on Multimedia. 34223430.Google ScholarGoogle ScholarDigital LibraryDigital Library
  36. [36] Wei Longhui, Zhang Shiliang, Gao Wen, and Tian Qi. 2018. Person transfer GAN to bridge domain gap for person re-identification. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 7988.Google ScholarGoogle ScholarCross RefCross Ref
  37. [37] Xiang Suncheng, Fu Yuzhuo, Guan Mengyuan, and Liu Ting. 2022. Learning from self-discrepancy via multiple co-teaching for cross-domain person re-identification. Machine Learning. Published online, June 14, 2022.Google ScholarGoogle Scholar
  38. [38] Xiang Suncheng, Fu Yuzhuo, You Guanjie, and Liu Ting. 2020. Unsupervised domain adaptation through synthesis for person re-identification. In Proceedings of the IEEE International Conference on Multimedia and Expo. IEEE, Los Alamitos, CA, 16.Google ScholarGoogle ScholarCross RefCross Ref
  39. [39] Xiang Suncheng, Fu Yuzhuo, You Guanjie, and Liu Ting. 2021. Taking a closer look at synthesis: Fine-grained attribute analysis for person re-identification. In Proceedings of the IEEE International Conference on Acoustics, Speech, and Signal Processing. IEEE, Los Alamitos, CA, 37653769.Google ScholarGoogle ScholarCross RefCross Ref
  40. [40] Xiang Suncheng, Gao Jingsheng, Zhang Zirui, Guan Mengyuan, Yan Binjie, Liu Ting, Qian Dahong, and Fu Yuzhuo. 2021. Rethinking person re-identification via semantic-based pretraining. arXiv preprint arXiv:2110.05074 (2021).Google ScholarGoogle Scholar
  41. [41] Xiang Suncheng, You Guanjie, Li Leqi, Guan Mengyuan, Liu Ting, Qian Dahong, and Fu Yuzhuo. 2022. Rethinking illumination for person re-identification: A unified view. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 47314739.Google ScholarGoogle ScholarCross RefCross Ref
  42. [42] Xiao Tong, Li Shuang, Wang Bochao, Lin Liang, and Wang Xiaogang. 2017. Joint detection and identification feature learning for person search. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 34153424.Google ScholarGoogle ScholarCross RefCross Ref
  43. [43] Yao Yue, Zheng Liang, Yang Xiaodong, Naphade Milind, and Gedeon Tom. 2020. Simulating content consistent vehicle datasets with attribute descent. In Proceedings of the European Conference on Computer Vision. 775791.Google ScholarGoogle ScholarDigital LibraryDigital Library
  44. [44] Zhang Tianyu, Xie Lingxi, Wei Longhui, Zhuang Zijie, Zhang Yongfei, Li Bo, and Tian Qi. 2021. UnrealPerson: An adaptive pipeline towards costless person re-identification. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 1150611515.Google ScholarGoogle ScholarCross RefCross Ref
  45. [45] Zhang Zhilu and Sabuncu Mert R.. 2018. Generalized cross entropy loss for training deep neural networks with noisy labels. In Proceedings of the 32nd International Conference on Neural Information Processing Systems.Google ScholarGoogle ScholarDigital LibraryDigital Library
  46. [46] Zhao Rui, Ouyang Wanli, and Wang Xiaogang. 2014. Learning mid-level filters for person re-identification. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 144151.Google ScholarGoogle ScholarDigital LibraryDigital Library
  47. [47] Zhao Zhongwei, Song Ran, Zhang Qian, Duan Peng, and Zhang Youmei. 2022. JoT-GAN: A framework for jointly training GAN and person re-identification model. ACM Transactions on Multimedia Computing, Communications, and Applications 18, 1s (2022), 118.Google ScholarGoogle ScholarDigital LibraryDigital Library
  48. [48] Zheng Liang, Shen Liyue, Tian Lu, Wang Shengjin, Wang Jingdong, and Tian Qi. 2015. Scalable person re-identification: A benchmark. In Proceedings of the IEEE/CVF International Conference on Computer Vision. 11161124.Google ScholarGoogle ScholarCross RefCross Ref
  49. [49] Zheng Zhedong, Zheng Liang, and Yang Yi. 2017. Unlabeled samples generated by GAN improve the person re-identification baseline in vitro. In Proceedings of the IEEE/CVF International Conference on Computer Vision. 37543762.Google ScholarGoogle ScholarCross RefCross Ref
  50. [50] Zhong Zhun, Zheng Liang, Cao Donglin, and Li Shaozi. 2017. Re-ranking person re-identification with k-reciprocal encoding. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 13181327.Google ScholarGoogle ScholarCross RefCross Ref
  51. [51] Zhong Zhun, Zheng Liang, Zheng Zhedong, Li Shaozi, and Yang Yi. 2018. CamStyle: A novel data augmentation method for person re-identification. IEEE Transactions on Image Processing 28, 3 (2018), 11761190.Google ScholarGoogle ScholarDigital LibraryDigital Library
  52. [52] Zhu Jun-Yan, Park Taesung, Isola Phillip, and Efros Alexei A.. 2017. Unpaired image-to-image translation using cycle-consistent adversarial networks. In Proceedings of the IEEE/CVF International Conference on Computer Vision. 22232232.Google ScholarGoogle ScholarCross RefCross Ref

Index Terms

  1. Less Is More: Learning from Synthetic Data with Fine-Grained Attributes for Person Re-Identification

        Recommendations

        Comments

        Login options

        Check if you have access through your login credentials or your institution to get full access on this article.

        Sign in

        Full Access

        • Published in

          cover image ACM Transactions on Multimedia Computing, Communications, and Applications
          ACM Transactions on Multimedia Computing, Communications, and Applications  Volume 19, Issue 5s
          October 2023
          280 pages
          ISSN:1551-6857
          EISSN:1551-6865
          DOI:10.1145/3599694
          • Editor:
          • Abdulmotaleb El Saddik
          Issue’s Table of Contents

          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: 7 June 2023
          • Online AM: 20 March 2023
          • Accepted: 7 March 2023
          • Revised: 23 January 2023
          • Received: 14 August 2022
          Published in tomm Volume 19, Issue 5s

          Permissions

          Request permissions about this article.

          Request Permissions

          Check for updates

          Qualifiers

          • research-article
        • Article Metrics

          • Downloads (Last 12 months)244
          • Downloads (Last 6 weeks)45

          Other Metrics

        PDF Format

        View or Download as a PDF file.

        PDF

        eReader

        View online with eReader.

        eReader

        Full Text

        View this article in Full Text.

        View Full Text
        About Cookies On This Site

        We use cookies to ensure that we give you the best experience on our website.

        Learn more

        Got it!