Semantic Map Guided Identity Transfer GAN for Person Re-identification

被引：3
作者：
Wu, Tian [1 ,2 ,3 ]
Zhu, Rongbo [1 ,2 ,3 ,4 ]
Wan, Shaohua [5 ]
机构：
[1] Shenzhen Institute of Nutrition and Health, Huazhong Agricultural University
[2] Shenzhen Branch, Guangdong Laboratory for Lingnan Modern Agriculture, Genome Analysis Laboratory of the Ministry of Agriculture, Agricultural Genomics Institute at Shenzhen, Chinese Academy of Agricultural Sciences
[3] Shenzhen Institute for Advanced Study, University of Electronic Science and Technology of China
来源：
ACM Transactions on Multimedia Computing, Communications and Applications | 2024年 / 20卷 / 11期
基金：
中国国家自然科学基金;
关键词：
generative adversarial network; identity transfer; joint training; Person re-identification;
D O I：
10.1145/3631355
中图分类号：
学科分类号：
摘要：
Generative adversarial networks (GANs)-based person re-identification (re-id) schemes provide potential ways to augment data in practical applications. However, existing solutions perform poorly because of the separation of data generation and re-id training and a lack of diverse data in real-world scenarios. In this paper, a person re-id model (IDGAN) based on semantic map guided identity transfer GAN is proposed to improve the person re-id performance. With the aid of the semantic map, IDGAN generates pedestrian images with varying poses, perspectives, and backgrounds efficiently and accurately, improving the diversity of training data. To increase the visual realism, IDGAN utilizes a gradient augmentation method based on local quality attention to refine the generated image locally. Then, a two-stage joint training framework is employed to allow the GAN and the person re-id network to learn from each other to better use the generated data. Detailed experimental results demonstrate that, compared with the existing state-of-the-art methods, IDGAN is capable of producing high-quality images and significantly enhancing re-id performance, with the FID of generated images on the Market-1501 dataset being reduced by 1.15, and mAP on the Market-1501 and DukeMTMC-reID datasets being increased by 3.3% and 2.6%, respectively. © 2024 Copyright held by the owner/author(s)
引用
收藏
相关论文
共 47 条
  • [1] Arjovsky M., Chintala S., Bottou L., Wasserstein generative adversarial networks, Proceedings of the 34th International Conference on Machine Learning, 70, pp. 214-223, (2017)
  • [2] Bai X., Yang M., Huang T., Dou Z., Yu R., Xu Y., Deep-person: Learning discriminative deep features for person re-identification, Pattern Recognition, 98, (2020)
  • [3] Chen H., Wang Y., Lagadec B., Dantcheva A., Bremond F., Joint generative and contrastive learning for unsupervised person re-identification, 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR’21), pp. 2004-2013, (2021)
  • [4] Deng J., Dong W., Socher R., Li L.-J., Li K., Fei-Fei L., ImageNet: A large-scale hierarchical image database, 2009 IEEE Conference on Computer Vision and Pattern Recognition, pp. 248-255, (2009)
  • [5] Ge Y., Li Z., Zhao H., Yin G., Yi S., Wang X., Li H., FD-GAN: Pose-guided feature distilling GAN for robust person re-identification, Advances in Neural Information Processing Systems, 31, (2018)
  • [6] Goodfellow I., Pouget-Abadie J., Mirza M., Xu B., Warde-Farley D., Ozair S., Courville A., Bengio Y., Generative adversarial nets, Advances in Neural Information Processing Systems, 27, (2014)
  • [7] Gou J., Sun L., Yu B., Wan S., Tao D., Hierarchical multi-attention transfer for knowledge distillation, ACM Trans. Multimedia Comput. Commun. Appl., 20, 2, (2023)
  • [8] Gulrajani I., Ahmed F., Arjovsky M., Dumoulin V., Courville A.C., Improved training of Wasserstein GANs, Advances in Neural Information Processing Systems, 30, (2017)
  • [9] He K., Zhang X., Ren S., Sun J., Deep residual learning for image recognition, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR’16), pp. 770-778, (2016)
  • [10] Hermans A., Beyer L., Leibe B., In defense of the triplet loss for person re-identification, CoRR, (2017)
12345