Abstract
It is manifested that when training and testing models on different datasets, the performance of trained models will severely dropped due to the differences in style of the datasets. In person ReID task, the clothing style is a crucial factor existing in different datasets, which has not been considered in the current research. We proposed a novel approach of Optimization of Domain Adaption Though Clothing Style Transfer (ODA-CST), which includes clothing mask extraction and clothing style transfer. Firstly, we generate the clothing mask by jointly locally extracting clothing and globally detecting the person. Meanwhile, we also organize a clothing mask dataset to improve the model. Our ODA-CST can effectively generate photos with the clothing style transferred, which is the first method that tries to solve the clothing style gap in person ReID task to the best knowledge. The importance of clothing style transfer and the effectiveness of our method are verified by the experiment.
Student paper.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsReferences
Zheng, Z., Zheng, L., Yang, Y.: Unlabeled samples generated by GAN improve the person re-identification baseline in vitro. In: ICCV 2017 (2017)
Qian, X., Fu, Y., Wang, W., et al.: Pose-normalized image generation for person re-identification. arXiv preprint. arXiv:1712.02225 (2017)
Zheng, L., Shen, L., Tian, L., Wang, S., Wang, J., Tian, Q.: Scalable person re-identification: a benchmark. In: ICCV 2015 (2015)
Li, W., Zhao, R., Xiao, T., Wang, X.: Deepreid: deep filter pairing neural network for person re-identification. In: CVPR 2014 (2014)
Mao, X., Li, Q., Xie, H., Lau, R.Y.K., Wang, Z., Paul Smolley, S.: Least squares generative adversarial networks. In: ICCV (2017)
Kim, T., Cha, M., Kim, H., Lee, J.K., Kim, J.: Learning to discover cross-domain relations with generative adversarial networks. arXiv preprint. arXiv:1703.05192 (2017)
Taigman, Y., Polyak, A., Wolf, L.: Unsupervised cross-domain image generation. arXiv preprint. arXiv:1611.02200 (2016)
Zheng, Z., Zheng, L., Yang, Y.: A discriminatively learned CNN embedding for person re-identification. In: TOMM (2016)
Wei, L., Zhang, S., Gao, W., et al.: Person transfer GAN to bridge domain gap for person re-identification. In: CVPR (2018)
Goodfellow, I., et al.: Generative adversarial nets. In: NIPS 2014 (2014)
Zheng, Z., Zheng, L., Yang, Y.: Unlabeled samples generated by GAN improve the person re-identification baseline in vitro. arXiv preprint. arXiv:1701.07717 (2017)
Zhong, Z., Zheng, L., Zheng, Z., et al.: Camera style adaptation for person re-identification. arXiv preprint. arXiv:1711.10295 (2017)
Ge, Y., et al.: FD-GAN: pose-guided feature distilling GAN for robust person re-identification. In: CVPR (2018)
Song, C., Huang, Y., Ouyang, W., Wang, L.: Mask-guided contrastive attention model for person re-identification. In: CVPR (2018)
Yang, W., Luo, P., Lin, L.: Clothing co-parsing by joint image segmentation and labeling. In: CVPR (2014)
Liang, X., et al.: Deep human parsing with active template regression. TPAMI 37(12), 2402–2414 (2015)
Zhu, J.-Y., Park, T., Isola, P., et al.: Unpaired image-to-image translation using cycle-consistent adversarial networks. arXiv preprint. arXiv:1703.10593 (2017)
He, K.M., Zhang, X.Y., Ren, S.Q., Sun, J.: Deep residual learning for image recognition. In: CVPR (2016)
Radford, A., Metz, L., Chintala, S.: Unsupervised representation learning with deep convolutional generative adversarial networks. In: ICLR (2016)
Isola, P., Zhu, J.-Y., Zhou, T., Efros, A.A.: Image-to-image translation with conditional adversarial nets. In: CVPR (2017)
Mo, S., Choy, M., Shin, J.: InstaGAN: instance-aware image-to-image translation. In: ICLR (2019)
Zhao, H., Shi, J., Qi, X., Wang, X., Jia, J.: Pyramid scene parsing network. In: CVPR (2017)
Peng, P., Xiang, T., Wang, Y., et al.: Unsupervised cross-dataset transfer learning for person reidentification. In: CVPR (2016)
Acknowledgement
This work is partially supported by the National Natural Science Foundation of China (Grant no. 61772568), the Guangzhou Science and Technology Program (Grant no. 201804010288), and the Fundamental Research Funds for the Central Universities (Grant no. 18lgzd15).
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2019 Springer Nature Switzerland AG
About this paper
Cite this paper
Wang, H., Yang, M., Li, H., Ye, L. (2019). Person ReID: Optimization of Domain Adaption Though Clothing Style Transfer Between Datasets. In: Lin, Z., et al. Pattern Recognition and Computer Vision. PRCV 2019. Lecture Notes in Computer Science(), vol 11859. Springer, Cham. https://doi.org/10.1007/978-3-030-31726-3_43
Download citation
DOI: https://doi.org/10.1007/978-3-030-31726-3_43
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-31725-6
Online ISBN: 978-3-030-31726-3
eBook Packages: Computer ScienceComputer Science (R0)