Abstract
Recently, researchers begin using generated as well as transferred images to expand the training dataset of person re-identification. It expands the training dataset’s sample space, which contributes to learning more robust features for the Re-ID network. However, these works only transfer a certain kind of feature between images. There is no known attempt to transfer multiple features across multiple images. By transferring multiple features, the sample space expands further, allowing Re-ID networks to learn more robust features. In this paper, we propose a unified framework and pipeline to integrate multiple feature transfer networks. Users are also free to determine how to transfer these features. Based on the above framework and pipeline, we create a large amount of transferred images from the Market-1501 dataset and create an expanded dataset named Market1501-EX. Further more, we propose a corresponding person identification labeling method for identity loss, using the generation information provided by the dataset. We use this dataset to train a Re-ID network, and the training result in this paper rests at mid-high level of related works which also utilize generated images.
Keywords
This project is supported by the NSFC (62076258, 61902444).
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
Bhuiyan, A., Liu, Y., Siva, P., Javan, M., Ayed, I.B., Granger, E.: Pose guided gated fusion for person re-identification. In: WACV, pp. 2675–2684 (2020)
Cao, Z., Simon, T., Wei, S.E., Sheikh, Y.: Realtime multi-person 2d pose estimation using part affinity fields. In: CVPR (2017)
Chen, T., et al.: Abd-net: Attentive but diverse person re-identification. In: ICCV, pp. 8351–8361 (2019)
Deng, W., Zheng, L., Ye, Q., Kang, G., Yang, Y., Jiao, J.: Image-image domain adaptation with preserved self-similarity and domain-dissimilarity for person re-identification. In: CVPR, pp. 994–1003 (2018)
Ge, Y., et al.: Fd-gan: Pose-guided feature distilling gan for robust person re-identification. arXiv preprint arXiv:1810.02936 (2018)
Gheissari, N., Sebastian, T.B., Hartley, R.: Person reidentification using spatiotemporal appearance. In: CVPR, vol. 2, pp. 1528–1535. IEEE (2006)
Isola, P., Zhu, J.Y., Zhou, T., Efros, A.A.: Image-to-image translation with conditional adversarial networks. In: CVPR, pp. 1125–1134 (2017)
Krizhevsky, A., Sutskever, I., Hinton, G.E.: Imagenet classification with deep convolutional neural networks. NIPS 25, 1097–1105 (2012)
LeCun, Y., Bottou, L., Bengio, Y., Haffner, P.: Gradient-based learning applied to document recognition. IEEE 86(11), 2278–2324 (1998)
Li, W., Zhao, R., Xiao, T., Wang, X.: Deepreid: deep filter pairing neural network for person re-identification. In: CVPR, pp. 152–159 (2014)
Li, W., Zhu, X., Gong, S.: Harmonious attention network for person re-identification. In: CVPR, pp. 2285–2294 (2018)
Li, Y., Wang, T., Liu, L.: Random style transfer for person re-identification with one example. AIMS Math. 6(5), 4715–4733 (2021)
Liu, H., Feng, J., Qi, M., Jiang, J., Yan, S.: End-to-end comparative attention networks for person re-identification. TIP 26(7), 3492–3506 (2017)
Liu, J., Ni, B., Yan, Y., Zhou, P., Cheng, S., Hu, J.: Pose transferrable person re-identification. In: CVPR, pp. 4099–4108 (2018)
Ma, L., Jia, X., Sun, Q., Schiele, B., Tuytelaars, T., Van Gool, L.: Pose guided person image generation. arXiv preprint arXiv:1705.09368 (2017)
Neverova, N., Guler, R.A., Kokkinos, I.: Dense pose transfer. In: ECCV (September 2018)
Pan, H., Cao, X.: Pose transfer based on generative adversarial networks. In: Su, R. (ed.) 2020 International Conference on Image, Video Processing and Artificial Intelligence, vol. 11584, pp. 239–244. International Society for Optics and Photonics, SPIE (2020)
Qian, X., et al.: Pose-normalized image generation for person re-identification. In: ECCV (September 2018)
Siarohin, A., Sangineto, E., Lathuiliere, S., Sebe, N.: Deformable gans for pose-based human image generation. In: CVPR, pp. 3408–3416 (2018)
Sun, J., Li, Y., Chen, H., Zhang, B., Zhu, J.: Memf: multi-level-attention embedding and multi-layer-feature fusion model for person re-identification. PR 116, 107937 (2021)
Sun, Y., Zheng, L., Yang, Y., Tian, Q., Wang, S.: Beyond part models: person retrieval with refined part pooling (and a strong convolutional baseline). In: ECCV, pp. 480–496 (2018)
Tang, Y., Xi, Y., Wang, N., Song, B., Gao, X.: Cgan-tm: a novel domain-to-domain transferring method for person re-identification. TIP 29, 5641–5651 (2020)
Wang, H., Hu, J., Zhang, G.: Multi-source transfer network for cross domain person re-identification. IEEE Access 8, 83265–83275 (2020)
Wang, Y., Liao, S., Shao, L.: Surpassing real-world source training data: Random 3d characters for generalizable person re-identification. In: ACMMM, pp. 3422–3430 (2020)
Wei, S.E., Ramakrishna, V., Kanade, T., Sheikh, Y.: Convolutional pose machines. In: CVPR (2016)
Yang, Q., Wu, A., Zheng, W.S.: Person re-identification by contour sketch under moderate clothing change. In: TPAMI (2020)
Yi, D., Lei, Z., Liao, S., Li, S.Z.: Deep metric learning for person re-identification. In: ICPR, pp. 34–39. IEEE (2014)
Zeng, Z., Wang, Z., Wang, Z., Zheng, Y., Chuang, Y.Y., Satoh, S.: Illumination-adaptive person re-identification. TMM 22(12), 3064–3074 (2020)
Zheng, Z., Yang, X., Yu, Z., Zheng, L., Yang, Y., Kautz, J.: Joint discriminative and generative learning for person re-identification. In: CVPR, pp. 2138–2147 (2019)
Zheng, Z., Zheng, L., Yang, Y.: Unlabeled samples generated by GAN improve the person re-identification baseline in vitro. In: ICCV, pp. 3754–3762 (2017)
Zhu, J.Y., Park, T., Isola, P., Efros, A.A.: Unpaired image-to-image translation using cycle-consistent adversarial networks. In: ICCV, pp. 2223–2232 (2017)
Zhu, Z., Huang, T., Shi, B., Yu, M., Wang, B., Bai, X.: Progressive pose attention transfer for person image generation. In: CVPR (June 2019)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2021 Springer Nature Switzerland AG
About this paper
Cite this paper
Deng, J., Feng, Z., Chen, P., Lai, J. (2021). Training Person Re-identification Networks with Transferred Images. In: Ma, H., et al. Pattern Recognition and Computer Vision. PRCV 2021. Lecture Notes in Computer Science(), vol 13019. Springer, Cham. https://doi.org/10.1007/978-3-030-88004-0_30
Download citation
DOI: https://doi.org/10.1007/978-3-030-88004-0_30
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-88003-3
Online ISBN: 978-3-030-88004-0
eBook Packages: Computer ScienceComputer Science (R0)