Guang Han
ABSTRACT
Person re-identification (re-id) is a challenging and valuable research topic in the field of computer vision. It needs to match person images with the same identity in multiple camera systems. The change of pose is one of the key factors that affect the network to extract robust features. In order to mitigate the influence of pose variations on person re-id, the paper proposes a person re-id method based on a pose-guided generative adversarial network (PG-GAN), which can be used to learn identity-sensitive and pose-insensitive features. The algorithm is composed of a Siamese convolutional neural network (SCNN) and generative adversarial networks (GANs). SCNN is a symmetric structure with ResNet-50. GANs contain multiple pose discriminators and identity discriminators, as well as incorporate pose loss, which requires appearance of the generated image with same identity to be similar. The proposed method has been well performed on pedestrian reidentification datasets.
- H. Zhao, M. Tian, S. Sun, J. Shao, S. Yi, X. Wang, X. Tang, "Spindle net: Person re-identification with human body region guided feature decomposition and fusion," in CVPR, pp.907--915, 2017.Google Scholar
- Z. Zheng, L. Zheng, Y. Yang, "Pedestrain alignment network for large-scale person re-identification," in TCSVT, pp.1--1, 2018.Google Scholar
- L. He, J. Liang, H. Li, Z. Sun, "Deep spatial feature reconstruction for partial person re-identification: alignment-free approach," in CVPR, pp.7073--7082, 2018.Google Scholar
- W. Li, X. Zhu, S. Gong, "Harmonious attention network for person reidentification," in CVPR, pp.2285--2294, 2018.Google Scholar
- Y. Guo, N. Cheung, "Efficient and deep person re-identification using multi-level similarity," in CVPR, pp.2335--2344, 2018.Google Scholar
- R. Alec, M. Luke, C. Soumith, "Unsupervised representation learning with deep convolutional generative adversarial networks," arXiv preprint arXiv:1511.06434, 2015.Google Scholar
- C. Xi, D. Yan, H. Rein, S. John, S. Ilya, A. Pieter, "Infogan: Interpretable representation learning by information maximizing generative adversarial nets," in NIPS, pp.2172--2180, 2016.Google Scholar
- A. Martín, C. Soumith, B. Léon, "Wasserstein GAN," arXiv preprint arXiv:1701.07875, 2017.Google Scholar
- Z. Zheng, L. Zheng, Y. Yang, "Unlabeled samples generated by gan improve the person re-identification baseline in vitro," in ICCV, pp.3774--3782, 2017.Google Scholar
- L. Wei, S. Zhang, W. Gao, Q. Tian, "Person transfer gan to bridge domain gap for person re-identification," in CVPR, pp.79--88, 2018.Google Scholar
- Z. Zhong, L. Zheng, D. Cao, et al., "Re-ranking Person Reidentification with k-Reciprocal Encoding," in CVPR, pp.3652--3661, 2017.Google Scholar
- L. Zheng, Y. Yang, Q. Tian, "SIFT meets CNN: A decade survey of instance retrieval," Pattern Analysis and Machine Intelligence, pp.1224--1244, 2018.Google Scholar
- R. Arandjelović, A. Zisserman, "Three things everyone should know to improve object retrieval," in CVPR, pp.2911--2918, 2012.Google Scholar
- S. Bai, X. Bai, "Sparse contextual activation for efficient visual reranking," in IEEE Trans on Image Processing, pp.1056--1069, 2016.Google Scholar
- J. Garcia, N. Martinel, C. Micheloni, et al., "Person re-identification ranking optimization by discriminant context information analysis," in ICCV, pp.1305--1313, 2015.Google Scholar
- H. Wang, S. Liao, Z. Lei, Y. Yang, "Is re-ranking useful for open-set person re-identification," in Big Data, pp.4625--4631, 2018.Google Scholar
- L. Zheng, L. Shen, L. Tian, et al., "Scalable person re-identification: A benchmark," in ICCV, pp.1116--1124, 2015.Google Scholar
- W. Li, R. Zhao, T. Xiao, X. Wang, "Deepreid: Deep filter pairing neural network for person re-identification," in CVPR, pp.152--159, 2014.Google Scholar
- E. Ristani, F. Solera, R. Zou, R. Cucchiara, C. Tomasi, "Performance measures and a data set for multi-target, multi-camera tracking," in ECCV, 2016.Google Scholar
- K. He, X. Zhang, S. Ren, et al., "Deep residual learning for image recognition," in CVPR, pp.770--778, 2016.Google Scholar
- Z. Cao, T. Simon, S. Wei, Y. Sheikh, "Realtime multi-person 2d pose estimation using part affinity fields," in CVPR, pp.1302--1310, 2017.Google Scholar
- P. Isola, J. Zhu, T. Zhou, et al., "Image-to-image translation with conditional adversarial networks," in CVPR, pp.5967--5976, 2017.Google Scholar
- J. Deng, W. Dong, R. et al., "Imagenet: A large-scale hierarchical image database," in CVPR, pp.248--255, 2009.Google Scholar
- T. Salimans, I. Goodfellow, W. Zaremba, et al., "Improved techniques for training gans," in NIPS, 2016.Google Scholar
- J. Xu, R. Zhao, F. Zhu, H. Wang, W. Ouyang, "Attention-aware compositional network for person re-identification," in CVPR, pp.2119--2128, 2018.Google Scholar
- M. Sarfraz, A. Schumann, A. Eberle, R. Stiefelhagen, "A posesensitive embedding for person re-identification with expanded cross neighborhood re-ranking," in CVPR, pp.420--429, 2018.Google Scholar
Index Terms
- Person Re-identification Based on Pose-guided Generative Adversarial Network
Recommendations
Generative Adversarial Networks (GANs): Challenges, Solutions, and Future Directions
Generative Adversarial Networks (GANs) is a novel class of deep generative models that has recently gained significant attention. GANs learn complex and high-dimensional distributions implicitly over images, audio, and data. However, there exist major ...
Deep Compact Person Re-Identification with Distractor Synthesis via Guided DC-GANs
Image Analysis and Processing – ICIAP 2019AbstractWe present a dual-stream CNN that learns both appearance and facial features in tandem from still images and, after feature fusion, infers person identities. We then describe an alternative architecture of a single, lightweight ID-CondenseNet ...
Anomaly detection of adversarial examples using class-conditional generative adversarial networks
AbstractDeep neural networks (DNNs) have been shown vulnerable to Test-Time Evasion attacks (TTEs, or adversarial examples), which, by making small changes to the input, alter the DNN’s decision. We propose an unsupervised attack detector for ...
Comments