Abstract
Person re-identification is a hot topic due to its huge application potentials. Siamese network is a good method to learn feature representation in verification tasks and has been used in previous person re-identification research, but hard to convergence during training process. This paper presents a multi-task learning pipeline including Siamese loss for learning deep feature representations of people appearance. Firstly, we point out the defects of training a convolutional neural network (CNN) only with Siamese loss which is usually used for person re-identification. Secondly, a multi-task CNN for person re-identification combing the Softmax loss with Siameses loss is proposed. Finally, some experiments are carried out to test the performance of proposed multi-task person appearance learning pipeline. Experiments on various pedestrian dataset shows the effectiveness of our pipeline. Our method outperforms state-of-the-art person re-identification methods in some public datasets.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Alexander, H., Lucas, B., Bastian, L.: In defense of the triplet loss for person re-identification. arXiv preprint arXiv:1703.07737 (2017)
Li, W., Zhao, R., Xiao, T., Wang, X.: DeepReID: deep filter pairing neural network for person re-identification. In: 2014 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 152–159. IEEE Press, Columbus (2014)
Ahmed, E., Jones, M., Marks, T.K.: An improved deep learning architecture for person re-identification. In: 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 3908–3916. IEEE Press, Boston (2015)
Zagoruyko, S., Komodakis, N.: Learning to compare image patches via convolutional neural networks. 2015 In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 4353–4361. IEEE Press, Boston (2015)
Sergey, Z., Nikos, K.: MatchNet: unifying feature and metric learning for patch-based matching. In: 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 3279–3286. IEEE Press, Boston (2015)
Person Re-identification Results. http://www.ssig.dcc.ufmg.br/reid-results/
State of the art on the Market-1501 dataset. http://liangzheng.com.cn/Project/state_of_the_art_market1501.html
Yi, D., Lei, Z., Liao, S.C., Li, S.Z.L.: Deep metric learning for practical person re-identification. In: 22nd International Conference on Pattern Recognition, Stockholm, pp. 34–39 (2014)
Chen, S.Z., Guo, C.C., Lai, J.H.: Deep ranking for person re-identification via joint representation learning. Trans. Image Process. 25, 2353–2366 (2016)
Xiao, T., Li, H., Ouyang, W., Wang, X.: Learning deep feature representations with domain guided dropout for person re-identification. In: 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 1249–1258. IEEE Press, Las Vegas (2016)
Wu, S., Chen, Y.C., Li, X., Wu, A.C., You, J.J., Zheng, W.S.: An enhanced deep feature representation for person re-identification. In: 2016 IEEE Winter Conference on Applications of Computer Vision, pp. 1–8. IEEE Press, Waikoloa (2016)
Tetsu, M., Einoshin, S.: Person re-identification using CNN features learned from combination of attributes. In: 23rd International Conference on Pattern Recognition (ICPR), pp. 2428–2433. IEEE Press, Cancun (2016)
McLaughlin, N., Martinez del Rincon, J., Miller, P.: Recurrent convolutional network for video-based person re-identification. In: 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 1325–1334. IEEE Press, Las Vegas (2016)
Cheng, D., Gong, Y., Zhou, S.: Person re-identification by multi-channel parts-based CNN with improved triplet loss function. In: 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 1335–1344. IEEE Press, Las Vegas (2016)
Chen, W.H., Chen, X.T., Zhang, J.G., Huang, K.Q.: Beyond triplet loss: a deep quadruplet network for person re-identification. CoRR abs/1704.01719 (2017)
Xiao, T., Li, S., Wang, B.C., Lin, L., Wang, X.G.: Joint detection and identification feature learning for person search. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR). IEEE Press, Salt Lake City (2017)
Paisitkriangkrai, S., Shen, C., Hengel, A.V.D.: Learning to rank in person re-identification with metric ensembles. In: 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 1846–1855. IEEE Press, Boston (2015)
Li, W., Wang, X.: Locally aligned feature transforms across views. In: 2013 IEEE Conference on Computer Vision and Pattern Recognition, pp. 3594–3601. IEEE Press, Portland (2013)
Hirzer, M., Beleznai, C., Roth, P.M., Bischof, H.: Person re-identification by descriptive and discriminative classification. In: Heyden, A., Kahl, F. (eds.) SCIA 2011. LNCS, vol. 6688, pp. 91–102. Springer, Heidelberg (2011). doi:10.1007/978-3-642-21227-7_9
Gray, D., Brennan, S., Tao, H.: Evaluating appearance models for recognition, reacquisition, and tracking. In: 10th IEEE International Workshop on Performance Evaluation of Tracking and Surveillance (PETS), pp. 71–91 (2007)
Baltieri, D., Vezzani, R., Cucchiara, R.. 3DPeS: 3D people dataset for surveillance and forensics. In: 11th Proceedings of 2011 Joint ACM Workshop on Human Gesture and Behavior Understanding, pp. 59–64. ACM Press, New York (2011)
Zheng, W.S., Gong, S., Xiang, T.: Associating groups of people. In: British Machine Vision Conference (BMVC 2009), London, pp. 1–11 (2009)
Schwartz, W.R., Davis, L.S.: Learning discriminative appearance-based models using partial least squares. In: XXII Brazilian Symposium on Computer Graphics and Image Processing (SIBGRAPI 2009), Rio de Janeiro, pp. 322–329 (2009)
Chen, D.P., Yuan, Z.J., Chen, B.D., Zheng, N.N.: Similarity learning with spatial constraints for person re-identification. In: 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 1268–1277. IEEE Press, Las Vegas (2016)
Raphael, P., William, R.S.: Kernel cross-view collaborative representation based classification for person re-identification. In: 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). IEEE press, Las Vegas (2016)
Hermans, A., Beyer, L., Leibe, B.: In defense of the triplet loss for person re-identification. Arxiv (2017)
Zheng, J.W., Yang, P., Chen, S.Y., Shen, G.J., Wang, W.L.: Iterative re-constrained group sparse face recognition with adaptive weights learning. IEEE Trans. Image Process. 26, 2408–2423 (2017)
Chopra, S., Hadsell, R., Lecun, Y.: Learning a similarity metric discriminatively, with application to face verification. In: 2005 IEEE Computer Society Conference on Computer Vision & Pattern Recognition, vol. 1, pp. 539–546 (2005)
Norouzi, M., Fleet, D.J., Salakhutdinov, R.: Hamming distance metric learning. In: 2013 Neural Information Processing Systems, vol. 2, pp. 1061–1069 (2013)
Shen, F.M., Shen, C.H., Zhou, X., Yang, Y., Shen, H.T.: Face image classification by pooling raw features. Pattern Recogn. (PR) 54, 94–103 (2016)
Sun, Y., Chen, Y.H., Wang, X.G., Tang, X.O.: Deep learning face representation by joint identification-verification. In: NIPS 2014, pp. 1988–1996 (2014)
Ioffe, S., Szegedy, C.: Batch normalization: accelerating deep network training by reducing internal covariate shift. In: Computer Science 2015 (2015)
Kumar, V., Namboodiri, A.M., Paluri, M., Jawahar, C.V.: Pose-aware person recognition. CoRR (2017)
Szegedy, C., Vanhoucke, V., Ioffe, S., Shlens, J., Wojna, Z.: Rethinking the inception architecture for computer vision. In: 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 2818–2826. IEEE press, Las Vegas (2016)
Krizhevsky, A., Sutskever, I., Hinton, G.E.: ImageNet classification with deep convolutional neural networks. In: 2012 International Conference on Neural Information Processing Systems, vol. 25, pp. 1097–1105 (2012)
Ding, S., Lin, L., Wang, G., Chao, H.: Deep feature learning with relative distance comparison for person re-identification. Pattern Recogn. 48(10), 2993–3003 (2015)
Acknowledgements
A project supported by Scientific Research Fund of Zhejiang Provincial Education Department (Grant No. Y201534841); Supported by National Natural Science Foundation of China (Grant No. 61503338) and Natural Science Foundation of Zhejiang Province (Grant No. LQ15F030005).
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2017 Springer International Publishing AG
About this paper
Cite this paper
Gao, H., Yu, L., Huang, Y., Dong, Y., Chan, S. (2017). Multi-task Learning for Person Re-identification. In: Sun, Y., Lu, H., Zhang, L., Yang, J., Huang, H. (eds) Intelligence Science and Big Data Engineering. IScIDE 2017. Lecture Notes in Computer Science(), vol 10559. Springer, Cham. https://doi.org/10.1007/978-3-319-67777-4_23
Download citation
DOI: https://doi.org/10.1007/978-3-319-67777-4_23
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-67776-7
Online ISBN: 978-3-319-67777-4
eBook Packages: Computer ScienceComputer Science (R0)