ABSTRACT
In person re-identification (re-ID), most state-of-the-art models extract features by convolutional neural networks to do similarity comparison. Feature representation becomes the key task for person re-ID. However, the learned features are not good enough based on a single-path and single-loss network because the learned objective only achieves one of the multiple minima. To improve feature representation, we propose a multi-path and multi-loss network (MPMLN) and concatenate multi-path features to represent pedestrian. Subsequently, we design MPMLN based on ResNet-50 and construct an end-to-end architecture. The backbone of our proposed network shares the local parameters for multiple paths and multiple losses. It has fewer parameters than multiple independent networks. Experimental results show that our MPMLN achieves the state-of-the-art performance on the public Market1501, DukeMTMC-reID and CUHK03 person re-ID benchmarks.
- Zheng, L., Yang, Y., and Hauptmann, A. G. 2016. Person re-identification: Past, present and future. CoRR, abs/1610.02984. DOI= http://arxiv.org/abs/1610.02984Google Scholar
- Shi, H., Yang, Y., Zhu, X., Liao, S., Lei, Z., Zheng, W., and Li, S. Z. 2016. Embedding deep metric for person re-identification: A study against large variations. In Computer Vision -- ECCV 2016 14th European Conference, (Amsterdam, The Nether-lands, October 11--14, 2016), Proceedings, Part I, pages 732--748.Google Scholar
- Zheng, Z., Zheng, L., and Yang, Y. 2016. A discriminatively learned CNN embedding for person re-identification. CoRR, abs/1611.05666. DOI= http://arxiv.org/abs/1611.05666Google Scholar
- Wang, J., Li, Y., and Miao, Z. 2017. Siamese cosine network embedding for person re-identification. In Computer Vision -- Second CCF Chinese Conference, CCCV 2017, (Tianjin, China, October 11--14, 2017), Proceedings, Part III, pages 352--362.Google Scholar
- Zeiler, M. D. and Fergus, R. 2014. Visualizing and understanding convolutional networks. In Computer Vision - ECCV 2014 13th European Conference, (Zurich, Switzerland, September 6--12, 2014), Proceedings, Part I, pages 818--833.Google Scholar
- Keskar, N. S., Mudigere, D., Nocedal, J., Smelyanskiy, M., and Tang, P. T. P. 2016. On large-batch training for deep learning: Generalization gap and sharp minima. CoRR, abs/1609.04836. DOI= http://arxiv.org/abs/1609.04836Google Scholar
- Wen, W., Wang, Y., Yan, F., Xu, C., Chen, Y., and Li, H. 2018. Smoothout: Smoothing out sharp minima for generalization in large-batch deep learning. CoRR, abs/1805.07898. DOI= http://arxiv.org/abs/1805.07898Google Scholar
- Zhang, Y., Xiang, T., Hospedales, T. M., and Lu, H. 2017. Deep mutual learning. CoRR, abs/1706.00384. DOI= http://arxiv.org/abs/1706.00384Google Scholar
- He, K., Zhang, X., Ren, S., and Sun, J. 2015. Delving deep into rectifiers: Surpassing human-level performance on imagenet classification. In 2015 IEEE International Conference on Computer Vision, ICCV 2015, (Santiago, Chile, December 7-13, 2015), pages 1026--1034. Google ScholarDigital Library
- Krizhevsky, A., Sutskever, I., and Hinton, G. E. 2012. Imagenet classification with deep convolutional neural networks. In Advances in Neural Information Processing Systems 25: 26th Annual Conference on Neural Information Processing Systems 2012. Proceedings of a meeting held December 3-6, 2012, Lake Tahoe, Nevada, United States., pages 1106--1114. DOI= http://papers.nips.cc/paper/4824-imagenet-classification-with-deep-convolutional-neural-networks Google ScholarDigital Library
- Simonyan, K. and Zisserman, A. 2014. Very deep convolutional networks for large-scale image recognition. CoRR, abs/1409.1556. DOI= http://arxiv.org/abs/1409.1556Google Scholar
- Szegedy, C., Liu, W., Jia, Y., Sermanet, P., Reed, S. E., Anguelov, D., Erhan, D., Vanhoucke, V., and Rabinovich, A. 2015. Going deeper with convolutions. In IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2015, (Boston, MA, USA, June 7-12, 2015), pages 1--9.Google ScholarCross Ref
- Larsson, G., Maire, M., and Shakhnarovich, G. 2016. Fractal net: Ultra-deep neural networks without residuals. CoRR, abs/1605.07648. DOI= http://arxiv.org/abs/1605.07648Google Scholar
- Zhong, Z., Zheng, L., Kang, G., Li, S., and Yang, Y. 2017. Random erasing data augmentation. CoRR, abs/1708.04896. DOI= http://arxiv.org/abs/1708.04896Google Scholar
- Zheng, L., Shen, L., Tian, L., Wang, S., Wang, J., and Tian, Q. 2015. Scalable person re-identification: A benchmark. In 2015 IEEE International Conference on Computer Vision, ICCV 2015, (Santiago, Chile, December 7-13, 2015), pages 1116--1124. Google ScholarDigital Library
- Zheng, Z., Zheng, L., and Yang, Y. 2017. Unlabeled samples generated by GAN improve the person re-identification baseline in vitro. In IEEE International Conference on Computer Vision, ICCV 2017, (Venice, Italy, October 22-29, 2017), pages 3774--3782.Google ScholarCross Ref
- Li, W., Zhao, R., Xiao, T., and Wang, X. 2014. Deepreid: Deep filter pairing neural network for person re-identification. In 2014 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2014, (Columbus, OH, USA, June 23-28, 2014), pages 152--159. Google ScholarDigital Library
- Felzenszwalb, P. F., Girshick, R. B., McAllester, D. A., and Ramanan, D. 2010. Object detection with discriminatively trained part-based models. IEEE Trans. Pattern Anal. Mach. Intell., 32(9):1627--1645. Google ScholarDigital Library
- Zhong, Z., Zheng, L., Cao, D., and Li, S. 2017. Re-ranking person re-identification with k-reciprocal encoding. In 2017 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2017, (Honolulu, HI, USA, July 21-26, 2017), pages 3652--3661.Google ScholarCross Ref
- Zheng, Z., Zheng, L., and Yang, Y. 2017. Pedestrian alignment network for large-scale person re-identification. CoRR, abs/1707.00408. DOI= http://arxiv.org/abs/1707.00408Google Scholar
- Sun, Y., Zheng, L., Deng, W., and Wang, S. 2017. Svdnet for pedestrian retrieval. In IEEE International Conference on Computer Vision, ICCV 2017, (Venice, Italy, October 22-29, 2017), pages 3820--3828.Google ScholarCross Ref
- Hermans, A., Beyer, L., and Leibe, B. 2017. In defense of the triplet loss for person re-identification. CoRR, abs/1703.07737. DOI= http://arxiv.org/abs/1703.07737Google Scholar
- Wang, Y., Wang, L., You, Y., Zou, X., Chen, V., Li, S., Huang, G., Hariharan, B., and Weinberger, K. Q. 2018. Resource aware person re-identification across multiple resolutions. CoRR, abs/1805.08805. DOI= http://arxiv.org/abs/1805.08805Google Scholar
- Chang, X., Hospedales, T. M., and Xiang, T. 2018. Multi-level factorisation net for person re-identification. CoRR, abs/1803.09132. DOI= http://arxiv.org/abs/1803.09132Google Scholar
- Li, W., Zhu, X., and Gong, S. 2018. Harmonious attention network for person re-identification. CoRR, abs/1802.08122. DOI= http://arxiv.org/abs/1802.08122Google Scholar
- Jin, H., Wang, X., Liao, S., and Li, S. Z. 2017. Deep person re-identification with improved embedding and efficient training. In 2017 IEEE International Joint Conference on Biometrics, IJCB 2017, (Denver, CO, USA, October 1-4, 2017), pages 261--267.Google ScholarCross Ref
- Sun, Y., Zheng, L., Yang, Y., Tian, Q., and Wang, S. 2017. Beyond part models: Person retrieval with refined part pooling. CoRR, abs/1711.09349. DOI= http://arxiv.org/abs/1711.09349Google Scholar
Index Terms
- Multi-Path and Multi-Loss Network for Person Re-Identification
Recommendations
Multi-view feature fusion for person re-identification
AbstractPerson re-identification (ReID) suffers from camera view variants. Existing works, which typically learn a feature for each image, share a limitation that the learned features are single-view: each feature only contains information in ...
Highlights- The complementary-view features are defined to mitigate view bias.
- Multi-view ...
Graphical abstractDisplay Omitted
Person re-identification based on multi-scale feature learning
AbstractExtracting discriminative pedestrian features is an effective method in person re-identification. Most person re-identification works focus on extracting abstract features from the high-layer of the network, but ignore the middle-layer ...
Video-based person re-identification using a novel feature extraction and fusion technique
AbstractPerson re-identification has received extensive attention in the academic community. In this paper, a novel multiple feature fusion network (MPFF-Net) is proposed for video-based person re-identification. The proposed network is used to obtain the ...
Comments