Abstract
Contrastive loss based deep metric learning has been generally used in video-based person re-identification, which learns a metric by preserving the distance between positive sample pairs close and negative sample pairs far on the embedding space. Yet contrastive loss still suffers not only from “hard” negative examples loosely defined by a hard margin, but also from severe sampling imbalance caused by equal sampling technique. To address these defeats, this paper presents a novel loss called Long-Tailed Contrastive Loss (LTCL). A Gaussian kernel function is used as the negative loss term, which takes into account the effect of long-range negative sample pairs. Meanwhile, a focusing factor is introduced for adaptive hard negative data mining and a rebalancing factor is used to compensate the sampling imbalance. Experiments conducted on two classic datasets demonstrate the effectiveness of the proposed method.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Bar-Hillel, A., Hertz, T., Shental, N., Weinshall, D.: Learning a mahalanobis metric from equivalence constraints. J. Mach. Learn. Res. 6(6), 937–965 (2005)
Boulgouris, N.V., Hatzinakos, D., Plataniotis, K.N.: Gait recognition: a challenging signal processing technology for biometric identification. IEEE Sig. Process. Mag. 22(6), 78–90 (2005)
Chung, D., Tahboub, K., Delp, E.J.: A two stream Siamese convolutional neural network for person re-identification. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1983–1991 (2017)
Ding, S., Lin, L., Wang, G., Chao, H.: Deep feature learning with relative distance comparison for person re-identification. Pattern Recognit. 48(10), 2993–3003 (2015)
Dong, S.C., Cristani, M., Stoppa, M., Bazzani, L., Murino, V.: Custom pictorial structures for re-identification, pp. 68.1–68.11 (2011)
Farenzena, M., Bazzani, L., Perina, A., Murino, V., Cristani, M.: Person re-identification by symmetry-driven accumulation of local features. In: Computer Vision and Pattern Recognition, pp. 2360–2367 (2010)
Hadsell, R., Chopra, S., Lecun, Y.: Dimensionality reduction by learning an invariant mapping. In: IEEE Computer Society Conference on Computer Vision and Pattern Recognition, pp. 1735–1742 (2006)
Hirzer, M., Roth, P.M., Kstinger, M., Bischof, H.: Relaxed pairwise learned metric for person re-identification. In: European Conference on Computer Vision, pp. 780–793 (2012)
Karaman, S., Bagdanov, A.D.: Identity inference: generalizing person re-identification scenarios. In: Fusiello, A., Murino, V., Cucchiara, R. (eds.) ECCV 2012. LNCS, vol. 7583, pp. 443–452. Springer, Heidelberg (2012). https://doi.org/10.1007/978-3-642-33863-2_44
Karanam, S., Li, Y., Radke, R.J.: Person re-identification with discriminatively trained viewpoint invariant dictionaries. In: IEEE International Conference on Computer Vision, pp. 4516–4524 (2015)
Klaser, A., Marszałek, M., Schmid, C.: A spatio-temporal descriptor based on 3D-gradients. In: 19th British Machine Vision Conference BMVC 2008, p. 275-1. British Machine Vision Association (2008)
Kviatkovsky, I., Adam, A., Rivlin, E.: Color invariants for person reidentification. IEEE Trans. Pattern Anal. Mach. Intell. 35(7), 1622–34 (2013)
Li, Y., Wu, Z., Karanam, S., Radke, R.J.: Multi-shot human re-identification using adaptive fisher discriminant analysis. In: British Machine Vision Conference, pp. 73.1–73.12 (2015)
Lin, T.Y., Goyal, P., Girshick, R., He, K., Dollr, P.: Focal loss for dense object detection (2017)
Liu, K., Ma, B., Zhang, W., Huang, R.: A spatio-temporal appearance representation for video-based pedestrian re-identification. In: IEEE International Conference on Computer Vision, pp. 3810–3818 (2015)
Lowe, D.G.: Similarity metric learning for a variable-kernel classifier. Neural Comput. 7(1), 72–85 (1995)
Ma, B., Su, Y., Jurie, F.: Local descriptors encoded by fisher vectors for person re-identification. In: Fusiello, A., Murino, V., Cucchiara, R. (eds.) ECCV 2012. LNCS, vol. 7583, pp. 413–422. Springer, Heidelberg (2012). https://doi.org/10.1007/978-3-642-33863-2_41
Mclaughlin, N., Rincon, J.M.D., Miller, P.: Recurrent convolutional network for video-based person re-identification. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 1325–1334 (2016)
Sohn, K.: Improved deep metric learning with multi-class n-pair loss objective. In: Advances in Neural Information Processing Systems, pp. 1857–1865 (2016)
Wang, T., Gong, S., Zhu, X., Wang, S.: Person re-identification by video ranking. In: European Conference on Computer Vision, pp. 688–703 (2014)
Wang, X., Doretto, G., Sebastian, T., Rittscher, J.: Shape and appearance context modeling. In: IEEE International Conference on Computer Vision, pp. 1–8 (2007)
Weinberger, K.Q., Saul, L.K.: Distance metric learning for large margin nearest neighbor classification. J. Mach. Learn. Res. 10(1), 207–244 (2009)
Xu, S., Cheng, Y., Gu, K., Yang, Y., Chang, S., Zhou, P.: Jointly attentive spatial-temporal pooling networks for video-based person re-identification (2017)
Yan, Y., Ni, B., Song, Z., Ma, C., Yan, Y., Yang, X.: Person re-identification via recurrent feature aggregation. In: European Conference on Computer Vision, pp. 701–716 (2016)
Yi, D., Lei, Z., Li, S.Z.: Deep metric learning for practical person re-identification, pp. 34–39. Computer Science (2014)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2019 Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Bao, L. (2019). Long-Tailed Contrastive Loss for Video-Based Person Re-identification. In: Wang, Y., Huang, Q., Peng, Y. (eds) Image and Graphics Technologies and Applications. IGTA 2019. Communications in Computer and Information Science, vol 1043. Springer, Singapore. https://doi.org/10.1007/978-981-13-9917-6_51
Download citation
DOI: https://doi.org/10.1007/978-981-13-9917-6_51
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-13-9916-9
Online ISBN: 978-981-13-9917-6
eBook Packages: Computer ScienceComputer Science (R0)