Abstract
Previous relation-based losses in person re-identification (ReID) typically comprise two sequential steps: they firstly sample both positive pair and negative pair and then deploy constraints to simultaneously improve intra-identity compactness and inter-identity separability. However, existing relation-based losses usually place emphasis on exploring the relation between images and therefore consider only several pairs during each optimization. This inevitably leads to different convergence status for pairs of the same kind and brings about the intra-pair variance problem. Accordingly, we propose a novel Relation-Aware (RA) loss to address the intra-pair variance via exploring the informative relation across pairs. In brief, we introduce a macro-constraint and a micro-constraint. The macro-constraint encourages the separation of positive pair and negative pair via pushing far apart the two “centers” of the positive pair and the negative pair. The “center” of each kind of pair are obtained via averaging all the pairs of the same kind. The micro-constraint further enhances the compactness by minimizing the discrepancies among pairs of the same kind. The two constraints work cooperatively to relieve the intra-pair variance and improve the quality of pedestriansąŕ representation. Results of extensive experiments on three widely used ReID benchmarks, i.e., Market-1501, DukeMTMC-ReID and CUHK03, demonstrate that the RA loss brings improvements over existing relation-based losses.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Notes
- 1.
In this paper, the distance of one pair denotes the distance between the two pedestrian images contained in this pair. In comparison, the distance between two pairs indicates the difference value in the two distances of the two pairs.
References
Carvalho, M., Cadene, R., Picard, D., Soulier, L., Thome, N., Cord, M.: Cross-modal retrieval in the cooking context: learning semantic text-image embeddings. In: The 41st International ACM SIGIR Conference on Research & Development in Information Retrieval, pp. 35–44 (2018)
Chen, B., Deng, W., Hu, J.: Mixed high-order attention network for person re-identification. In: ICCV, pp. 371–381 (2019)
Chen, T., et al.: Abd-net: attentive but diverse person re-identification. In: ICCV, pp. 8350–8360 (2019)
Chen, W., Chen, X., Zhang, J., Huang, K.: Beyond triplet loss: a deep quadruplet network for person re-identification. In: CVPR, pp. 403–412 (2017)
Chen, X., et al.: Salience-guided cascaded suppression network for person re-identification. In: CVPR, pp. 3300–3310 (2020)
Chopra, S., Hadsell, R., LeCun, Y.: Learning a similarity metric discriminatively, with application to face verification. In: CVPR, vol. 1, pp. 539–546 (2005)
Dai, Z., Chen, M., Gu, X., Zhu, S., Tan, P.: Batch dropblock network for person re-identification and beyond. In: ICCV, pp. 3690–3700 (2019)
Ding, C., Wang, K., Wang, P., Tao, D.: Multi-task learning with coarse priors for robust part-aware person re-identification. IEEE Trans. Pattern Anal. Mach. Intell. 44, 1474–1488 (2020)
Fang, P., Zhou, J., Roy, S.K., Petersson, L., Harandi, M.: Bilinear attention networks for person retrieval. In: ICCV, pp. 8029–8038 (2019)
Fu, Y., et al.: Horizontal pyramid matching for person re-identification. In: AAAI, pp. 8295–8302 (2019)
Gu, X., Ma, B., Chang, H., Shan, S., Chen, X.: Temporal knowledge propagation for image-to-video person re-identification. In: ICCV, pp. 9647–9656 (2019)
Guo, J., Yuan, Y., Huang, L., Zhang, C., Yao, J.G., Han, K.: Beyond human parts: dual part-aligned representations for person re-identification. In: ICCV, pp. 3641–3650 (2019)
Hadsell, R., Chopra, S., LeCun, Y.: Dimensionality reduction by learning an invariant mapping. In: CVPR, vol. 2, pp. 1735–1742 (2006)
He, L., Wang, Y., Liu, W., Zhao, H., Sun, Z., Feng, J.: Foreground-aware pyramid reconstruction for alignment-free occluded person re-identification. In: ICCV, pp. 8449–8458 (2019)
He, S., Luo, H., Wang, P., Wang, F., Li, H., Jiang, W.: Transreid: transformer-based object re-identification. In: ICCV, pp. 15013–15022 (2021)
Hermans, A., Beyer, L., Leibe, B.: In defense of the triplet loss for person re-identification. arXiv preprint arXiv:1703.07737 (2017)
Hou, R., Ma, B., Chang, H., Gu, X., Shan, S., Chen, X.: Interaction-and-aggregation network for person re-identification. In: CVPR, pp. 9317–9326 (2019)
Hou, R., Ma, B., Chang, H., Gu, X., Shan, S., Chen, X.: Vrstc: occlusion-free video person re-identification. In: CVPR, pp. 7183–7192 (2019)
Kalayeh, M.M., Basaran, E., Gökmen, M., Kamasak, M.E., Shah, M.: Human semantic parsing for person re-identification. In: CVPR, pp. 1062–1071 (2018)
Kim, S., Kim, D., Cho, M., Kwak, S.: Proxy anchor loss for deep metric learning. In: CVPR, pp. 3238–3247 (2020)
Li, J., Zhang, S., Tian, Q., Wang, M., Gao, W.: Pose-guided representation learning for person re-identification. IEEE Trans. Pattern Anal. Mach. Intell. 44, 622–635 (2019)
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)
Luo, C., Chen, Y., Wang, N., Zhang, Z.: Spectral feature transformation for person re-identification. In: ICCV, pp. 4975–4984 (2019)
Maaten, L.V.D., Hinton, G.: Visualizing data using t-sne. JMLR 9, 2579–2605 (2008)
Miao, J., Wu, Y., Liu, P., Ding, Y., Yang, Y.: Pose-guided feature alignment for occluded person re-identification. In: ICCV, pp. 542–551 (2019)
Nguyen, B., De Baets, B.: Kernel distance metric learning using pairwise constraints for person re-identification. IEEE Trans. Image Process. 28(2), 589–600 (2019)
Qian, X., Fu, Y., Xiang, T., Jiang, Y.G., Xue, X.: Leader-based multi-scale attention deep architecture for person re-identification. IEEE Trans. Pattern Anal. Mach. Intell. 42(2), 371–385 (2020)
Quan, R., Dong, X., Wu, Y., Zhu, L., Yang, Y.: Auto-reid: searching for a part-aware convnet for person re-identification. In: ICCV, pp. 3749–3758 (2019)
Saquib Sarfraz, M., Schumann, A., Eberle, A., Stiefelhagen, R.: A pose-sensitive embedding for person re-identification with expanded cross neighborhood re-ranking. In: CVPR, pp. 420–429 (2018)
Schroff, F., Kalenichenko, D., Philbin, J.: Facenet: a unified embedding for face recognition and clustering. In: CVPR, pp. 815–823 (2015)
Si, J., et al.: Dual attention matching network for context-aware feature sequence based person re-identification. In: CVPR, pp. 5363–5372 (2018)
Sohn, K.: Improved deep metric learning with multi-class n-pair loss objective. In: NIPS, vol. 29 (2016)
Suh, Y., Wang, J., Tang, S., Mei, T., Lee, K.M.: Part-aligned bilinear representations for person re-identification. In: ECCV, pp. 402–419 (2018)
Sun, Y., et al.: Circle loss: a unified perspective of pair similarity optimization. In: CVPR, pp. 6398–6407 (2020)
Sun, Y., Zheng, L., Deng, W., Wang, S.: Svdnet for pedestrian retrieval. In: ICCV, pp. 3800–3808 (2017)
Sun, Y., Zheng, L., Li, Y., Yang, Y., Tian, Q., Wang, S.: Learning part-based convolutional features for person re-identification. IEEE Trans. Pattern Anal. Mach. Intell. 43, 902–917 (2019)
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)
Sutskever, I., Martens, J., Dahl, G.E., Hinton, G.E.: On the importance of initialization and momentum in deep learning. In: ICML, pp. 1139–1147 (2013)
Tang, Z., Huang, J.: Branch interaction network for person re-identification. In: ACCV (2020)
Tang, Z., Huang, J.: Harmonious multi-branch network for person re-identification with harder triplet loss. ACM Trans. Multimedia Comput. Commun. Appl. 18(4), 1–21 (2022)
Tao, D., Guo, Y., Yu, B., Pang, J., Yu, Z.: Deep multi-view feature learning for person re-identification. IEEE Trans. Circ. Syst. Video Technol. 28(10), 2657–2666 (2017)
Wang, G., Yuan, Y., Chen, X., Li, J., Zhou, X.: Learning discriminative features with multiple granularities for person re-identification. In: ACM MM, pp. 274–282 (2018)
Wang, H., Shen, J., Yongtuo, L., Gao, Y., Gavves, E.: Nformer: robust person re-identification with neighbor transformer. In: CVPR, pp. 7297–7307 (2022)
Wang, K., Ding, C., Maybank, S.J., Tao, D.: CDPM: convolutional deformable part models for semantically aligned person re-identification. IEEE Trans. Image Process. 29, 3416–3428 (2020)
Wang, K., Ding, C., Pang, J., Xu, X.: Context sensing attention network for video-based person re-identification. arXiv preprint arXiv:2207.02631 (2022)
Wang, K., Wang, P., Ding, C., Tao, D.: Batch coherence-driven network for part-aware person re-identification. IEEE Trans. Image Process. 30, 3405–3418 (2021)
Wang, L., Fan, B., Guo, Z., Zhao, Y., Zhang, R., Li, R., Gong, W.: Dense-scale feature learning in person re-identification. In: ACCV (2020)
Wang, P., Ding, C., Shao, Z., Hong, Z., Zhang, S., Tao, D.: Quality-aware part models for occluded person re-identification. IEEE Trans. Multimedia (2022)
Wang, P., Ding, C., Tan, W., Gong, M., Jia, K., Tao, D.: Uncertainty-aware clustering for unsupervised domain adaptive object re-identification. IEEE Trans. Multimedia (2022)
Wen, Y., Zhang, K., Li, Z., Qiao, Yu.: A discriminative feature learning approach for deep face recognition. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9911, pp. 499–515. Springer, Cham (2016). https://doi.org/10.1007/978-3-319-46478-7_31
Wen, Y., Zhang, K., Li, Z., Qiao, Y.: A comprehensive study on center loss for deep face recognition. IJCV 127(6), 668–683 (2019)
Xia, B.N., Gong, Y., Zhang, Y., Poellabauer, C.: Second-order non-local attention networks for person re-identification. In: ICCV, pp. 3759–3768 (2019)
Yao, H., Zhang, S., Hong, R., Zhang, Y., Xu, C., Tian, Q.: Deep representation learning with part loss for person re-identification. IEEE Trans. Image Process. 28(6), 2860–2871 (2019)
Yu, B., Tao, D.: Deep metric learning with tuplet margin loss. In: ICCV, pp. 6490–6499 (2019)
Zhang, A., Gao, Y., Niu, Y., Liu, W., Zhou, Y.: Coarse-to-fine person re-identification with auxiliary-domain classification and second-order information bottleneck. In: CVPR, pp. 598–607 (2021)
Zhang, Z., Lan, C., Zeng, W., Chen, Z.: Densely semantically aligned person re-identification. In: CVPR, pp. 667–676 (2019)
Zhao, L., Li, X., Zhuang, Y., Wang, J.: Deeply-learned part-aligned representations for person re-identification. In: ICCV, pp. 3219–3228 (2017)
Zheng, L., Huang, Y., Lu, H., Yang, Y.: Pose invariant embedding for deep person re-identification. IEEE Trans. Image Process. 28(9), 4500–4509 (2019)
Zheng, L., Shen, L., Tian, L., Wang, S., Wang, J., Tian, Q.: Scalable person re-identification: a benchmark. In: ICCV, pp. 1116–1124 (2015)
Zheng, L., Zhang, H., Sun, S., Chandraker, M., Yang, Y., Tian, Q.: Person re-identification in the wild. In: ICCV, pp. 1367–1376 (2017)
Zheng, M., Karanam, S., Wu, Z., Radke, R.J.: Re-identification with consistent attentive siamese networks. In: CVPR, pp. 5735–5744 (2019)
Zheng, Z., Zheng, L., Yang, Y.: A discriminatively learned CNN embedding for person reidentification. ACM Trans. Multimedia Comput. Commun. Appl. 14(1), 1–20 (2017)
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)
Zhong, Z., Zheng, L., Cao, D., Li, S.: Re-ranking person re-identification with k-reciprocal encoding. In: CVPR, pp. 1318–1327 (2017)
Zhong, Z., Zheng, L., Kang, G., Li, S., Yang, Y.: Random erasing data augmentation, pp. 13001–13008 (2020)
Zhou, K., Yang, Y., Cavallaro, A., Xiang, T.: Omni-scale feature learning for person re-identification. In: ICCV, pp. 3701–3711 (2019)
Zhou, S., Wang, F., Huang, Z., Wang, J.: Discriminative feature learning with consistent attention regularization for person re-identification. In: ICCV, pp. 8039–8048 (2019)
Zhu, H., Ke, W., Li, D., Liu, J., Tian, L., Shan, Y.: Dual cross-attention learning for fine-grained visual categorization and object re-identification. In: CVPR, pp. 4692–4702 (2022)
Zhu, K., Guo, H., Liu, Z., Tang, M., Wang, J.: Identity-guided human semantic parsing for person re-identification. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12348, pp. 346–363. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-58580-8_21
Zhu, K., et al.: Aaformer: auto-aligned transformer for person re-identification. arXiv preprint arXiv:2104.00921 (2021)
Acknowledgements
This research is supported by the National Natural Science Foundation of China (U2013601), and Key-Area Research and Development Program of Guangdong Province, China (2019B010154003), and the Program of Guangdong Provincial Key Laboratory of Robot Localization and Navigation Technology (2020B121202011), and the Natural Science Foundation of China (U21A20487), and Shenzhen Technology Project (JCYJ20180507182610734, KCXFZ20201221173411032, Y795001001), and CAS Key Technology Talent Program, and Guangdong Technology Project (No. 2016B010125003).
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Wang, K., Hu, S., Cheng, J., Cheng, J., Pang, J., Tan, H. (2023). RA Loss: Relation-Aware Loss for Robust Person Re-identification. In: Wang, L., Gall, J., Chin, TJ., Sato, I., Chellappa, R. (eds) Computer Vision – ACCV 2022. ACCV 2022. Lecture Notes in Computer Science, vol 13842. Springer, Cham. https://doi.org/10.1007/978-3-031-26284-5_23
Download citation
DOI: https://doi.org/10.1007/978-3-031-26284-5_23
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-26283-8
Online ISBN: 978-3-031-26284-5
eBook Packages: Computer ScienceComputer Science (R0)