Abstract
Person re-identification (Re-ID) aims to match a particular person captured by different cameras, which has great potential in video surveillance. However, Re-ID is still challenging due to occlusions, misalignment, background clutter, viewpoint changes, etc. To relieve these issues, this paper presents a multi-spectral channel attention network (MSCANet) to learn discriminative features for Re-ID. First, to better compress channels and explore the information left out by global average pooling (GAP), we employ multi-spectral channel attention (MSCA) to generalize the channel attention into the frequency domain. Second, to better capture more coarse and fine-grained clues, we design an improved attention pyramid (IAP) module which uses MSCA at the shallow level of the IAP to explore information lost by GAP so that more useful information can be introduced in attention learning. Sufficient experiments demonstrate the competitive performances of our MSCANet on the Market-1501 and DukeMTMC datasets. The mAP and Rank-1 accuracy of our model reach 89.3/95.8% and 80.2/89.9%, respectively
Similar content being viewed by others
Data availability
The original datasets have been published online. The datasets generated during and/or analyzed during the current study are available from the corresponding author on reasonable request
References
Zhang, Q., Lai, J., Feng, Z., Xie, X.: Seeing like a human: asynchronous learning with dynamic progressive refinement for person re-identification. IEEE Trans. Image Process. 31, 352–365 (2021)
Zhong, Y., Wang, Y., Zhang, S.: Progressive feature enhancement for person re-identification. IEEE Trans. Image Process. 30, 8384–8395 (2021)
He, S., Luo, H., Wang, P., Wang, F., Li, H., Jiang, W.: Transreid: transformer-based object re-identification. In: Proceedings of the IEEE/CVF international conference on computer vision, pp. 15013–15022 (2021)
Chen, G., Gu, T., Lu, J., Bao, J.-A., Zhou, J.: Person re-identification via attention pyramid. IEEE Trans. Image Process. 30, 7663–7676 (2021)
Wang, Y., Zhang, P., Gao, S., Geng, X., Lu, H., Wang, D.: Pyramid spatial-temporal aggregation for video-based person re-identification. In: Proceedings of the IEEE/CVF international conference on computer vision, pp. 12026–12035 (2021)
Zheng, F., Deng, C., Sun, X., Jiang, X., Guo, X., Yu, Z., Huang, F., Ji, R.: Pyramidal person re-identification via multi-loss dynamic training. In: Proceedings of the IEEE/cvf conference on computer vision and pattern recognition, pp. 8514–8522 (2019)
Hu, J., Shen, L., Sun, G.: Squeeze-and-excitation networks. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp. 7132–7141 (2018)
Qin, Z., Zhang, P., Wu, F., Li, X.: Fcanet: frequency channel attention networks. In: Proceedings of the IEEE/CVF international conference on computer vision, pp. 783–792 (2021)
Wang, Z., Jiang, J., Wu, Y., Ye, M., Bai, X., Satoh, S.: Learning sparse and identity-preserved hidden attributes for person re-identification. IEEE Trans. Image Process. 29, 2013–2025 (2019)
Zhao, Y., Shen, X., Jin, Z., Lu, H., Hua, X.-S.: Attribute-driven feature disentangling and temporal aggregation for video person re-identification. In: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pp. 4913–4922 (2019)
Zhou, K., Yang, Y., Cavallaro, A., Xiang, T.: Omni-scale feature learning for person re-identification. In: Proceedings of the IEEE/CVF international conference on computer vision, pp. 3702–3712 (2019)
He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp. 770–778 (2016)
Zhang, W., Ding, Q., Hu, J., Ma, Y., Lu, M.: Pixel-wise graph attention networks for person re-identification. In: Proceedings of the 29th ACM international conference on multimedia, pp. 5231–5238 (2021)
Ma, X., Guo, J., Sansom, A., McGuire, M., Kalaani, A., Chen, Q., Tang, S., Yang, Q., Fu, S.: Spatial pyramid attention for deep convolutional neural networks. IEEE Trans. Multimed. 23, 3048–3058 (2021)
Szegedy, C., Vanhoucke, V., Ioffe, S., Shlens, J., Wojna, Z.: Rethinking the inception architecture for computer vision. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp. 2818–2826 (2016)
Ye, M., Shen, J., Lin, G., Xiang, T., Shao, L., Hoi, S.C.: Deep learning for person re-identification: a survey and outlook. IEEE Trans. Patt. Anal. Mach. Intell. 44(6), 2872–2893 (2021)
Zheng, L., Shen, L., Tian, L., Wang, S., Wang, J., Tian, Q.: Scalable person re-identification: A benchmark. In: Proceedings of the IEEE international conference on computer vision, pp. 1116–1124 (2015)
Ristani, E., Solera, F., Zou, R., Cucchiara, R., Tomasi, C.: Performance measures and a data set for multi-target, multi-camera tracking. In: Proceedings of the European conference on computer vision, pp. 17–35 (2016)
Deng, J., Dong, W., Socher, R., Li, L.-J., Li, K., Fei-Fei, L.: Imagenet: A large-scale hierarchical image database. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp. 248–255 (2009)
Gu, H., Li, J., Fu, G., Yue, M., Zhu, J.: Loss function search for person re-identification. Patt. Recogn. 124, 108432 (2022)
Dosovitskiy, A., Beyer, L., Kolesnikov, A., Weissenborn, D., Zhai, X., Unterthiner, T., Dehghani, M., Minderer, M., Heigold, G., Gelly, S., Uszkoreit, J., Houlsby, N.: An image is worth 16x16 words: Transformers for image recognition at scale. In: Proceedings of the international conference on learning representations (2021)
Zhang, Z., Lan, C., Zeng, W., Jin, X., Chen, Z.: Relation-aware global attention for person re-identification. In: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pp. 3186–3195 (2020)
Zhao, S., Gao, C., Zhang, J., Cheng, H., Han, C., Jiang, X., Guo, X., Zheng, W.-S., Sang, N., Sun, X.: Do not disturb me: Person re-identification under the interference of other pedestrians. In: Proceedings of the European conference on computer vision, pp. 647–663 (2020)
Zhu, K., Guo, H., Liu, Z., Tang, M., Wang, J.: Identity-guided human semantic parsing for person re-identification. In: Proceedings of the European conference on computer vision, pp. 346–363 (2020)
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: Proceedings of the IEEE/cvf conference on computer vision and pattern recognition, pp. 598–607 (2021)
Zhang, X., Hou, M., Deng, X., Feng, Z.: Multi-cascaded attention and overlapping part features network for person re-identification. Sign. Image Video Process. 16(6), 1525–1532 (2022)
Guo, C., Zhao, X., Zou, Q.: Relation network based on multi-granular hypergraphs for person re-identification. Appl. Intell. 52(10), 11394–11406 (2022)
Wang, Z., Zhu, F., Tang, S., Zhao, R., He, L., Song, J.: Feature erasing and diffusion network for occluded person re-identification. In: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pp. 4754–4763 (2022)
Gu, H., Li, J., Fu, G., Wong, C., Chen, X., Zhu, J.: Autoloss-gms: Searching generalized margin-based softmax loss function for person re-identification. In: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pp. 4744–4753 (2022)
Wu, G., Zhu, X., Gong, S.: Learning hybrid ranking representation for person re-identification. Patt. Recogn. 121, 108239 (2022)
Selvaraju, R.R., Cogswell, M., Das, A., Vedantam, R., Parikh, D., Batra, D.: Grad-cam: Visual explanations from deep networks via gradient-based localization. In: Proceedings of the IEEE international conference on computer vision, pp. 618–626 (2017)
Acknowledgements
This work was partly supported by the National Natural Science Foundation of China (No. 62102320) and the Fundamental Research Funds for the Central Universities (No. D5000210737)
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Conflict of interest
The authors have no relevant financial or non-financial interests to disclose
Ethics approval
This article does not contain any studies with human participants performed by any of the authors
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
About this article
Cite this article
Duan, Q., Hu, Z., Lu, M. et al. Learning discriminative features for person re-identification via multi-spectral channel attention. SIViP 17, 3019–3026 (2023). https://doi.org/10.1007/s11760-023-02522-1
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11760-023-02522-1