Interpretable Attention Part Model for Person Re-identification

被引：0
作者：
Zhou Y. [1 ,2 ]
Wang H.-Z. [1 ,2 ]
Zhao J.-Q. [1 ,2 ]
Chen Y. [1 ,2 ]
Yao R. [1 ,2 ]
Chen S.-L. [1 ,2 ]
机构：
[1] School of Computer Science and Technology, China University of Mining and Technology, Xuzhou
[2] Engineering Research Center of Mine Digitization of Ministry of Education, Xuzhou
来源：
Zidonghua Xuebao/Acta Automatica Sinica | 2023年 / 49卷 / 10期
基金：
中国国家自然科学基金;
关键词：
attention mechanism; interpretable deep learning; part model; Person re-identification (ReID);
D O I：
10.16383/j.aas.c200493
中图分类号：
学科分类号：
摘要：
Most person re-identification (ReID) methods only use the attention mechanism as an auxiliary method to extract salient features, and lack of quantitative research on the attention degree of person images on the network. Based on this, this paper proposes an interpretable attention part model (IAPM). The model has three advantages: 1) Using the attention mask to extract component features for solving the problem of component misalignment; 2) To generate interpretable weights based on the significance of the components, we devise the interpretable weight generation module (IWM); 3) Salient part triple loss (SPTL) for IWM is proposed to further improve recognition accuracy and interpretability. A series of experiments are carried out on three mainstream datasets, and demonstrate that our method is superior to the state-of-the-art methods. Finally, a crowd subjective test is used to compare the relative size of the interpretable weights generated by IWM and human intuitive judgment scores, which proves that the method has good interpretability. © 2023 Science Press. All rights reserved.
引用
收藏
页码：2159 / 2171
页数：12
相关论文
共 46 条
  • [1] Yi D, Lei Z, Liao S C, Li S Z., Deep metric learning for person reidentification, Proceedings of the 22nd IEEE International Conference on Pattern Recognition, pp. 34-39, (2014)
  • [2] Liao S C, Hu Y, Zhu X Y, Li S Z., Person re-identification by local maximal occurrence representation and metric learning, Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2197-2206, (2015)
  • [3] Luo Hao, Jiang Wei, Fan Xing, Zhang Si-Peng, A survey on deep learning based person re-identification, Acta Automatica Sinica, 45, 11, pp. 2032-2049, (2019)
  • [4] Rumelhart D E, Hinton G E, Williams R J., Learning representations by back-propagating errors, Nature, 323, 6088, (1986)
  • [5] Wu Fei, Liao Bin-Bing, Han Ya-Hong, Interpretability for deep learning, Aero Weaponry, 26, 1, pp. 43-50, (2019)
  • [6] Chen W H, Chen X T, Zhang J G, Huang K Q., A multi-task deep network for person re-identification, Proceedings of the 31st Conference on Artificial Intelligence, pp. 3988-3994, (2017)
  • [7] Sun Y G, Zheng L, Yang Y, Tian Q, Wang S J., Beyond part models: Person retrieval with refined part pooling (and a strong convolutional baseline), Proceedings of the European Conference on Computer Vision, pp. 480-496, (2018)
  • [8] Zhou S P, Wang J J, Wang J Y, Gong Y H, Zheng N N., Point to set similarity based deep feature learning for person re-identification, Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 5028-5037, (2017)
  • [9] Sarfraz M S, Schumann A, Eberle A, Stiefelhagen R., A posepensitive embedding for person re-identification with expanded cross neighborhood re-ranking, Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 420-429, (2018)
  • [10] Zhao L M, Li X, Zhuang Y T, Wang J D., Deeply-learned part-aligned representations for person re-identification, Proceedings of the IEEE International Conference on Computer Vision, pp. 3239-3248, (2017)
12345