首页 > 论文 > 激光与光电子学进展 > 57卷 > 20期(pp:201001--1)

基于多尺度注意力机制的多分支行人重识别算法

Multi-Branch Person Re-Identification Based on Multi-Scale Attention

李聪   蒋敏   孔军  
  • 摘要
  • 论文信息
  • 参考文献
  • 被引情况
  • PDF全文
分享:

摘要

针对基于深度学习的传统方法对于次显著细节信息关注不足的问题,提出一种基于多尺度注意力机制的多分支网络来统筹图像的显著信息及次显著信息。首先,将多尺度特征融合方法(MSFF)与注意力机制相结合,设计了一个多尺度注意力模块(MSA),使得网络可以根据输入信息自适应地调节感受野大小,实现了对于不同尺度信息的充分利用。其次,建立一个多分支网络,实现对于全局特征和多元局部特征的协调统一,并利用多尺度注意力模块,分别实现对于全局显著信息及次显著局部细节信息的加权强化,得到更具判别性的特征用于最终的识别。实验结果表明,本文所设计的网络在多个数据集上都取得了较好的表现。

Abstract

The traditional method based on deep learning does not focus on sub-significant information. Therefore, a multi-branch network based on multi-scale attention (MSA) mechanism was proposed to coordinate significant and sub-significant information. Firstly, the proposed algorithm combined the multi-scale feature fusion module (MSFF) with the attention mechanism to get an MSA module. This module enables the network to adaptively adjust the size of the receptive field according to the input information so as to make full use of information of different scales. Additionally, a multi-branch network was established to realize the coordination of global features and multiple local features. Using the MSA module, weighted enhancement of global information and local detail information can be achieved separately, and a more discriminative feature is obtained for final recognition. The experiment results show that the proposed method performs well on multiple datasets.

广告组1 - 空间光调制器+DMD
补充资料

中图分类号:TP391.4

DOI:10.3788/LOP57.201001

所属栏目:图像处理

基金项目:国家自然科学基金、中国博士后科学基金、科技援疆专项计划、江苏博士后科学基金;

收稿日期:2020-01-06

修改稿日期:2020-03-12

网络出版日期:2020-10-01

作者单位    点击查看

李聪:江南大学物联网工程学院江苏省模式识别与计算智能工程实验室, 江苏 无锡 214122
蒋敏:江南大学物联网工程学院江苏省模式识别与计算智能工程实验室, 江苏 无锡 214122
孔军:江南大学物联网工程学院江苏省模式识别与计算智能工程实验室, 江苏 无锡 214122

联系人作者:蒋敏(minjiang@jiangnan.edu.cn)

备注:国家自然科学基金、中国博士后科学基金、科技援疆专项计划、江苏博士后科学基金;

【1】Liu K W, Fang P P, Xiong H X, et al. Person re-identification based on multi-layer feature [J]. Laser & Optoelectronics Progress. 2020, 57(8): 081503.
刘可文, 房攀攀, 熊红霞, 等. 基于多层级特征的行人重识别 [J]. 激光与光电子学进展. 2020, 57(8): 081503.

【2】Bi X J, Wang H. Person re-identification based on view information embedding [J]. Acta Optica Sinica. 2019, 39(6): 0615007.
毕晓君, 汪灏. 基于视角信息嵌入的行人重识别 [J]. 光学学报. 2019, 39(6): 0615007.

【3】Chen B, Zha Y F, Li Y Q, et al. Person re-identification based on convolutional neural network discriminative feature learning [J]. Acta Optica Sinica. 2018, 38(7): 0720001.
陈兵, 查宇飞, 李运强, 等. 基于卷积神经网络判别特征学习的行人重识别 [J]. 光学学报. 2018, 38(7): 0720001.

【4】Dai Z Z, Chen M Q, Gu X D, et al. Batch DropBlock network for person re-identification and beyond[C]∥2019 IEEE/CVF International Conference on Computer Vision (ICCV), October 27-November 2, 2019, Seoul, Korea (South). New York: , 2019, 3691-3701.

【5】Sun Y F, Zheng L, Yang Y, et al. Beyond part models: person retrieval with refined part pooling (and a strong convolutional baseline)[M]. ∥Computer Vision - ECCV 2018. Cham: , 2018, 501-518.

【6】Wang G S, Yuan Y F, Chen X, et al. Learning discriminative features with multiple granularities for person Re-identification[C]∥2018 ACM Multimedia Conference on Multimedia Conference - MM ''''18. New York: , 2018, 274-282.

【7】Xu L Z, Peng L. Person reidentification based on multiscale convolutional feature fusion [J]. Laser & Optoelectronics Progress. 2019, 56(14): 141504.
徐龙壮, 彭力. 基于多尺度卷积特征融合的行人重识别 [J]. 激光与光电子学进展. 2019, 56(14): 141504.

【8】Ghiasi G, Lin T Y, Le Q V. DropBlock: a regularization method for convolutional networks . [C]∥Advances in Neural Information Processing Systems. 2018, 10727-10737.

【9】Xu J, Zhao R, Zhu F, et al. Attention-aware compositional network for person re-identification[C]∥2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition, June 18-23, 2018, Salt Lake City, UT, USA. New York: , 2018, 2119-2128.

【10】Si J L, Zhang H G, Li C G, et al. Dual attention matching network for context-aware feature sequence based person re-identification[C]∥2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition, June 18-23, 2018, Salt Lake City, UT, USA. New York: , 2018, 5363-5372.

【11】Li W, Zhu X T, Gong S G. Harmonious attention network for person re-identification[C]∥2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition, June 18-23, 2018, Salt Lake City, UT, USA. New York: , 2018, 2285-2294.

【12】Li X, Wang W H, Hu X L, et al. Selective kernel networks[C]∥2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), June 15-20, 2019, Long Beach, CA, USA. New York: , 2019, 510-519.

【13】Zhou K Y, Yang Y X, Cavallaro A, et al. Omni-scale feature learning for person re-identification[C]∥2019 IEEE/CVF International Conference on Computer Vision (ICCV), October 27- November 2, 2019, Seoul, Korea (South). New York: , 2019, 3701-3711.

【14】Chen Y P, Kalantidis Y, Li J S, et al. -10-27)[2019-12-26] . https: ∥arxiv. 2018, org/abs/1810: 11579.

【15】Chollet F. Xception: , 2017, 1800-1807.

【16】Hu J, Shen L, Sun G. Squeeze-and-excitation networks[C]∥2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition, June 18-23, 2018, Salt Lake City, UT, USA. New York: , 2018, 7132-7141.

【17】Lin T Y. RoyChowdhury A, Maji S. Bilinear CNN models for fine-grained visual recognition[C]∥2015 IEEE International Conference on Computer Vision (ICCV), December 7-13, 2015, Santiago, Chile. New York: , 2015, 1449-1457.

【18】Wang H X, Gong S G. -12-05)[2019-12-26] . https: ∥arxiv. 2016, org/abs/1612: 01341.

【19】Zheng Z D, Zheng L, Yang Y. Unlabeled samples generated by GAN improve the person re-identification baseline in vitro[C]∥2017 IEEE International Conference on Computer Vision (ICCV), October 22-29, 2017, Venice, Italy. New York: , 2017, 3774-3782.

【20】Li W, Zhao R, Xiao T, et al. DeepReID: , 2014, 152-159.

【21】Felzenszwalb P F, Girshick R B. McAllester D, et al. Object detection with discriminatively trained part-based models [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence. 2010, 32(9): 1627-1645.

【22】Song C F, Huang Y, Wanli O Y, et al. Mask-guided contrastive attention model for person re-identification[C]∥2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition, June 18-23, 2018, Salt Lake City, UT, USA. New York: , 2018, 1179-1188.

【23】Li D W, Chen X T, Zhang Z, et al. Learning deep context-aware features over body and latent parts for person re-identification[C]∥2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), July 21-26, 2017, Honolulu, HI, USA. New York: , 2017, 7398-7407.

【24】Chang X B, Hospedales T M, Xiang T. Multi-level factorisation net for person re-identification[C]∥2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition, June 18-23, 2018, Salt Lake City, UT, USA. New York: , 2018, 2109-2118.

【25】Kalayeh M M, Basaran E, G?kmen M, et al. Human semantic parsing for person re-identification[C]∥2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition, June 18-23, 2018, Salt Lake City, UT, USA. New York: , 2018, 1062-1071.

【26】Zhong Z, Zheng L, Cao D L, et al. Re-ranking person re-identification with k-reciprocal encoding[C]∥2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), July 21-26, 2017, Honolulu, HI, USA. New York: , 2017, 3652-3661.

【27】Li W, Zhu X T. -05-12)[2019-12-26] . https: ∥arxiv. 2017, org/abs/1705: 04724.

【28】Sun Y F, Zheng L, Deng W J, et al. SVDNet for pedestrian retrieval[C]∥2017 IEEE International Conference on Computer Vision (ICCV), October 22-29, 2017, Venice, Italy. New York: , 2017, 3820-3828.

【29】Chen Y B, Zhu X T, Gong S G. Person re-identification by deep learning multi-scale representations[C]∥2017 IEEE International Conference on Computer Vision Workshops (ICCVW), October 22-29, 2017, Venice, Italy. New York: , 2017, 2590-2600.

【30】Sandler M, Howard A, Zhu M L, et al. MobileNetV2: , 2018, 4510-4520.

引用该论文

Li Cong,Jiang Min,Kong Jun. Multi-Branch Person Re-Identification Based on Multi-Scale Attention[J]. Laser & Optoelectronics Progress, 2020, 57(20): 201001

李聪,蒋敏,孔军. 基于多尺度注意力机制的多分支行人重识别算法[J]. 激光与光电子学进展, 2020, 57(20): 201001

您的浏览器不支持PDF插件,请使用最新的(Chrome/Fire Fox等)浏览器.或者您还可以点击此处下载该论文PDF