基于IBN-Net和通道注意力的行人重识别方法

doi:10.3778/j.issn.1002-8331.2205-0390

摘要/Abstract

摘要： 针对因拍摄的行人图像模糊、遮挡、姿势、视角、颜色、风格和亮度不同等不良因素的影响，行人重识别任务难以提取具有判别力的特征，设计了一种基于IBN-Net和双池通道注意力模块的新颖网络IBNC-Net。以IBN-Net50-a作为骨干网络学习不因图像风格、颜色和亮度等外观变化而变化的特征；在不同的网络层嵌入双池通道注意力模块DPCAM，抑制无关特征，增强具有判别力的特征；引入广义平均池化GeM，通过模型训练自动调整池化尺度。为了验证提出的IBNC-Net方法的有效性，在三个流行的数据集上进行实验，包括Market1501、DukeMTMC-ReID和CUHK03。IBNC-Net模型的Rank-1分别达到了95.6%、91.2%和80.5%，mAP分别达到了89.1%、80.3%和79.4%，实验结果表明，所提方法能够有效提高行人重识别模型的性能。

关键词: 行人重识别, 深度学习, 注意力机制, 计算机视觉

Abstract: Due to the influence of bad factors such as blurred pedestrian images, occlusion, posture, different angles of view, color, style and brightness, it is difficult to extract distinguishing features in person re-identification task. This paper designs a novel network IBNC-Net based on IBN-Net and dual pool channel attention module. Firstly, IBN-Net50-a is used as the backbone network to learn the features that do not change with the appearance changes such as image style, color and brightness. Secondly, the dual pool channel attention module（DPCAM） is embedded in different network layers to suppress irrelevant features and enhance distinguishing features. Then, the generalized mean pooling（GeM） is introduced, and the pool scale is automatically adjusted by the model through training. Finally, in order to verify the effectiveness of the proposed IBNC-Net method, experiments are conducted on three popular datasets, including Market1501, DukeMTMC-ReID and CUHK03. The proposed IBNC-Net model has reached 95.6%/89.1%, 91.2%/80.3% and 80.5%/79.4%（mAP/Rank-1）?respectively. Experimental results show that the proposed method can effectively improve the performance of person re-identification model.

Key words: person re-identification, deep learning, attention mechanism, computer vision

杨永胜, 邓淼磊, 张德贤. 基于IBN-Net和通道注意力的行人重识别方法[J]. 计算机工程与应用, 2023, 59(17): 143-151.

YANG Yongsheng, DENG Miaolei, ZHANG Dexian. Person Re-Identification Method Based on IBN-Net and Channel Attention[J]. Computer Engineering and Applications, 2023, 59(17): 143-151.

参考文献

[1] GOU M，WU Z，RATES-BORRAS A，et al.A systematic evaluation and benchmark for person re-identification：features，metrics，and datasets[J].IEEE Transactions on Pattern Analysis and Machine Intelligence，2018，41（3）：523-536.
[2] ZHENG L，YANG Y，HAUPTMANN A G.Person re-identification：past，present and future[J].arXiv：1610. 02984，2016.
[3] HERMANS A，BEYER L，LEIBE B.In defense of the triplet loss for person re-identification[J].arXiv：1703. 07737，2017.
[4] 厍向阳，李蕊心，叶鸥.融合随机擦除和残差注意力网络的行人重识别[J].计算机工程与应用，2022，58（3）：215-221.
SHE X Y，LI R X，YE O.Pedestrian re-identification combining random erasing and residual attention network[J].Computer Engineering and Applications，2022，58（3）：215-221.
[5] HU B，XU J，WANG X.Learning generalizable deep feature using triplet-batch-center loss for person re-identification[J].Sci China Inf Sci，2021，64：1-2.
[6] SUN Y，ZHENG L，YANG Y，et al.Beyond part models：person retrieval with refined part pooling（and a strong convolutional baseline）[C]//Proceedings of the European Conference on Computer Vision（ECCV），2018：480-496.
[7] FU Y，WEI Y，ZHOU Y，et al.Horizontal pyramid matching for person re-identification[C]//Proceedings of the AAAI Conference on Artificial Intelligence，2019：8295-8302.
[8] 肖雅妮，范馨月，陈文峰.多分支融合局部特征的行人重识别算法[J].计算机工程与应用，2021，57（18）：213-219.
XIAO Y N，FAN X Y，CHEN W F.Research on person re-identification based on integrating local features under multi-branches[J].Computer Engineering and Applications，2021，57（18）：213-219.
[9] 石跃祥，周玥.基于阶梯型特征空间分割与局部注意力机制的行人重识别[J].电子与信息学报，2022，44（1）：195-202.
SHI Y X，ZHOU Y.Person re-identification based on stepped feature space segmentation and local attention mechanism[J].Journal of Electronics & Information Technology，2022，44（1）：195-202.
[10] LIU H，FENG J，QI M，et al.End-to-end comparative attention networks for person re-identification[J].IEEE Transactions on Image Processing，2017，26（7）：3492-3506.
[11] ZHENG M，KARANAM S，WU Z，et al.Re-identification with consistent attentive siamese networks[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition，2019：5735-5744.
[12] LI W，ZHU X，GONG S.Harmonious attention network for person re-identification[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition，2018：2285-2294.
[13] BAO L，MA B，CHANG H，et al.Masked graph attention network for person re-identification[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops，2019.
[14] ZHANG W，DING Q，HU J，et al.Pixel-wise graph attention networks for person re-identification[C]//Proceedings of the 29th ACM International Conference on Multimedia，2021：5231-5238.
[15] JIA M，CHENG X，LU S，et al.Learning disentangled representation implicitly via transformer for occluded person re-identification[J].IEEE Transactions on Multimedia，2022，25：1294-1305.
[16] ZHU H，KE W，LI D，et al.Dual cross-attention learning for fine-grained visual categorization and object re-identification[J].arXiv：2205.02151，2022.
[17] ZHU K，GUO H，ZHANG S，et al.AAformer：auto-aligned transformer for person re-identification[J].arXiv：2104. 00921，2021.
[18] RAGHU M，UNTERTHINER T，KORNBLITH S，et al.Do vision transformers see like convolutional neural networks?[C]//Advances in Neural Information Processing Systems，2021.
[19] PAN X，LUO P，SHI J，et al.Two at once：enhancing learning and generalization capacities via IBN-Net[C]//Proceedings of the European Conference on Computer Vision（ECCV），2018：464-479.
[20] RADENOVI? F，TOLIAS G，CHUM O.Fine-tuning CNN image retrieval with no human annotation[J].IEEE Transactions on Pattern Analysis and Machine Intelligence，2018，41（7）：1655-1668.
[21] KRIZHEVSKY A，SUTSKEVER I，HINTON G E.Image-Net classification with deep convolutional neural networks[C]//Advances in Neural Information Processing Systems，2012.
[22] DAI J，QI H，XIONG Y，et al.Deformable convolutional networks[C]//Proceedings of the IEEE International Conference on Computer Vision，2017：764-773.
[23] ULYANOV D，VEDALDI A，LEMPITSKY V.Improved texture networks：maximizing quality and diversity in feed-forward stylization and texture synthesis[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition，2017：6924-6932.
[24] NIU Z，ZHONG G，YU H.A review on the attention mechanism of deep learning[J].Neurocomputing，2021，452：48-62.
[25] WANG Q，WU B，ZHU P，et al.ECA-Net：efficient channel attention for deep convolutional neural networks[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition，2020：11531-11539.
[26] SZEGEDY C，VANHOUCKE V，IOFFE S，et al.Rethinking the inception architecture for computer vision[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition，2016：2818-2826.
[27] ZHENG L，SHEN L，TIAN L，et al.Scalable person re-identification：a benchmark[C]//Proceedings of the IEEE International Conference on Computer Vision，2015：1116-1124.
[28] ZHENG Z，ZHENG L，YANG Y.Unlabeled samples generated by GAN improve the person re-identification baseline in vitro[C]//Proceedings of the IEEE International Conference on Computer Vision，2017：3754-3762.
[29] LI W，ZHAO R，XIAO T，et al.Deepreid：deep filter pairing neural network for person re-identification[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition，2014：152-159.
[30] LUO H，GU Y，LIAO X，et al.Bag of tricks and a strong baseline for deep person re-identification[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops，2019.
[31] TAN H，LIU X，BIAN Y，et al.Incomplete descriptor mining with elastic loss for person re-identification[J].IEEE Transactions on Circuits and Systems for Video Technology，2021，32（1）：160-171.
[32] 徐胜军，刘求缘，史亚，等.基于多样化局部注意力网络的行人重识别[J].电子与信息学报，2022，44（1）：211-220.
XU S J，LIU Q Y，SHI Y，et al.Person re-identification based on diversified local attention network[J].Journal of Electronics & Information Technology，2022，44（1）：211-220.
[33] ZHU K，GUO H，LIU Z，et al.Identity-guided human semantic parsing for person re-identification[C]//European Conference on Computer Vision.Cham：Springer，2020：346-363.
[34] ZHAO S，GAO C，ZHANG J，et al.Do not disturb me：person re-identification under the interference of other pedestrians[C]//European Conference on Computer Vision.Cham：Springer，2020：647-663.
[35] CHEN G，LIN C，REN L，et al.Self-critical attention learning for person re-identification[C]//Proceedings of the IEEE/CVF International Conference on Computer Vision，2019：9637-9646.