基于双重注意力与精确特征分布匹配的车辆重识别

doi:10.3778/j.issn.1002-8331.2305-0458

摘要/Abstract

摘要： 为了解决目前车辆重识别方法细粒度特征提取能力弱、域泛化能力差的问题，提出了一种基于双重注意力与精确特征分布匹配的车辆重识别方法。提出一种新的双重注意力机制，使用WideResNet50与双重注意力模块构建多细粒度特征提取网络的前置部分，用于高效建模全局上下文信息并增强对车辆细粒度特征的提取能力。将基于精确特征分布匹配的风格迁移策略融入浅层主干来增强源域的域多样性，实现数据增广，从而有效提升车辆重识别的跨域性能和特征表达能力。提出了一种逐深度多尺度特征金字塔结构来加强特征提取，整合不同尺度特征层的多层次信息，并将该结构输出的车辆特征采用特征图分割的思想来突出局部细粒度信息，提升模型对车辆细粒度信息的敏感度。引入Tuplet边际损失来缓解最困难样本的过拟合问题。在两个大型基准车辆数据集VeRi-776和VehicleID上的实验结果表明，所提出算法在单域和跨域任务上都具有较好的重识别效果。

关键词: 双重注意力机制, 精确特征分布匹配, 多尺度特征金字塔, 车辆重识别, 深度学习

Abstract: In order to solve the problems of weak fine-grained feature extraction and poor domain generalization of current vehicle re-identification（Re-ID） methods, a vehicle Re-ID method based on dual attention and exact feature distribution matching is proposed. A new dual attention mechanism is proposed, using WideResNet50 with a dual attention module to construct the front part of a multi-fine grained feature extraction network for efficiency modelling global contextual information and enhancing the extraction capability of fine-grained features of vehicles. A style transfer strategy based on exact feature distribution matching is incorporated into the shallow backbone to enhance the domain diversity of the source domain and achieve data augmentation, thus effectively improving the cross-domain performance and feature representation capability of vehicle Re-ID. A depth-by-depth multi-scale feature pyramid structure is designed to enhance feature extraction, integrate multi-level information from different scale feature layers, and adopt the idea of feature map segmentation for the vehicle features output from this structure to highlight local fine-grained information and enhance the sensitivity of the model to vehicle fine-grained information. Tuplet margin loss is introduced to alleviate the overfitting problem of the most difficult samples. Experimental results on two large benchmark vehicle datasets, VeRi-776 and VehicleID, show that the proposed algorithm has good Re-ID results on both single-domain and cross-domain tasks.

Key words: dual attention mechanism, exact feature distribution matching, multi-scale feature pyramid, vehicle re-identification, deep learning

徐岩, 潘旭光, 郭晓燕, 刘香兰. 基于双重注意力与精确特征分布匹配的车辆重识别[J]. 计算机工程与应用, 2023, 59(23): 114-124.

XU Yan, PAN Xuguang, GUO Xiaoyan, LIU Xianglan. Vehicle Re-Identification Based on Dual Attention and Exact Feature Distribution Matching[J]. Computer Engineering and Applications, 2023, 59(23): 114-124.

参考文献

[1] YU B，TAO D.Deep metric learning with Tuplet margin loss[C]//Proceedings of the IEEE/CVF International Conference on Computer Vision，Seoul，Oct 27-Nov 2，2019.Los Alamitos：IEEE Computer Society Press，2019：6490-6499.
[2] ZHANG Y，LI M，LI R，et al.Exact feature distribution matching for arbitrary style transfer and domain generalization[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition，New Orleans，Jun 19-24，2022.Los Alamitos：IEEE Computer Society Press，2022：8035-8045.
[3] 魏富强，古兰拜尔·吐尔洪，买日旦·吾守尔.生成对抗网络及其应用研究综述[J].计算机工程与应用，2021，57（19）：18-31.
WEI F Q，GULANBAIER T，BUYIDAN G.Review of research on generative adversarial networks and its application[J].Computer Engineering and Applications，2021，57（19）：18-31.
[4] WEI L，ZHANG S，GAO W，et al.Person transfer gan to bridge domain gap for person reidentification[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition，Salt Lake City，Jun 18-22，2018.Los Alamitos：IEEE Computer Society Press，2018：79-88.
[5] ZHU J Y，PARK T，ISOLA P，et al.Unpaired image-to-image translation using cycle-consistent adversarial networks[C]//Proceedings of the IEEE International Conference on Computer Vision，Venice，Oct 22-29，2017.Los Alamitos：IEEE Computer Society Press，2017：2223-2232.
[6] DENG W，ZHENG L，YE Q，et al.Image-image domain adaptation with preserved self-similarity and domain dissimilarity for person re-identification[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition，Salt Lake City，Jul 21-26，2017.Los Alamitos：IEEE Computer Society Press，2018：994-1003.
[7] PENG J，WANG H，XU F，et al.Cross domain knowledge learning with dual-branch adversarial network for vehicle re-identification[J].Neurocomputing，2020，401：133-144.
[8] WANG Y，PENG J，WANG H，et al.Progressive learning with multi-scale attention network for cross-domain vehicle re-identification[J].Science China Information Sciences，2022，65（6）：29-43.
[9] 徐岩，郭晓燕，荣磊磊.无监督学习的车辆重识别方法研究综述[J].计算机科学与探索，2023，17（5）：1017-1037.
XU Y，GUO X Y，RONG L L.Review of research on vehicle re-identification methods with unsupervised learning[J].Journal of Frontiers of Computer Science and Technology，2023，17（5）：1017-1037.
[10] BASHIR R M S，SHAHZAD M，FRAZ M M.Vr-proud：vehicle re-identification using progressive unsupervised deep architecture[J].Pattern Recognition，2019，90：52-65.
[11] WANG Q，MIN W，HAN Q，et al.Inter-domain adaptation label for data augmentation in vehicle re-identification[J].IEEE Transactions on Multimedia，2021，24：1031-1041.
[12] WANG Z，TANG L，LIU X，et al.Orientation invariant feature embedding and spatial temporal regularization for vehicle re-identification[C]//Proceedings of the IEEE International Conference on Computer Vision，Venice，Oct 22-29，2017.Los Alamitos：IEEE Computer Society Press，2017：379-387.
[13] HE B，LI J，ZHAO Y，et al.Part-regularized near-duplicate vehicle re-identification[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition，Long Beach，Jun 16-20，2019.Los Alamitos：IEEE Computer Society Press，2019：3997-4005.
[14] SUPREM A，PU C.Looking glamorous：vehicle Re-ID in heterogeneous cameras networks with global and local attention[J].arXiv：2002.02256，2020.
[15] ZAGORUYKO S，KOMODAKIS N.Wide residual networks[J].arXiv：1605.07146，2016.
[16] 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），Munich，Sep 8-14，2018.Heidelberg：Springer，2018：480-496.
[17] 张宸嘉，朱磊，俞璐.卷积神经网络中的注意力机制综述[J].计算机工程与应用，2021，57（20）：64-72.
ZHANG C J，ZHU L，YU L.Review of attention mechanism in convolutional neural networks[J].Computer Engineering and Applications，2021，57（20）：64-72.
[18] RONG L，XU Y，ZHOU X，et al.A vehicle re-identification framework based on the improved multi-branch feature fusion network[J].Scientific Reports，2021，11（1）：1-12.
[19] 项学泳，王力，宗文鹏，等.ASIS模块支持下融合注意力机制KNN的点云实例分割算法[J].浙江大学学报（工学版），2023，57（5）：875-882.
XIANG X Y，WANG L，ZONG W P，et al.Point cloud instance segmentation based on attention mechanism KNN and ASIS module[J].Journal of Zhejiang University（Engineering Science），2023，57（5）：875-882.
[20] WANG X，GIRSHICK R，GUPTA A，et al.Non-local neural networks[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition，Salt Lake City，Jun 18-22，2018.Los Alamitos：IEEE Computer Society Press，2018：7794-7803.
[21] WOO S，PARK J，LEE J Y，et al.CBAM：convolutional block attention module[C]//Proceedings of the European Conference on Computer Vision （ECCV），Munich，Sep 8-14，2018.Heidelberg：Springer，2018：3-19.
[22] CAO Y，XU J，LIN S，et al.GCNet：non-local networks meet squeeze-excitation networks and beyond[C]//Proceedings of the IEEE/CVF International Conference on Computer Vision Workshops，Seoul，Oct 27-Nov 2，2019.Heidelberg：Springer，2019.
[23] CHEN T，DING S，XIE J，et al.ABD-Net：attentive but diverse person re-identification[C]//Proceedings of the IEEE/CVF International Conference on Computer Vision，Seoul，Oct 27-Nov 2，2019.Heidelberg：Springer，2019：8351-8361.
[24] CHOLLET F.Xception：deep learning with depthwise separable convolutions[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition，Hawaii，Jul 21-26，2017.Los Alamitos：IEEE Computer Society Press，2017：1251-1258.
[25] CAO J，LI Y，SUN M，et al.DO-Conv：depthwise over-parameterized convolutional layer[J].IEEE Transactions on Image Processing，2022，31：3726-3736.
[26] TAN M，PANG R，LE Q V.Efficientdet：scalable and efficient object detection[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition，Seattle，Jun 14-19，2020.Los Alamitos：IEEE Computer Society Press，2020：10781-10790.
[27] ZHANG S，YIN Z，WU X，et al.FPB：feature pyramid branch for person re-identification[J].arXiv：2108.01901，2021.
[28] LIU X，LIU W，MEI T，et al.A deep learning-based approach to progressive vehicle re-identification for urban surveillance[C]//European Conference on Computer Vision，Amsterdam，Oct 8-16，2016.Heidelberg：Springer，2016：869-884.
[29] LIU H，TIAN Y，YANG Y，et al.Deep relative distance learning：tell the difference between similar vehicles[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition，Las Vegas，Jun 26-Jul 1，2016.Los Alamitos：IEEE Computer Society Press，2016：2167-2175.
[30] ZHENG A，LIN X，DONG J，et al.Multi-scale attention vehicle re-identification[J].Neural Computing and Applications，2020，32（23）：17489-17503.
[31] CHENG Y，ZHANG C，GU K，et al.Multi-scale deep feature fusion for vehicle re-identification[C]//2020 IEEE International Conference on Acoustics，Speech and Signal Processing（ICASSP），Barcelona，May 4-8，2020：1928-1932.
[32] TENG S，ZHANG S，HUANG Q，et al.Viewpoint and scale consistency reinforcement for UAV vehicle re-identification[J].International Journal of Computer Vision，2021，129（3）：719-735.
[33] SUN Z，NIE X，XI X，et al.CFVMNet：a multi-branch network for vehicle re-identification based on common field of view[C]//Proceedings of the 28th ACM International Conference on Multimedia，Seattle，Oct 12-16，2020：3523-3531.
[34] ZHANG X，ZHANG R，CAO J，et al.Part-guided attention learning for vehicle instance retrieval[J].IEEE Transactions on Intelligent Transportation Systems，2022，23（4）：3048-3060.
[35] SHEN F，ZHU J，ZHU X，et al.Exploring spatial significance via hybrid pyramidal graph network for vehicle re-identification[J].IEEE Transactions on Intelligent Transportation Systems，2022，23（7）：8793-8804.
[36] SHEN F，XIE Y，ZHU J，et al.GiT：graph interactive transformer for vehicle re-identification[J].IEEE Transactions on Image Processing，2023，32：1039-1051.
[37] ZHU J，ZENG H，HUANG J，et al.Vehicle re-identification using quadruple directional deep learning features[J].IEEE Transactions on Intelligent Transportation Systems，2019，21（1）：410-420.
[38] XU Z，WEI L，LANG C，et al.HSS-GCN：a hierarchical spatial structural graph convolutional network for vehicle re-identification[C]//International Conference on Pattern Recognition，Jan 10-15，2021：356-364.
[39] CHEN Y，KE W，LIN H，et al.Local perspective based synthesis for vehicle re-identification：a transformation state adversarial method[J].Journal of Visual Communication and Image Representation，2022，83：103432.
[40] XU Y，RONG L，ZHOU X，et al.Cross-domain evaluation for vehicle re-identification[C]//2021 IEEE 6th International Conference on Cloud Computing and Big Data Analytics（ICCCBDA），Chengdu，Apr 24-26，2021：474-477.