基于DCN的无监督域自适应行人重识别方法  

DCN-Based unsupervised domain adaptive person re-identification method

作　　者：杨海伦 王金聪[2,3] 任洪娥 陶锐[1,4] YANG Hai-lun;WANG Jin-cong;REN Hong-e;TAO Rui(College of Information and Computer Engineering,Northeast Forestry University,Harbin 150040,China;College of Mechanical and Electrical Engineering,Northeast Forestry University,Harbin 150040,China;Heilongjiang Forestry Intelligent Equipment Engineering Research Center,Harbin 150040,China;Hulunbuir University,Hulunbuir 0210008,China)

机构地区：[1]东北林业大学信息与计算机工程学院,黑龙江哈尔滨150040 [2]东北林业大学机电工程学院,黑龙江哈尔滨150040 [3]黑龙江林业智能装备工程研究中心,黑龙江哈尔滨150040 [4]呼伦贝尔学院,内蒙古呼伦贝尔021008

出　　处：《液晶与显示》2021年第11期1573-1582,共10页Chinese Journal of Liquid Crystals and Displays

基　　金：黑龙江省自然科学基金(No.LH2020F040);中央高校基本科研业务费专项资金(No.2572017PZ10)。

摘　　要：为解决无监督行人重识别研究中存在的遮挡、域间及相机间风格差异较大等问题,本文提出基于可变形卷积的无监督域自适应模型。针对特征提取过程中的遮挡问题提出基于可变形卷积的CNN模型;在预训练阶段提出应用SPGAN直接减小域间差异,训练过程中提出使用CycleGAN生成不同相机风格图像缓解相机风格差异性问题;提出多损失协同训练的方法实现CycleGAN和复用CNN模型的迭代优化进一步提高识别准确率。实验结果表明,本文提出的方法在源域DukeMTMC-reID/Market-1501和目标域Market-1501/DukeMTMC-reID下进行实验,mAP和Rank-1分别达到了68.7%、64.1%和88.2%、78.1%。本文所提出的模型有效缓解了行人被遮挡、域间及相机间风格差异较大等问题,与现有方法比较,有更好的识别效果。In order to solve the problems of occlusion,large differences in styles between domains and cameras in the research of unsupervised person re-recognition,this paper proposes an unsupervised domain adaptive model based on deformable convolution.Aiming at the occlusion problem in the feature extraction process,a CNN model based on deformable convolution is proposed.In the pre-training stage,it is proposed to apply SPGAN to directly reduce the difference between domains.During the training process,it is proposed to use CycleGAN to generate images of different camera styles to alleviate the problem of camera style differences.A multi-loss collaborative training method is proposed to realize the iterative optimization of CycleGAN and re-used CNN models to further improve the recognition accuracy.The experimental results show that the method proposed in this paper is tested in the source domain DukeMTMC-reID/Market-1501 and the target domain Market-1501/DukeMTMC-reID,and mAP and Rank-1 reach 68.7%,64.1%and 88.2%,78.1%,respectively.The model proposed in this paper effectively alleviates the problems of pedestrians being occluded,and large differences in styles between domains and cameras.Compared with the existing methods,it has a better recognition effect.

关 键 词：DCN 生成对抗网络 无监督域自适应 多损失训练 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]