<address id="xrvvb"><listing id="xrvvb"></listing></address>

          <form id="xrvvb"></form>

          <address id="xrvvb"></address>

          華中科技大學學報(自然科學版) 2020, Vol. 48 Issue (9): 44-49 DOI10.13245/j.hust.200908

          欄目:計算機與控制工程
          基于圖卷積神經網絡的跨域行人再識別
          潘少明 , 王玉杰 , 種衍文
          武漢大學測繪遙感信息工程國家重點實驗室,湖北 武漢 430079
          摘要 針對由源域訓練的行人再識別模型通常在目標域的泛化能力不強的問題,提出基于圖卷積神經網絡的跨域行人再識別方法,將源域數據學習到的整合鄰居樣本信息的能力遷移至目標域數據.首先,為經過特征提取后的源域數據建立親屬子圖,并將源域數據特征和親屬子圖作為所設計的圖卷積神經網絡模塊的輸入,以基于源域的監督信息訓練圖卷積神經網絡模塊;然后,對經過特征提取后的目標域數據建立親屬子圖,將訓練過的圖卷積神經網絡模塊應用于目標域數據,為目標域數據賦偽標簽;最后,聯合源域數據和目標域數據訓練得到一個泛化能力強的行人再識別模型.分別在兩個大規模公開數據集Market-1501和DukeMTMC-reID上對所提出方法進行實驗驗證,結果表明所提出的方法與所選擇的基準模型相比使得Market-1501的rank-1準確率和平均準確率均值(mAP)分別提高了7.4%和9.2%,而DukeMTMC-reID的rank-1準確率和mAP分別提高了14.2%和14.9%.
          關鍵詞 行人再識別 ;跨域 ;圖卷積神經網絡 ;親屬圖 ;深度學習
          Cross-domain person re-identification using graph convolutional networks
          PAN Shaoming , WANG Yujie , CHONG Yanwen
          State Key Laboratory of Information Engineering in Surveying,Mapping and Remote Sensing,Wuhan University,Wuhan 430079,China
          Abstract Considering the problem that the person re-identification model trained by the source domain usually can only obtain weak generalization ability in target domain,a method based on graph convolutional networks (GCN) was proposed for cross-domain person re-identification by transferring the ability of integrating neighbor sample information learned from the source domain to target domain.Firstly,a source affinity subgraph was established based on data features of source domain.Then the source affinity subgraph and data features of source domain were taken together as the input of the designed graph convolutional neural network module so as to train the module based on the supervisory information of the source domain.Secondly,after establishing the target affinity subgraph based on data features of target domain,the target affinity subgraph and the trained graph convolution neural network module can be used to realize the purpose of assigning pseudo labels for the target domain data.Lastly,a generalized person re-identification model can be obtained by combining the source domain data and the target domain data.Experiments are constructed on two large public dataset:Market-1501 and DukeMTMC-reID.As shown in the extensive experimental results,compared with the baseline model,the rank-1 accuracy and mean average precision (mAP) on Market-1501 is improved 7.4% and 9.2%,respectively;the rank-1 accuracy and mAP on DukeMTMC-reID is improved 14.2% and 14.9%,respectively.
          Keywords person re-identification ; cross-domain ; graph convolutional networks ; affinity graph ; deep learning
          基金資助國家自然科學基金資助項目(41671382,61572372,41271398);國家重點研發計劃資助項目(2017YFB0504202)

          中圖分類號TP18
          文獻標志碼A
          文章編號1671-4512(2020)09-0044-06
          參考文獻
          [1] PENG P,XIANG T,WANG Y,et al.Unsupervised cross-dataset transfer learning for person re-identification [C]// Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.Las Vegas:IEEE,2016:1306-1315.
          [2] 張建明,王偉,陸朝銓,等.基于壓縮卷積神經網絡的交通標志分類算法[J].華中科技大學學報(自然科學版),2019,47(1):108-113.
          [3] 黃心漢,蘇豪,彭剛,等.基于卷積神經網絡的目標識別及姿態檢測[J].華中科技大學學報(自然科學版),2017,45(10):7-11.
          [4] 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 Conference on Computer Vision and Pattern Recognition Workshops.Long Beach:IEEE,2019:1487-1495.
          [5] DENG W,ZHENG L,YE Q,et al.Image-image domain adaptation with preserved self-similarity and domaindissimilarity for person re-identification[C]// Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.Salt Lake City:IEEE,2018:994-1003.
          [6] WEI L,ZHANG S,GAO W,et al.Person transfer gan to bridge domain gap for person re-identification[C]// Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.Salt Lake City:IEEE,2018:79-88.
          [7] FAN H,ZHENG L,YAN C,et al.Unsupervised person re-identification:clustering and fine-tuning[J].ACM Transactions on Multimedia Computing,Communications,and Applications (TOMM),2018,14(4):1-83.
          [8] LIN S,LI H,LI C T,et al.Multi-task mid-level feature alignment network for unsupervised cross-dataset person re-Identification[C]// Proceedings of British Machine Vision Conference.Newcastle:BWVA Press,2018:9-13.
          [9] WANG J,ZHU X,GONG S,et al.Transferable joint attribute-identity deep learning for unsupervised person re-identification[C]// Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. Salt Lake City:IEEE,2018:2275-2284.
          [10] ZHONG Z,ZHENG L,LI S,et al.Generalizing a person retrieval model hetero-and homogeneously[C]// Proceedings of the European Conference on Computer Vision (ECCV).Munich:Springer,2018:172-188.
          [11] WANG Z,ZHENG L,LI Y,et al.Linkage based face clustering via graph convolution network[C]// Proc of the IEEE Conference on Computer Vision and Pattern Recognition.Long Beach:IEEE,2019:1117-1125.
          [12] YANG L,ZHAN X,CHEN D,et al.Learning to cluster faces on an affinity graph[C]// Proceedings of the IEEE Conference on Computer Vision and Pattern Recogni- tion.Long Beach:IEEE,2019:2298-2306.
          [13] YAN S,XIONG Y,LIN D.Spatial temporal graph convolutional networks for skeleton-based action recognition[C]// Proceedings of Thirty-Second AAAI Conference on Artificial Intelligence.New Orleans:AAAI,2018:7444-7452.
          [14] SHEN Y,LI H,XIAO T,et al.Deep group-shuffling random walk for person re-identification[C]// Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.Salt Lake City:IEEE,2018:2265-2274.
          [15] ZHONG Z,ZHENG L,CAO D,et al.Re-ranking person re-identification with k-reciprocal encoding[C]// Proceed- ings of the IEEE Conference on Computer Vision and Pattern Recognition.Honolulu:IEEE,2017:1318-1327.
          [16] ZHENG L,SHEN L,TIAN L,et al.Scalable person re-identification:a benchmark[C]// Proc of the IEEE International Conference on Computer Vision.Santiago:IEEE,2015:1116-1124.
          [17] 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.Venice:IEEE,2017:3754-3762.
          文獻來源
          潘少明, 王玉杰, 種衍文. 基于圖卷積神經網絡的跨域行人再識別[J]. 華中科技大學學報(自然科學版), 2020, 48(9): 44-49
          DOI:10.13245/j.hust.200908
          澳门盘口