+高级检索
首页 > 优先出版
PDF HTML阅读 XML下载 导出引用 引用提醒
知识引导和细粒度信息增强的无监督域自适应行人再识别
作者:
作者单位:

1.昆明理工大学信息工程与自动化学院;2.昆明理工大学 信息工程与自动化学院

中图分类号:

TP311

基金项目:

国家自然科学基金(61966021,61562053),大学生创新创业训练计划项目(202010674098)


Knowledge guidance and fine-grained information enhancement for Unsupervised domain adaptation person re-identification
Author:
Affiliation:

Faculty of Information Engineering and Automation,Kunming University of Science and Technology

Fund Project:

National Natural Science Foundation of China(61966021,61562053),College Students' Innovative Entrepreneurial Training Plan Program(202010674098)

  • 摘要
    • | |
  • 访问统计
    • |
  • 参考文献 [52]
    • | |
  • 引证文献
    • | |
  • 文章评论
    摘要:

    无监督域自适应旨在将源域知识迁移到目标域数据集上，是行人再识别中一个非常重要的任务。现实情况下，采集到的数据往往具有视频帧信息。因此，目标域数据集中单一视角下的行人标签极易获取。然而，已有的方法忽略了这些信息，从而限制了识别性能的提升。为此，提出知识引导和细粒度信息增强的无监督域自适应行人再识别。在该方法中，开发了目标域单视角下行人样本已知的新范式，充分挖掘了目标域中有用的信息。同时，将源域知识作为引导，辅助模型提取目标域行人图像的判别性特征。与已有的知识迁移策略相比，这种知识引导的方式能更加有效地缓解域偏移。进一步，将行人的局部信息嵌入到全局特征中，增强了特征的细粒度信息。在两个公开的数据集上进行实验，充分证明了提出方法的有效性和优越性。代码地址：https://github.com/lhf12278/KG-FGIN

    Abstract:

    Unsupervised domain adaptation aims to transfer the source domain knowledge to the target domain dataset, which is a very important task in person re-identification. In reality, the collected data often has video frame information. Therefore, it is very easy to obtain pedestrian labels from a single camera view in the target domain dataset. However, the existing methods ignore the available information, which limits the improvement of recognition performance. For this reason, knowledge guidance and fine-grained information enhancement for unsupervised domain adaptation person re-identification is proposed. In this method, a new paradigm with a single-view pedestrian sample known in the target domain is developed to fully mine the useful information in the target domain. At the same time, the source domain knowledge is used as a guide to assist the model to extract the discriminative features of pedestrian images in the target domain. Compared with the existing knowledge transfer strategies, this knowledge-guided approach can effectively alleviate the domain shift. Furthermore, the local information of pedestrians is embedded into the global feature, and the fine-grained information of the feature is enhanced. Experiments on two publicly datasets fully prove the effectiveness and superiority of the proposed method. Code: https://github.com/lhf12278/KG-FGIN

    参考文献
    [1] 刘智, 冯欣, 张杰. 基于深度卷积神经网络和深度视频的人体行为识别[J]. 重庆大学学报, 2017, 40(11): 99-106.
    [2] LIU ZHI, FENG XIN, ZHANG JIE. Action recognition based on deep convolution neural network and depth sequences[J]. Journal of Chongqing University, 2017, 40(11): 99-106. (in chinese).
    [3] 许晓泓, 何霆, 王华珍, 陈坚. 结合Transformer模型与深度神经网络的数据到文本生成方法[J]. 重庆大学学报, 2020, 43(7): 91-100.
    [4] XU XIAOHONG, HE TING, WANG HUAZHENG, CHEN JIAN. Research on data-to-text generation based on transformer model and deep neural network[J]. Journal of Chongqing University, 2020, 43(7): 91-100. (in chinese).
    [5] Zheng M, Karanam S, Wu Z Y and Radke R J. Re-Identification With Consistent Attentive Siamese Networks[C]. IEEE International Conference on Computer Vision (ICCV), 2019:5728-5737.
    [6] [4]雷大江, 滕君, 王明达. 基于卡方核的正则化线性判别行人再识别算法[J]. 重庆大学报, 2018, 41(09): 66-76.
    [7] LEI DAJIANG, TENG JUN, WANG MINGDA. Chi square kernel regularized linear discriminant analysis for person re-identification[J]. Journal of Chongqing University, 2018, 41(09): 66-76. (in chinese).
    [8] [5]Wu A C, Zheng W S, Guo X W and Lai J H. Distilled person re-identification: Towards a more scalable system[C]. IEEE Conference on Computer Vision and Pattern Recognition (CVPR). 2019:1187-1196.
    [9] [6]张林华,方正云,李仕林,赵明,王红斌,余正涛. 双重对抗无监督域自适应绝缘子检测算法[J]. 重庆大学学报, 2021, 44(03): 122-131.
    [10] ZHANG SHILIN, FANG ZHENGYUN, LI SHILIN, ZHAO MING, WANG HONGBIN, YU ZHENGTAO. Unsupervised domain adaptation insulator detection algorithm based on dual adversarial[J]. Journal of Chongqing University, 2021, 44(03): 122-131. (in chinese).
    [11] [7]Yang F, Li K, Zhong Z, Luo Z, Sun X, Cheng H, Guo X, Huang F, Ji R and Li S. Asymmetric co-teaching for unsupervised cross-domain person re-identification[C]. AAAI Conference on Artificial Intelligence (AAAI), 2020:12597-12604.
    [12] [8]Li H F, Yan S L, Yu Z T and D. Tao. Attribute-identity embedding and self-supervised learning for scalable person re-identification[J]. IEEE Transactions on Circuits and Systems for Video Technology, 2020, 30(10):3472-3485.
    [13] [9]李玲莉,谢明鸿,李凡,张亚飞,李华锋,谭婷婷. 低秩先验引导的无监督域自适应行人重识别[J]. 重庆大学学报.
    [14] LI LINGLI, XIE MINGHONG, LI FAN, ZHANG YAFEI, LI HUAFENG, TAN TINGTING. Unsupervised domain adaptation person re-identification guided by low-rank priori[J]. Journal of Chongqing University. (in chinese).
    [15] [10]Zhong Z, Zheng L, Zheng Z D, Li S Z and Y. Yang. Camstyle: A novel data augmentation method for person re-identification[J]. IEEE Transactions on Image Processing. 2018, 28(3):1176-1190.
    [16] [11]Ren C X, Liang B H, Ge P F, Zhai Y M and Lei Z. Domain adaptive person re-identification via camera style generation and label propagation[J]. IEEE Transactions on Information Forensics and Security, 2019, 15:1290-1302.
    [17] [12]Qi L, Wang L, Huo J, Zhou L P, Shi Y H and Gao Y. A novel unsupervised camera-aware domain adaptation framework for person re-identification[C]. IEEE International Conference on Computer Vision (ICCV), 2019:8080-8089.
    [18] [13]Yu H Y, Zheng W S, Wu A C, Guo X W, Gong S G and Lai J H. Unsupervised person re-identification by soft multi-label learning[C]. IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2019:2143-2152.
    [19] [14]Zhu J Y, Park T, Isola P and Efros A. A. Unpaired image-to-image translation using cycle-consistent adversarial networks[C]. IEEE International Conference on Computer Vision (ICCV), 2017:2242-2251.
    [20] [15]Zheng L, Shen L, Lu T, Wang S and Tian Q. Scalable person re-identification: A benchmark[C]. IEEE International Conference on Computer Vision (ICCV), 2019:1116-1124.
    [21] [16]Ristani E, Solera F, Zou R, Cucchiara R and Tomasi C. Performance measures and a data set for multi target, multi-camera tracking[C]. European Conference On Computer Vision (ECCV), 2016:17-35.
    [22] [17]Chen H R, Wang Y W, Shi Y M, Yan K, Geng M Y, Tian Y H and Xiang T. Deep transfer learning for person re-identification[C]. IEEE Fourth International Conference on Multimedia Big Data (BigMM), 2018:1-5.
    [23] [18]Cheng D, Gong Y H, Zhou S P, Wang J J and Zheng N N. Person re-identification by multi-channel parts-based cnn with improved triplet loss function[C]. IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2016:1335-1344.
    [24] [19]Qian X L, Fu Y W, Xiang T, Jiang Y G and Xue X Y. Multi-scale deep learning architectures for person re-identification[C]. IEEE International Conference on Computer Vision (ICCV), 2017:5399-5408.
    [25] [20]Zheng Z D, Zheng L and Yang Y. Unlabeled samples generated by gan improve the person re-identification baseline in vitro[C]. IEEE International Conference on Computer Vision (ICCV), 2017:3754-3762.
    [26] [21]Goodfellow I, Pouget-Abadie J, Mirza M, Xu B, Warde-Farley D, Ozair A, Courvile A and Bengio Y. Generative adversarial nets[C]. International Conference on Neural Information Processing Systems (NeurIPS), 2014:2672-2680.
    [27] [22]Sun Y F, Zheng L, Yang Y, Tian Q and Wang S J. Beyond part models: Person retrieval with refined part pooling (and a strong convolutional baseline)[C]. European Conference On Computer Vision (ECCV), 2018:480-496.
    [28] [23]Zhao H Y, Tian M Q, Sun S Y, Shao J, Yan J J, Yi S, Wang X G and Tang X O. Spindle net: Person re-identification with human body region guided feature decomposition and fusion[C]. IEEE Conference on Computer Vision and Pattern (CVPR), 2017:1077-1085.
    [29] [24]Zheng L, Huang Y J, Lu H C and Yang Y. Pose-invariant embedding for deep person re-identification[J]. IEEE Transactions on Image Processing, 2019, 28(9): 4500-4509.
    [30] [25]Fan H H, Zheng L, Yan C G and Y. Yang. Unsupervised person re-identification: Clustering and fine-tuning[J]. ACM Transactions on Multimedia Computing, Communications, and Applications, 2018, 14(4):1-18.
    [31] [26]Lin Y T, Dong X Y, Zheng L, Yan Y and Yang Y. A bottom-up clustering approach to unsupervised person re-identification[C]. AAAI Conference on Artificial Intelligence (AAAI), 2019:8738-8745.
    [32] [27]Deng W J, Zheng L, Ye Q X, Kang G L, Yang Y and Jiao J B. Image-image domain adaptation with preserved self-similarity and domain-dissimilarity for person re-identification[C]. IEEE Conference on Computer Vision and Pattern Recognition (ICCV), 2018:994-1003.
    [33] [28]Wei L H, Zhang S L, Gao W and Tian Q. Person transfer gan to bridge domain gap for person re-identification[C]. IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2018:79-88.
    [34] [29]Liu J W, Zha Z J, Chen D, Hong R C and Wang M. Adaptive transfer network for cross-domain person re-identification[C]. IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2019:7195-7204.
    [35] [30]Yang Q Z, Yu H X, Wu A C and Zheng W S. Patch-based discriminative feature learning for unsupervised person re-identification[C]. IEEE Conference on Computer Vision and Pattern Recognition (CVPR). 2019:3628-3637.
    [36] [31]Zhong Z, Zheng L, Luo Z M, Li S Z and Yang Y. Invariance matters: Exemplar memory for domain adaptive person re-identification[C]. 2019 IEEE Conference on Computer Vision and Pattern Recognition, 2019:598-607.
    [37] [32]Santoro A, Bartunov S, Botvinick M, Wierstra D and Lillicrap T. One-shot learning with memory-augmented neural networks[C]. International Conference on Machine Learning(ICML), 2016:1842-1850.
    [38] [33]Andrychowicz M, Denil M, Gomez S, Hoffman M, Pfau D, Schaul T and Freitas N. Learning to learn by gradient descent by gradient descent[C]. International Conference on Neural Information Processing Systems (NeurIPS), 2016:3981-3989.
    [39] [34]Vinyals O, Blundell C, Lillicrap T, Kavukcuoglu K and Wierstra D. Matching networks for one shot learning[C]. International Conference on Neural Information Processing Systems (NeurIPS), Barcelone, Spain, 2016:3630-3638.
    [40] [35]Finn C, Abbeel P, and Levine S. Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks[C]. IEEE International Conference on Machine Learning (ICML), 2017.
    [41] [36]Zhao Y Y, Zhong Z, Yang F X, Luo Z M, Lin Y J, Li S and Sebe N. Learning to Generalize Unseen Domains via Memory-based Multi-Source Meta-Learning for Person Re-Identification[C]. IEEE Conference on Computer Vision and Pattern (CVPR), 2021.
    [42] [37]Szegedy C, Vanhoucke V, Ioffe S, Shlens J, and Wojna Z. Rethinking the inception architecture for computer vision[C]. IEEE conference on computer vision and pattern recognition (CVPR), 2016: 2818- 2826.
    [43] [38]Deng J, Dong W, Socher R, Li L J, Li K and Li F F. ImageNet: A large-scale hierarchical image database[C]. S IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2009:248-255.
    [44] [39]He K M, Zhang X Y, Ren S Q and Sun J. Deep Residual Learning for Image Recognition[C]. IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2016:770-778.
    [45] [40]Luo H, Gu Y Z, Liao X Y, Lai S Q and Jiang W. Bag of tricks and a strong baseline for deep person re-identification[C]. IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2019:1487-1495.
    [46] [41]Yu H X, Wu A C and Zheng W S. Cross-view asymmetric metric learning for unsupervised person re-identification[C]. IEEE International Conference on Computer Vision (ICCV), 2017:994-1002.
    [47] [42]Yu H Y, Wu A C and Zheng W S. Unsupervised Person Re-Identification by Deep Asymmetric Metric Embedding[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2020, 42(4):956-973.
    [48] [43]Huang Y, Wu Q, Xu J S and Zhong Y. Sbsgan: Suppression of inter-domain background shift for person re-identification[C]. IEEE International Conference on Computer Vision (ICCV), 2019:9526-9535.
    [49] [44]Wang J Y, Zhu X T, Gong S G and Li W. Transferable joint attribute-identity deep learning for unsupervised person re-identification[C]. IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2018: 2275-2284.
    [50] [45]Chang X B, Yang Y X, Xiang and Hospedales T. Disjoint label space transfer learning with common factorised space[C]. AAAI Conference on Artificial Intelligence (AAAI), 2019: 3288-3295.
    [51] [46]Li H F, Kuang Z Y, Yu Z T and Luo J B. Structure alignment of attributes and visual features for cross-dataset person re-identification[J]. Pattern Recognition, 2020, 106:107414.
    [52] [47]Yuan Y, Chen W Y, Chen T L, Yang Y, Ren Z, Wang Z Y and Hua G. Calibrated domain-invariant learning for highly generalizable large scale re-identification[C]. IEEE Winter Conference on Applications of Computer Vision (WACV), 2020:3589-3598.
    相似文献
    引证文献
    引证文献 [0] 您输入的地址无效！
    没有找到您想要的资源，您输入的路径无效！

    网友评论
    网友评论
    分享到微博
    发 布
引用本文

复制
分享
文章指标
  • 点击次数:507
  • 下载次数: 0
  • HTML阅读次数: 0
  • 引用次数: 0
历史
  • 收稿日期:2021-04-19
  • 最后修改日期:2021-05-08
  • 录用日期:2021-05-25
文章二维码
您是第11658715 位访问者
主管单位：中华人民共和国教育部
主办单位：重庆大学
地址：重庆市沙坪坝正街174号
电话：
重庆大学学报 ® 2025 版权所有