南京大学学报(自然科学版) ›› 2021, Vol. 57 ›› Issue (5): 715723.doi: 10.13232/j.cnki.jnju.2021.05.001
• •
Feng Xue1,2, Fan Li1,2(), Shuang Li1,2, Huafeng Li1,2
摘要:
针对跨域行人重识别应用中源域与目标域差异较大、现有模型无法在剥离域信息的同时有效获取关键身份信息的问题,提出一种基于对抗学习分离图像域信息与身份信息的方法.该方法由域分离和对抗学习两个阶段构成:域分离阶段分离图像行人特征和域特征;对抗学习阶段通过特征提取器与相机分类器的对抗学习,提升模型对域信息与身份信息的区分能力.在Market?1501,DukeMTMC?reID和MSMT17数据集上开展跨域行人重识别验证实验,实验结果表明,所提方法在跨域行人重识别任务上取得了显著的性能提升.
中图分类号:
1 | 宋婉茹,赵晴晴,陈昌红等. 行人重识别研究综述. 智能系统学报,2017,12(6):770-780. (Song W R,Zhao Q Q,Chen C H,et al. Survey on pedestrian |
research re?identification. Journal of Intelligent | |
Systems,2017,12(6):770-780. | |
2 | Li D W,Chen X T,Zhang Z,et al. Learning deep context?aware features over body and latent parts for person re?dentification∥2017 IEEE Conference on Computer Vision and Pattern Recognition. Honolulu,HI,USA:IEEE,2017:7398-7407. |
3 | Zhao H Y,Tian M Q,Sun S Y,et al. Spindle Net:Person re?identification with human body region guided feature decomposition and fusion∥2017 IEEE Conference on Computer Vision and Pattern Recognition. Honolulu,HI,USA:IEEE,2017:907-915. |
4 | Liu J W,Zha Z J,Chen D,et al. Adaptive transfer network for cross?domain person re?identification∥2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Long Beach,CA,USA:IEEE,2019:7195-7204. |
5 | 崔鹏,范志旭. 基于域鉴别网络和域自适应的行人重识别. 光电子·激光,2019,30(6):632-639. (Cui P,Fan Z X. Person re?identification based on domain discriminative network and domain adaptation. |
Journal of Optoelectronics·Laser,2019,30(6):632-639. | |
6 | Wang J S,Zhu X,Gong S J,et al. Transferable joint attribute?identity deep learning for unsupervised person re?identification∥2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Salt Lake City,UT,USA:IEEE,2018:2275-2284. |
7 | Zhang X Y,Cao J W,Shen C H,et al. Self?training with progressive augmentation for unsupervised |
cross?domain person re?identification∥2019 IEEE/CVF International Conference on Computer Vision. Seoul,Korea (South):IEEE,2019:8221-8230. | |
8 | Long M S,Cao Y,Cao Z J,et al. Transferable representation learning with deep adaptation networks. IEEE Transactions on Pattern Analysis and Machine Intelligence,2019,41(12):3071-3085. |
9 | Jia X B,Jin Y,Su X,et al. Domain?invariant representation learning using an unsupervised domain adversarial adaptation deep neural network. Neurocomputing,2019(355):209-220. |
10 | Cai G Y,Wang Y Q,He L H,et al. Unsupervised domain adaptation with adversarial residual transform networks. IEEE Transactions on Neural Networks and Learning Systems,2020,31(8):3073-3086. |
11 | 张伟信,刘斌. 基于残差网络的特征加权行人重识别研究. 微电子学与计算机,2020,37(4):26-31. |
Zhang W X,Liu B. Person re?identification based on residual network with weightedfeatures. Microelectronics & Computer,2020,37(4):26-31. | |
12 | Wang Z,Ye M,Yang F,et al. Cascaded SR?GAN for scale?adaptive low resolution person re?identification∥Proceedings of the 27th International Joint Conference on Artificial Intelligence. Stockholm,Sweden:AAAI,2018:3891-3897. |
13 | 淦艳,叶茂,曾凡玉. 生成对抗网络及其应用研究综述. 小型微型计算机系统,2020,41(6):1133-1139. (Gan Y,Ye M,Zeng F Y. Review of research on |
generative adversarial networks and its application. Journal of Chinese Computer Systems,2020,41(6):1133-1139. | |
14 | Chadha A,Andreopoulos Y. Improved techniques for adversarial discriminative domain adaptation. IEEE Transactions on Image Processing,2019(29):2622-2637. |
15 | Hao L,Gu Y Z,Liao X Y,et al. Bag of tricks and a strong baseline for deep person re?identification∥2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Long Beach,CA,USA:IEEE,2019:1487-1495. |
16 | He K M,Zhang X Y,Ren S Q,et al. Deep residual learning for image recognition∥2016 IEEE Conference on Computer Vision and Pattern Recognition. Las Vegas,NV,USA:IEEE,2016:770-778. |
17 | Hu J,Shen L,Albanie S,et al. Squeeze?and?excitation networks. IEEE Transactions on Pattern Analysis and Machine Intelligence,2020,42(8):2011-2023. |
18 | Zheng L,Shen L Y,Tian L,et al. Scalable person re?identification:A benchmark∥2015 IEEE Inter?national Conference on Computer Vision. Santiago,Chile:IEEE,2015:1116-1124. |
19 | Ristani E,Solera F,Zou R S,et al. Performance measures and a data set for multi?target,multi?camera tracking∥European Conference on Computer Vision. Springer Berlin Heidelberg,2016:17-35. |
20 | Wei L H,Zhang S L,Wen G,et al. Person transfer GAN to bridge domain gap for person re?identification∥2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Salt Lake City,UT,USA:IEEE,2018:79-88. |
21 | Jin X,Lan C L,Zeng W J,et al. Style normalization and restitution for generalizable person re?identi?fication∥2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Seattle,WA,USA:IEEE,2020:3140-3149. |
22 | Deng W J,Zheng L,Ye Q X,et al. Image?image domain adaptation with preserved self?similarity and domain?dissimilarity for person re?identification∥2018 IEEE/CVF Conference on Computer Vision and Pattern recognition. Salt Lake City,UT,USA:IEEE,2018:994-1003. |
23 | Zhong Z,Zheng L,Zheng Z D,et al. CamStyle:a novel data augmentation method for person re?identi?fication. IEEE Transactions on Image Processing,2019,28(3):1176-1190. |
24 | Chen G Y,Lin C Z,Ren L L,et al. Self?critical attention learning for person re?identification∥2019 IEEE/CVF International Conference on Computer Vision. Seoul,Korea (South):IEEE,2019:9636-9645. |
25 | Zhou K Y,Yang Y X,Cavallaro A,et al. Omni?scale feature learning for person re?identification∥2019 IEEE/CVF International Conference on Computer Vision. Seoul,Korea (South):IEEE,2020:3701-3711. |
26 | Qi L,Wang L,Huo J,et al. A novel unsupervised camera?aware domain adaptation framework for person re?identification∥2019 IEEE/CVF Inter?national Conference on Computer Vision. Seoul,Korea (South):IEEE,2020:8079-8088. |
27 | Zhong Z,Zheng L,Luo Z M,et al. Invariance matters:exemplar memory for domain adaptive person Re?identification∥2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Long Beach,CA,USA:IEEE,2019:598-607. |
[1] | 王发旺, 陈睿, 伏云发. 基于DBN和RF的跨被试情绪识别研究[J]. 南京大学学报(自然科学版), 2021, 57(4): 617-626. |
[2] | 乔宇鑫, 葛洪伟. 自适应样本加权的多视图聚类算法[J]. 南京大学学报(自然科学版), 2021, 57(4): 544-550. |
[3] | 王晓琳, 赵磊, 张维, 伏云发. 基于HHT和核函数选择的情绪特征提取与识别[J]. 南京大学学报(自然科学版), 2021, 57(3): 502-511. |
[4] | 戴臣超, 王洪元, 曹亮, 殷雨昌, 张继. 一种多目标跨摄像头跟踪技术研究与实现[J]. 南京大学学报(自然科学版), 2021, 57(2): 227-236. |
[5] | 陈睿, 伏云发. 基于EEG握力变化及想象单次识别研究[J]. 南京大学学报(自然科学版), 2020, 56(2): 159-166. |
[6] | 杨 薇, 王洪元, 张 继, 张中宝. 一种基于Faster-RCNN的车辆实时检测改进算法[J]. 南京大学学报(自然科学版), 2019, 55(2): 231-237. |
|