计算机科学 ›› 2020, Vol. 47 ›› Issue (10): 180-186.doi: 10.11896/jsjkx.191100061
李灏, 唐敏, 林建武, 赵云波
LI Hao, TANG Min, LIN Jian-wu, ZHAO Yun-bo
摘要: 为了提升跨模态行人重识别算法的识别精度,提出了一种基于改进困难三元组损失的特征学习框架。首先,改进了传统困难三元组损失,使其转换为全局三元组损失。其次,基于跨模态行人重识别中存在模态间变化及模态内变化的问题,设计了模态间三元组损失及模态内三元组损失,以配合全局三元组损失进行模型训练。在改进困难三元组损失的基础上,首次在跨模态行人重识别模型中设计属性特征来提高模型的特征提取能力。最后,针对跨模态行人重识别中出现的类别失衡问题,首次将Focal Loss用于替代传统交叉熵损失来进行模型训练。相比现有算法,在RegDB数据集实验中,所提框架在各项指标中均有1.9%~6.4%的提升。另外,通过消融实验证明了3种方法均能提升模型的特征提取能力。
中图分类号:
[1]SONG W R,ZHAO Q Q,CHEN C H,et al.Survey on pedestrian re-identification research[J].CAAI transactions on intelligent systems,2017,12(6):770-780. [2]ZHENG L,YANG Y,HAUPTMANN A G.Person re-identification:Past,present and future[J].arXiv:1610.02984,2016. [3]MATSUKAWA T,SUZUKI E.Person re-identification usingCNN features learned from combination of attributes[C]//2016 23rd International Conference on Pattern Recognition (ICPR).Cancun:IEEE Press,2016:2428-2433. [4]SCHROFF F,KALENICHENKO D,PHILBIN J.Facenet:A unified embedding for face recognition and clustering[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.Boston:IEEE Press,2015:815-823. [5]YE M,LAN X,LI J,et al.Hierarchical discriminative learning for visible thermal person re-identification[C]//Thirty-Second AAAI Conference on Artificial Intelligence.New Orleans AAAI Press,2018. [6]NGUYEN D,HONG H,KIM K,et al.Person recognition system based on a combination of body images from visible light and thermal cameras[J].Sensors,2017,17(3):605. [7]HAO Y,WANG N,LI J,et al.HSME:Hypersphere ManifoldEmbedding for Visible Thermal Person Re-Identification[C]//Proceedings of the AAAI Conference on Artificial Intelligence.Hawaii:AAAI Press,2019,33:8385-8392. [8]WANG G,ZHANG T,CHENG J,et al.RGB-Infrared Cross-Modality Person Re-Identification via Joint Pixel and Feature Alignment[C]//Proceedings of the IEEE International Conference on Computer Vision.Seoul:IEEE Press,2019:3623-3632. [9]YU Q,CHANG X,SONG Y Z,et al.The devil is in the middle:Exploiting mid-level representations for cross-domain instance matching[J].arXiv:1711.08106,2017. [10]HERMANS A,BEYER L,LEIBE B.In defense of the tripletloss for person re-identification[J].arXiv:1703.07737,2017. [11]LIN Y,ZHENG L,ZHENG Z,et al.Improving person re-identification by attribute and identity learning[J].Pattern Recognition,2019,95:151-161. [12]LIN T Y,GOYAL P,GIRSHICK R,et al.Focal loss for dense object detection[C]//Proceedings of the IEEE International Conference on Computer Vision.Venice:IEEE Press,2017:2980-2988. [13]BEN X Y,XU S,WANG K J.Review on Pedestrian Gait Feature Expression and Recognition[J].Pattern Recognition and Artificial Intelligence,2012,25(1):71-81. [14]BAO Z M,GONG S R,ZHONG S,et al.Person Re-identification Algorithm Based on Bidirectional KNN Ranking Optimization[J].Computer Science,2019,46 (11):267-271. [15]WU A,ZHENG W S,LAI J H.Robust depth-based person re-identification[J].IEEE Transactions on Image Processing,2017,26(6):2588-2603. [16]YE M,WANG Z,LAN X,et al.Visible Thermal Person Re-Identification via Dual-Constrained Top-Ranking[C]//the 27th International Joint Conference on Artificial Intelligence.Stockholm:Morgan Kaufmann Press,2018:1092-1099. [17]WU A,ZHENG W S,YU H X,et al.Rgb-infrared cross-modality person re-identification[C]//Proceedings of the IEEE International Conference on Computer Vision.Venice:IEEE Press,2017:5380-5389. [18]LIN L,WANG G,ZUO W,et al.Cross-domain visual matching via generalized similarity measure and feature learning[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2016,39(6):1089-1102. [19]LIAO S,LI S Z.Efficient psd constrained asymmetric metriclearning for person re-identification[C]//Proceedings of the IEEE International Conference on Computer Vision.Santiago:IEEE Press,2015:3685-3693. [20]LIAO S,HU Y,ZHU X,et al.Person re-identification by local maximal occurrence representation and metric learning[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.Santiago:IEEE Press,2015:2197-2206. [21]YE M,WANG Z,LAN X,et al.Visible Thermal Person Re-Identification via Dual-Constrained Top-Ranking[C]//the 27th International Joint Conference on Artificial Intelligence.Stockholm:Morgan Kaufmann Press,2018:1092-1099. [22]WANG Z,WANG Z,ZHENG Y,et al.Learning to reduce dual-level discrepancy for infrared-visible person re-identification[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.Long Beach:IEEE Press,2019:618-626. [23]SELVARAJU R R,COFSWELL M,DAS A,et al.Grad-cam:Visual explanations from deep networks via gradient-based localization[C]//Proceedings of the IEEE International Confe-rence on Computer Vision.Venice:IEEE Press,2017:618-626. |
[1] | 聂秀山, 潘嘉男, 谭智方, 刘新放, 郭杰, 尹义龙. 基于自然语言的视频片段定位综述 Overview of Natural Language Video Localization 计算机科学, 2022, 49(9): 111-122. https://doi.org/10.11896/jsjkx.220500130 |
[2] | 李瑶, 李涛, 李埼钒, 梁家瑞, Ibegbu Nnamdi JULIAN, 陈俊杰, 郭浩. 基于多尺度的稀疏脑功能超网络构建及多特征融合分类研究 Construction and Multi-feature Fusion Classification Research Based on Multi-scale Sparse Brain Functional Hyper-network 计算机科学, 2022, 49(8): 257-266. https://doi.org/10.11896/jsjkx.210600094 |
[3] | 曾志贤, 曹建军, 翁年凤, 蒋国权, 徐滨. 基于注意力机制的细粒度语义关联视频-文本跨模态实体分辨 Fine-grained Semantic Association Video-Text Cross-modal Entity Resolution Based on Attention Mechanism 计算机科学, 2022, 49(7): 106-112. https://doi.org/10.11896/jsjkx.210500224 |
[4] | 孟月波, 穆思蓉, 刘光辉, 徐胜军, 韩九强. 基于向量注意力机制GoogLeNet-GMP的行人重识别方法 Person Re-identification Method Based on GoogLeNet-GMP Based on Vector Attention Mechanism 计算机科学, 2022, 49(7): 142-147. https://doi.org/10.11896/jsjkx.210600198 |
[5] | 杨晓宇, 殷康宁, 候少麒, 杜文仪, 殷光强. 基于特征定位与融合的行人重识别算法 Person Re-identification Based on Feature Location and Fusion 计算机科学, 2022, 49(3): 170-178. https://doi.org/10.11896/jsjkx.210100132 |
[6] | 张新峰, 宋博. 一种基于改进三元组损失和特征融合的行人重识别方法 A Person Re-identification Method Based on Improved Triple Loss and Feature Fusion 计算机科学, 2021, 48(9): 146-152. https://doi.org/10.11896/jsjkx.200800200 |
[7] | 刘立波, 苟婷婷. 融合深度典型相关分析和对抗学习的跨模态检索 Cross-modal Retrieval Combining Deep Canonical Correlation Analysis and Adversarial Learning 计算机科学, 2021, 48(9): 200-207. https://doi.org/10.11896/jsjkx.200600119 |
[8] | 冯霞, 胡志毅, 刘才华. 跨模态检索研究进展综述 Survey of Research Progress on Cross-modal Retrieval 计算机科学, 2021, 48(8): 13-23. https://doi.org/10.11896/jsjkx.200800165 |
[9] | 王栋, 周大可, 黄有达, 杨欣. 基于多尺度多粒度特征的行人重识别 Multi-scale Multi-granularity Feature for Pedestrian Re-identification 计算机科学, 2021, 48(7): 238-244. https://doi.org/10.11896/jsjkx.200600043 |
[10] | 董虎胜, 钟珊, 杨元峰, 孙逊, 龚声蓉. 基于多粒度区域相关深度特征学习的行人重识别 Person Re-identification by Region Correlated Deep Feature Learning with Multiple Granularities 计算机科学, 2021, 48(12): 269-277. https://doi.org/10.11896/jsjkx.210400121 |
[11] | 邓一姣, 张凤荔, 陈学勤, 艾擎, 余苏喆. 面向跨模态检索的协同注意力网络模型 Collaborative Attention Network Model for Cross-modal Retrieval 计算机科学, 2020, 47(4): 54-59. https://doi.org/10.11896/jsjkx.190600181 |
[12] | 邵阳雪, 孟伟, 孔德珍, 韩林轩, 刘扬. 基于深度学习的特种车辆跨模态检索方法 Cross-modal Retrieval Method for Special Vehicles Based on Deep Learning 计算机科学, 2020, 47(12): 205-209. https://doi.org/10.11896/jsjkx.191000132 |
[13] | 冯耀功,蔡国永. 融合多层语义的跨模态检索 Cross-modal Retrieval Fusing Multilayer Semantics 计算机科学, 2019, 46(3): 227-233. https://doi.org/10.11896/j.issn.1002-137X.2019.03.034 |
[14] | 李晓雨, 聂秀山, 崔超然, 蹇木伟, 尹义龙. 基于迁移学习的图像检索算法 Image Retrieval Algorithm Based on Transfer Learning 计算机科学, 2019, 46(1): 73-77. https://doi.org/10.11896/j.issn.1002-137X.2019.01.011 |
[15] | 刘栋,张彩环. 一种可扩展的soa服务质量描述模型 Extensible Model for SOA Quality of Service 计算机科学, 2012, 39(Z6): 339-342. |
|