图采样泛化行人重识别算法

doi:10.3778/j.issn.1002-8331.2304-0269

摘要/Abstract

摘要： 最近的研究表明，度量学习中的深度特征匹配方法，结合大规模、多样化的训练数据，可以显著增强人员再识别的泛化能力。然而，许多现有的方法会产生大量的内存和计算成本，如分类参数或类记忆学习等。为解决上述问题，提出了一种新的基于相关性图采样（correlation graph sampler，CGS）的泛化行人重识别算法，CGS的基本思想是在训练开始时使用局部敏感哈希函数（locality-sensitive Hashing，LSH）和特征度量为所有类构造最近邻关系图。这确保了每一小批训练样本由随机选择的基类和与基类具有相似性的近邻类组成，以提供信息量大且具有挑战性的学习示例，提高行人重识别模型的判别性学习能力。CGS的采样原理会受主干网提取的特征质量影响，因此CGS采样能力会随着主干网的训练而增强，具有可学习性。通过在大规模数据集（包括CUHK03、Market-1501和MSMT17）上交叉评估该方法，广泛的实验结果证实了该方法的有效性，并展示了其在行人重识别应用中的潜力。

关键词: 行人重识别, 度量学习, 相关性图采样, 局部敏感哈希函数

Abstract: Recent study has shown that deep feature matching methods in metric learning, combined with large-scale and diverse training data, can significantly enhance the generalization ability of person re-identification. However, many existing methods generate large memory and computational costs, such as classification parameters or class memory learning. To address these issues, a new generalization person re-identification method based on correlation graph sampler(CGS) is proposed. The basic idea of CGS is to construct a nearest neighbor relationship graph for all classes using local sensitive Hashing (LSH) and feature metrics at the beginning of training. This ensures that each small batch of training samples is composed of randomly selected base classes and near-neighboring classes that are similar to the base classes to provide informative and challenging learning examples and improve the discriminative learning ability of person re-identification models. The sampling principle of CGS is influenced by the quality of features extracted by the backbone network, and therefore, the sampling ability of CGS can be enhanced with the training of the backbone network and has learnability.Through cross-evaluation of this method on large-scale datasets(including CUHK03, Market-1501, and MSMT17), extensive experimental results demonstrate the effectiveness of this method and showcase its potential in person re-identification applications.

Key words: person re-identification, metric learning, correlation graph sampler, local sensitive Hashing (LSH)

闵锋, 毛一新, 况永刚, 彭伟明, 郝琳琳, 吴波. 图采样泛化行人重识别算法[J]. 计算机工程与应用, 2024, 60(14): 219-227.

MIN Feng, MAO Yixin, KUANG Yonggang, PENG Weiming, HAO Linlin, WU Bo. Generalized Pedestrian Re-Identification Method Based on Graph Sampling[J]. Computer Engineering and Applications, 2024, 60(14): 219-227.

参考文献

[1] CHEN Y C, ZHU X, ZHENG W S, et al. Person re-identification by camera correlation aware feature augmentation[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2017, 40(2): 392-408.
[2] 温静, 张福康. 基于多粒度信息融合的无监督行人重识别方法[J]. 计算机工程与应用, 2023, 59(13): 99-109.
WEN J, ZHANG F K. Unsupervised person re-identification method based on multi-granularity information fusion[J]. Computer Engineering and Applications, 2023, 59(13): 99-109.
[3] KARANAM S, LI Y, RADKE R J. Person re-identification with discriminatively trained viewpoint invariant dictionaries[C]//Proceedings of the IEEE International Conference on Computer Vision, 2015: 4516-4524.
[4] WANG Y, WANG L, YOU Y, et al. Resource aware person re-identification across multiple resolutions[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2018: 8042-8051.
[5] 郑爱华, 冯孟雅, 李成龙, 等. 面向跨模态行人重识别的双向动态交互网络[J]. 计算机辅助设计与图形学学报, 2023, 35(3): 371-382.
ZHENG A H, FENG M Y, LI C L, et al. Bi-directional dynamic interaction network for cross-modality person re-identification[J]. Journal of Computer-Aided Design and Computer Graphics, 2023, 35(3): 371-382.
[6] DAS A, PANDA R, ROY-CHOWDHURY A. Active image pair selection for continuous person re-identification[C]//Proceedings of the 2015 IEEE International Conference on Image Processing, 2015: 4263-4267.
[7] SU C, ZHANG S, XING J, et al. Deep attributes driven multi-camera person re-identification[C]//Proceedings of the European Conference on Computer Vision, 2016: 475-491.
[8] BAK S, CARR P. One-shot metric learning for person re-identification[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2017: 2990-2999.
[9] HU Y, YI D, LIAO S, et al. Cross dataset person re-identification[C]//Proceedings of the Asian Conference on Computer Vision, 2014: 650-664.
[10] SONG J, YANG Y, SONG Y Z, et al. Generalizable person re-identification by domain-invariant mapping network[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2019: 719-728.
[11] JIA J, RUAN Q, HOSPEDALES T M. Frustratingly easy person re-identification: generalizing person RE-ID in practice[J]. arXiv:1905.03422, 2019.
[12] SONG C, HUANG Y, OUYANG W, et al. Mask-guided contrastive attention model for person re-identification[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2018: 1179-1188.
[13] JIN X, LAN C, ZENG W, et al. Style normalization and restitution for generalizable person re-identification[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2020: 3143-3152.
[14] YUAN Y, CHEN W, CHEN T, et al. Calibrated domain-invariant learning for highly generalizable large scale re-identification[C]//Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision, 2020: 3589-3598.
[15] 熊明福, 肖应雄, 陈佳, 等. 二次聚类的无监督行人重识别方法[J]. 计算机工程与应用, 2024, 60(1): 227-235.
XIONG M F, XIAO Y X, CHEN J, et al. Unsupervised person re-identification based on quadratic clustering[J]. Computer Engineering and Applications, 2024, 60(1): 227-235.
[16] ZHAO Y, ZHONG Z, YANG F, et al. Learning to generalize unseen domains via memory-based multi-source meta-learning for person re-identification[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2021: 6277-6286.
[17] 杨永胜, 邓淼磊, 张德贤. 基于IBN-Net和通道注意力的行人重识别方法[J]. 计算机工程与应用, 2023, 59(17): 143-151.
YANG Y S, DENG M L, ZHANG D X. Person re-identification method based on IBN-Net and channel attention[J]. Computer Engineering and Applications, 2023, 59(17): 143-151.
[18] BAI Y, JIAO J, CE W, et al. Person30k: a dual-meta generalization network for person re-identification[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2021: 2123-2132.
[19] SUH Y, HAN B, KIM W, et al. Stochastic class-based hard example mining for deep metric learning[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2019: 7251-7259.
[20] SMIRNOV E, MELNIKOV A, NOVOSELOV S, et al. Doppelganger mining for face representation learning[C]//Proceedings of the IEEE International Conference on Computer Vision Workshops, 2017: 1916-1923.
[21] WANG C, ZHANG X, LAN X. How to train triplet networks with 100k identities?[C]//Proceedings of the IEEE International Conference on Computer Vision Workshops, 2017: 1907-1915.
[22] HARWOOD B, KUMAR B G V, CARNEIRO G, et al. Smart mining for deep metric learning[C]//Proceedings of the IEEE International Conference on Computer Vision, 2017: 2821-2829.
[23] YE M, SHEN J, LIN G, et al. Deep learning for person re-identification: a survey and outlook[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2022, 44 (6): 2872-2893.
[24] 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, 2015: 815-823.
[25] LIU W, WEN Y, YU Z, et al. SphereFace: deep hypersphere embedding for face recognition[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2017: 212-220.
[26] WEN Y, ZHANG K, LI Z, et al. A discriminative feature learning approach for deep face recognition[C]//Proceedings of the European Conference on Computer Vision, 2016: 499-515.
[27] SUN K, XIAO B, LIU D, et al. Deep high-resolution representation learning for human pose estimation[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2019: 5693-5703.
[28] LI W, ZHAO R, XIAO T, et al. DeepReID: deep filter pairing neural network for person re-identification[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2014: 152-159.
[29] ZHENG L, SHEN L, TIAN L, et al. Scalable person re-identification: a benchmark[C]//Proceedings of the IEEE International Conference on Computer Vision, 2015: 1116-1124.
[30] 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, 2018: 79-88.
[31] LIAO S, SHAO L. Interpretable and generalizable person re-identification with query-adaptive convolution and temporal lifting[C]//Proceedings of the European Conference on Computer Vision, 2020: 456-474.
[32] ZHOU K, YANG Y. CAVALLARO A, et al. Omni-scale feature learning for person re-identification[C]//Proceedings of the CVF International Conference on Computer Vision, 2019: 3702-3712.
[33] ZHOU K, YANG Y, CAVALLARO A, et al. Learning generalisable omni-scale representations for person re-identification[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2021, 44(9): 5056-5069.
[34] QIAN X, FU Y, XIANG T, et al. Leader-based multi-scale attention deep architecture for person re-identification[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2020, 42 (2): 371-385.
[35] ZHUANG Z, WEI L, XIE L, et al. Rethinking the distribution gap of person re-identification with camera-based batch normalization[C]//Proceedings of the 16th European Conference on Computer Vision, 2020: 140-157.
[36] WANG G, YUAN Y, CHEN X, et al. Learning discriminative features with multiple granularities for person re-identification[C]//Proceedings of the 26th ACM International Conference on Multimedia, 2018: 274-282.
[37] NI H, SONG J, LUO X, et al. Meta distribution alignment for generalizable person re-identification[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2022: 2487-2496.
[38] LIAO S, SHAO L. Graph sampling based deep metric learning for generalizable person re-identification[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2022: 7359-7368.