Margin CosReid Network for Pedestrian Re-Identification

This paper proposes a margin CosReid network for effective pedestrian re-identification. Aiming to overcome the overfitting, gradient explosion, and loss function non-convergence problems caused by traditional CNNs, the proposed GBNeck model can realize a faster, stronger generalization, and more discriminative feature extraction task. Furthermore, to enhance the classification ability of the softmax loss function within classes, the margin cosine softmax loss (MCSL) is proposed through a boundary margin introduction to ensure intraclass compactness and interclass separability of the learning depth features and thus to build a stronger metric-based learning model for pedestrian re-identification. The effectiveness of the margin CosReid network was verified on the mainstream datasets Market-1501 and DukeMTMC-reID compared with other state-of-the-art pedestrian re-identification methods.

[1]  Huchuan Lu,et al.  Pose-Invariant Embedding for Deep Person Re-Identification , 2017, IEEE Transactions on Image Processing.

[2]  Chao Li,et al.  Local Feature-Aware Siamese Matching Model for Vehicle Re-Identification , 2020 .

[3]  Radford M. Neal.  Pattern Recognition and Machine Learning , 2007, Technometrics.

[4]  Yichuan Tang,et al.  Deep Learning using Linear Support Vector Machines , 2013, 1306.0239.

[5]  Nitish Srivastava,et al.  Improving neural networks by preventing co-adaptation of feature detectors , 2012, ArXiv.

[6]  Liang Zheng,et al.  Improving Person Re-identification by Attribute and Identity Learning , 2017, Pattern Recognit..

[7]  Long-Sheng Chen,et al.  Journal of Informetrics , 2022 .

[8]  Yi Yang,et al.  Pedestrian Alignment Network for Large-scale Person Re-Identification , 2017, IEEE Transactions on Circuits and Systems for Video Technology.

[9]  Feng Liu,et al.  Discriminative feature extraction for video person re-identification via multi-task network , 2020, Applied Intelligence.

[10]  Hongyan Yu,et al.  Instance Hard Triplet Loss for In-video Person Re-identification , 2020, Applied Sciences.

[11]  Wei Jiang,et al.  A Strong Baseline and Batch Normalization Neck for Deep Person Re-Identification , 2019, IEEE Transactions on Multimedia.

[12]  Fei Zhu,et al.  Spectral-Spatial Feature Extraction and Classification by ANN Supervised With Center Loss in Hyperspectral Imagery , 2017, IEEE Transactions on Geoscience and Remote Sensing.

[13]  Jie Liu,et al.  A spatial and temporal features mixture model with body parts for video-based person re-identification , 2019, Applied Intelligence.

[14]  Xian-Sheng Hua,et al.  SIF: Self-Inspirited Feature Learning for Person Re-Identification , 2020, IEEE Transactions on Image Processing.

[15]  Wei Jiang,et al.  SphereReID: Deep Hypersphere Manifold Embedding for Person Re-Identification , 2018, J. Vis. Commun. Image Represent..