Lightweight Multi-Branch Network For Person Re-Identification

Person Re-Identification aims to retrieve person identities from images captured by multiple cameras or the same cameras in different time instances and locations. Because of its importance in many vision applications from surveillance to human-machine interaction, person re-identification methods need to be reliable and fast. While more and more deep architectures are proposed for increasing performance, those methods also increase overall model complexity. This paper proposes a lightweight network that combines global, part-based, and channel features in a unified multi-branch architecture that builds on the resource-efficient OSNet backbone. Using a well-founded combination of training techniques and design choices, our final model achieves state-of-the-art results on CUHK03 labeled, CUHK03 detected, and Market-1501 with 85.1% mAP / 87.2% rank1, 82.4% mAP / 84.9% rank1, and 91.5% mAP / 96.3% rank1, respectively.

[1]  James Philbin,et al.  FaceNet: A unified embedding for face recognition and clustering , 2015, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[2]  Zhi Zhang,et al.  Bag of Tricks for Image Classification with Convolutional Neural Networks , 2018, 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[3]  Sergey Ioffe,et al.  Rethinking the Inception Architecture for Computer Vision , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[4]  Helio Pedrini,et al.  Top-DB-Net: Top DropBlock for Activation Enhancement in Person Re-Identification , 2020, 2020 25th International Conference on Pattern Recognition (ICPR).

[5]  Qi Tian,et al.  Scalable Person Re-identification: A Benchmark , 2015, 2015 IEEE International Conference on Computer Vision (ICCV).

[6]  Rongrong Ji,et al.  Salience-Guided Cascaded Suppression Network for Person Re-Identification , 2020, 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[7]  Wei Jiang,et al.  Bag of Tricks and a Strong Baseline for Deep Person Re-Identification , 2019, 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW).

[8]  Liang Zheng,et al.  Re-ranking Person Re-identification with k-Reciprocal Encoding , 2017, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[9]  Luca Antiga,et al.  Automatic differentiation in PyTorch , 2017 .

[10]  Lihi Zelnik-Manor,et al.  Compact Network Training for Person ReID , 2020, ICMR.

[11]  Lucas Beyer,et al.  In Defense of the Triplet Loss for Person Re-Identification , 2017, ArXiv.

[12]  Andrea Cavallaro,et al.  Omni-Scale Feature Learning for Person Re-Identification , 2019, 2019 IEEE/CVF International Conference on Computer Vision (ICCV).

[13]  Hao Chen,et al.  Learning Discriminative and Generalizable Representations by Spatial-Channel Partition for Person Re-Identification , 2020, 2020 IEEE Winter Conference on Applications of Computer Vision (WACV).

[14]  Ling Shao,et al.  Deep Learning for Person Re-Identification: A Survey and Outlook , 2020, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[15]  Yi Yang,et al.  Random Erasing Data Augmentation , 2017, AAAI.

[16]  Jimmy Ba,et al.  Adam: A Method for Stochastic Optimization , 2014, ICLR.

[17]  Qi Tian,et al.  Beyond Part Models: Person Retrieval with Refined Part Pooling , 2017, ECCV.

[18]  Xiong Chen,et al.  Learning Discriminative Features with Multiple Granularities for Person Re-Identification , 2018, ACM Multimedia.

[19]  H Moon,et al.  Computational and Performance Aspects of PCA-Based Face-Recognition Algorithms , 2001, Perception.

[20]  Xiaogang Wang,et al.  DeepReID: Deep Filter Pairing Neural Network for Person Re-identification , 2014, 2014 IEEE Conference on Computer Vision and Pattern Recognition.

[21]  Matthew R. Scott,et al.  Multi-Similarity Loss With General Pair Weighting for Deep Metric Learning , 2019, 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[22]  Rongrong Ji,et al.  Pyramidal Person Re-IDentification via Multi-Loss Dynamic Training , 2018, 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[23]  Richard I. Hartley,et al.  Person Reidentification Using Spatiotemporal Appearance , 2006, 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'06).

[24]  Jian Sun,et al.  Deep Residual Learning for Image Recognition , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[25]  Xiangyu Zhu,et al.  VOC-RelD: Vehicle Re-identification based on Vehicle-Orientation-Camera , 2020, 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW).

[26]  Geoffrey E. Hinton,et al.  ImageNet classification with deep convolutional neural networks , 2012, Commun. ACM.

[27]  Ming Li,et al.  Learning Diverse Features with Part-Level Resolution for Person Re-Identification , 2020, PRCV.

[28]  Kaiming He,et al.  Accurate, Large Minibatch SGD: Training ImageNet in 1 Hour , 2017, ArXiv.

[29]  Yi Yang,et al.  Person Re-identification: Past, Present and Future , 2016, ArXiv.

[30]  Zuozhuo Dai,et al.  Batch DropBlock Network for Person Re-Identification and Beyond , 2018, 2019 IEEE/CVF International Conference on Computer Vision (ICCV).