Generated Data With Sparse Regularized Multi-Pseudo Label for Person Re-Identification

Recently, Generative Adversarial Network (GAN) has been adopted to improve person re-identification (person re-ID) performance through data augmentation. However, directly leveraging generated data to train a re-ID model may easily lead to over-fitting issue on these extra data and decrease the generalisability of model to learn true ID-related features from real data. Inspired by the previous approach which assigns multi-pseudo labels on the generated data to reduce the risk of over-fitting, we propose to take sparse regularization into consideration. We attempt to further improve the performance of current re-ID models by using the unlabeled generated data. The proposed Sparse Regularized Multi-Pseudo Label (SRMpL) can effectively prevent the over-fitting issue when some larger weights are assigned to the generated data. Our experiments are carried out on two publicly available person re-ID datasets (e.g., Market-1501 and DukeMTMC-reID). Compared with existing unlabeled generated data re-ID solutions, our approach achieves competitive performance. Two classical re-ID models are used to verify our sparse regularization label on generated data, i.e., an ID-embedding network and a two-stream network.

[1]  Yi Yang,et al.  Unlabeled Samples Generated by GAN Improve the Person Re-identification Baseline in Vitro , 2017, 2017 IEEE International Conference on Computer Vision (ICCV).

[2]  Zhedong Zheng,et al.  Joint Discriminative and Generative Learning for Person Re-Identification , 2019, 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[3]  Dong-Hyun Lee,et al.  Pseudo-Label : The Simple and Efficient Semi-Supervised Learning Method for Deep Neural Networks , 2013 .

[4]  Luc Van Gool,et al.  Pose Guided Person Image Generation , 2017, NIPS.

[5]  Qi Tian,et al.  Scalable Person Re-identification on Supervised Smoothed Manifold , 2017, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[6]  Yifan Sun,et al.  SVDNet for Pedestrian Retrieval , 2017, 2017 IEEE International Conference on Computer Vision (ICCV).

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

[8]  Qiang Wu,et al.  Beyond Scalar Neuron: Adopting Vector-Neuron Capsules for Long-Term Person Re-Identification , 2020, IEEE Transactions on Circuits and Systems for Video Technology.

[9]  Qiang Wu,et al.  Multi-pseudo Regularized Label for Generated Samples in Person Re-Identification , 2018, ArXiv.

[10]  Xiaogang Wang,et al.  Spindle Net: Person Re-identification with Human Body Region Guided Feature Decomposition and Fusion , 2017, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[11]  Zhaoxiang Zhang,et al.  Spectral Feature Transformation for Person Re-Identification , 2018, 2019 IEEE/CVF International Conference on Computer Vision (ICCV).

[12]  Yunhong Wang,et al.  Relevance Metric Learning for Person Re-identification by Exploiting Global Similarities , 2014, 2014 22nd International Conference on Pattern Recognition.

[13]  Tao Xiang,et al.  Pose-Normalized Image Generation for Person Re-identification , 2017, ECCV.

[14]  Yi Yang,et al.  A Discriminatively Learned CNN Embedding for Person Reidentification , 2016, ACM Trans. Multim. Comput. Commun. Appl..

[15]  Narendra Ahuja,et al.  Pedestrian Recognition with a Learned Metric , 2010, ACCV.

[16]  Xiaogang Wang,et al.  Joint Detection and Identification Feature Learning for Person Search , 2016, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[17]  Kaiqi Huang,et al.  Learning Deep Context-Aware Features over Body and Latent Parts for Person Re-identification , 2017, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[18]  Jian Lu,et al.  Centralized and Clustered Features for Person Re-Identification , 2019, IEEE Signal Processing Letters.

[19]  Yoshua Bengio,et al.  Generative Adversarial Nets , 2014, NIPS.

[20]  Wojciech Zaremba,et al.  Improved Techniques for Training GANs , 2016, NIPS.

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

[22]  Soumith Chintala,et al.  Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks , 2015, ICLR.

[23]  Qiang Wu,et al.  Multi-Pseudo Regularized Label for Generated Data in Person Re-Identification , 2018, IEEE Transactions on Image Processing.

[24]  Yanwei Zheng,et al.  DeepDiff: Learning deep difference features on human body parts for person re-identification , 2017, Neurocomputing.

[25]  Francesco Solera,et al.  Performance Measures and a Data Set for Multi-target, Multi-camera Tracking , 2016, ECCV Workshops.

[26]  Shaogang Gong,et al.  Person Re-Identification by Deep Joint Learning of Multi-Loss Classification , 2017, IJCAI.

[27]  Jingsong Xu,et al.  Celebrities-ReID: A Benchmark for Clothes Variation in Long-Term Person Re-Identification , 2019, 2019 International Joint Conference on Neural Networks (IJCNN).

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

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