Pedestrian Retrieval Using Valuable Absence Augmentation

In this paper, we propose a novel data augmentation method named valuable absence augmentation (VAA) in order to alleviate the overfitting and evaluate the influence of the pedestrian valuable parts for the network performance. Specifically, we first train a base convolutional neural network model and obtain the attention map of the pedestrian. Then, we use the attention map to generate new samples. Finally, original samples and new samples are combined to fine-tune the base network model. We conduct experiments on a large-scale pedestrian retrieval database, i.e., Market-1501. Experimental results show that the pedestrian valuable part has a crucial influence for the network performance and that the proposed method achieves better performance than other state-of-the-art methods.

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

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

[3]  Andrew Zisserman,et al.  Very Deep Convolutional Networks for Large-Scale Image Recognition , 2014, ICLR.

[4]  Jingdong Wang,et al.  Deeply-Learned Part-Aligned Representations for Person Re-identification , 2017, 2017 IEEE International Conference on Computer Vision (ICCV).

[5]  Guanglu Sun,et al.  Self-supervised sparse coding scheme for image classification based on low rank representation , 2018, PloS one.

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

[7]  Nicholette D. Palmer,et al.  Novel genetic associations for blood pressure identified via gene-alcohol interaction in up to 570K individuals across multiple ancestries , 2018, PloS one.

[8]  Shuang Liu,et al.  Pedestrian Retrieval via Part-Based Gradation Regularization in Sensor Networks , 2018, IEEE Access.

[9]  Shengcai Liao,et al.  Person re-identification by Local Maximal Occurrence representation and metric learning , 2014, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[10]  David A. McAllester,et al.  Object Detection with Discriminatively Trained Part Based Models , 2010, IEEE Transactions on Pattern Analysis and Machine Intelligence.

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

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

[13]  Xiaogang Wang,et al.  Learning Deep Feature Representations with Domain Guided Dropout for Person Re-identification , 2016, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[14]  Gang Wang,et al.  Gated Siamese Convolutional Neural Network Architecture for Human Re-identification , 2016, ECCV.

[15]  Chunheng Wang,et al.  Cross-View Action Recognition via a Continuous Virtual Path , 2013, 2013 IEEE Conference on Computer Vision and Pattern Recognition.

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

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

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

[19]  Shiliang Zhang,et al.  Deep Attributes Driven Multi-Camera Person Re-identification , 2016, ECCV.

[20]  Guanglu Sun,et al.  Collaborative Self-Regression Method With Nonlinear Feature Based on Multi-Task Learning for Image Classification , 2018, IEEE Access.

[21]  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).

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

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

[24]  Yi Yang,et al.  Generalizing a Person Retrieval Model Hetero- and Homogeneously , 2018, ECCV.

[25]  Haifeng Hu,et al.  Joint Head Attribute Classifier and Domain-Specific Refinement Networks for Face Alignment , 2018, ACM Trans. Multim. Comput. Commun. Appl..

[26]  Chunheng Wang,et al.  Cross-View Action Recognition Using Contextual Maximum Margin Clustering , 2014, IEEE Transactions on Circuits and Systems for Video Technology.