Random Erasing Data Augmentation

In this paper, we introduce Random Erasing, a new data augmentation method for training the convolutional neural network (CNN). In training, Random Erasing randomly selects a rectangle region in an image and erases its pixels with random values. In this process, training images with various levels of occlusion are generated, which reduces the risk of over-fitting and makes the model robust to occlusion. Random Erasing is parameter learning free, easy to implement, and can be integrated with most of the CNN-based recognition models. Albeit simple, Random Erasing is complementary to commonly used data augmentation techniques such as random cropping and flipping, and yields consistent improvement over strong baselines in image classification, object detection and person re-identification. Code is available at: this https URL.

[1]  Zhuowen Tu,et al.  Aggregated Residual Transformations for Deep Neural Networks , 2016, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[2]  Samy Bengio,et al.  Understanding deep learning requires rethinking generalization , 2016, ICLR.

[3]  Fei-Fei Li,et al.  ImageNet: A large-scale hierarchical image database , 2009, 2009 IEEE Conference on Computer Vision and Pattern Recognition.

[4]  Roland Vollgraf,et al.  Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms , 2017, ArXiv.

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

[6]  Sergey Ioffe,et al.  Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift , 2015, ICML.

[7]  Nanning Zheng,et al.  Similarity Learning with Spatial Constraints for Person Re-identification , 2016, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

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

[10]  Qi Tian,et al.  DisturbLabel: Regularizing CNN on the Loss Layer , 2016, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

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

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

[13]  Yi Yang,et al.  Unsupervised Person Re-identification , 2018, ACM Trans. Multim. Comput. Commun. Appl..

[14]  Ziyan Wu,et al.  A Comprehensive Evaluation and Benchmark for Person Re-Identification: Features, Metrics, and Datasets , 2016, ArXiv.

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

[16]  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).

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

[18]  Shaogang Gong,et al.  Person Re-identification by Deep Learning Multi-scale Representations , 2017, 2017 IEEE International Conference on Computer Vision Workshops (ICCVW).

[19]  Rui Yu,et al.  Divide and Fuse: A Re-ranking Approach for Person Re-identification , 2017, BMVC.

[20]  Brendan J. Frey,et al.  Adaptive dropout for training deep neural networks , 2013, NIPS.

[21]  Shaogang Gong,et al.  Learning a Discriminative Null Space for Person Re-identification , 2016, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

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

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

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

[25]  Nitish Srivastava,et al.  Dropout: a simple way to prevent neural networks from overfitting , 2014, J. Mach. Learn. Res..

[26]  Rainer Stiefelhagen,et al.  Person Re-identification by Deep Learning Attribute-Complementary Information , 2017, 2017 IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW).

[27]  Alex Krizhevsky,et al.  Learning Multiple Layers of Features from Tiny Images , 2009 .

[28]  Luc Van Gool,et al.  The Pascal Visual Object Classes (VOC) Challenge , 2010, International Journal of Computer Vision.

[29]  Nikos Komodakis,et al.  Wide Residual Networks , 2016, BMVC.

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

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

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

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

[34]  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).

[35]  Jian Sun,et al.  Identity Mappings in Deep Residual Networks , 2016, ECCV.

[36]  Abhinav Gupta,et al.  A-Fast-RCNN: Hard Positive Generation via Adversary for Object Detection , 2017, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[37]  Song Bai,et al.  Sparse Contextual Activation for Efficient Visual Re-Ranking , 2016, IEEE Transactions on Image Processing.

[38]  Ross B. Girshick,et al.  Fast R-CNN , 2015, 1504.08083.

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

[40]  François Fleuret,et al.  Scalable Metric Learning via Weighted Approximate Rank Component Analysis , 2016, ECCV.

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

[42]  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).

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

[44]  Yi Yang,et al.  PatchShuffle Regularization , 2017, ArXiv.

[45]  Rob Fergus,et al.  Stochastic Pooling for Regularization of Deep Convolutional Neural Networks , 2013, ICLR.

[46]  Yann LeCun,et al.  Regularization of Neural Networks using DropConnect , 2013, ICML.