Batch Feature Erasing for Person Re-identification and Beyond

This paper presents a new training mechanism called Batch Feature Erasing (BFE) for person re-identification. We apply this strategy to train a novel network with two branches and employing the ResNet-50 as the backbone. The two branches consist of a conventional global branch and a feature erasing branch where the BFE strategy is applied. When training the feature erasing branch, we randomly erase the same region of all the feature maps in a batch. The network then concatenates features from the two branches for person re-identification. Albeit simple, our method achieves state-of-the-art on person re-identification and is applicable to general metric learning tasks in image retrieval problems. For instance, we achieve 75.4% Rank1 accuracy on the CUHK03-Detect dataset and 83.0% Recall-1 score on the Stanford Online Products dataset, outperforming the existed works by a large margin (more than 6%).

[1]  Shengcai Liao,et al.  Salient Color Names for Person Re-identification , 2014, ECCV.

[2]  Jonathan Tompson,et al.  Efficient object localization using Convolutional Networks , 2014, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

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

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

[5]  Kihyuk Sohn,et al.  Improved Deep Metric Learning with Multi-class N-pair Loss Objective , 2016, NIPS.

[6]  Weilin Huang,et al.  Deep Metric Learning with Hierarchical Triplet Loss , 2018, ECCV.

[7]  Xiaogang Wang,et al.  DeepFashion: Powering Robust Clothes Recognition and Retrieval with Rich Annotations , 2016, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[8]  Xiaogang Wang,et al.  Deep Group-Shuffling Random Walk for Person Re-identification , 2018, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

[9]  Xiaogang Wang,et al.  Unsupervised Salience Learning for Person Re-identification , 2013, 2013 IEEE Conference on Computer Vision and Pattern Recognition.

[10]  Naila Murray,et al.  Re-ID done right: towards good practices for person re-identification , 2018, ArXiv.

[11]  Jungmin Lee,et al.  Attention-based Ensemble for Deep Metric Learning , 2018, ECCV.

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

[13]  Kaiqi Huang,et al.  Adversarially Occluded Samples for Person Re-identification , 2018, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

[14]  Jonathan Krause,et al.  3D Object Representations for Fine-Grained Categorization , 2013, 2013 IEEE International Conference on Computer Vision Workshops.

[15]  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).

[16]  Tao Xiang,et al.  Unsupervised Learning of Generative Topic Saliency for Person Re-identification , 2014, BMVC.

[17]  Xiaogang Wang,et al.  HydraPlus-Net: Attentive Deep Features for Pedestrian Analysis , 2017, 2017 IEEE International Conference on Computer Vision (ICCV).

[18]  Robert Pless,et al.  Deep Randomized Ensembles for Metric Learning , 2018, ECCV.

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

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

[21]  Victor S. Lempitsky,et al.  Multi-Region bilinear convolutional neural networks for person re-identification , 2015, 2017 14th IEEE International Conference on Advanced Video and Signal Based Surveillance (AVSS).

[22]  Zhen Li,et al.  Learning Locally-Adaptive Decision Functions for Person Verification , 2013, 2013 IEEE Conference on Computer Vision and Pattern Recognition.

[23]  Alessandro Perina,et al.  Multiple-Shot Person Re-identification by HPE Signature , 2010, 2010 20th International Conference on Pattern Recognition.

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

[25]  C. V. Jawahar,et al.  Pose-Aware Person Recognition , 2017, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[26]  Xiang Li,et al.  Partial Person Re-Identification , 2015, 2015 IEEE International Conference on Computer Vision (ICCV).

[27]  Graham W. Taylor,et al.  Improved Regularization of Convolutional Neural Networks with Cutout , 2017, ArXiv.

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

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

[30]  Xiang Yu,et al.  Deep Metric Learning via Lifted Structured Feature Embedding , 2016 .

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

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

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

[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]  Victor S. Lempitsky,et al.  Learning Deep Embeddings with Histogram Loss , 2016, NIPS.

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

[37]  Barbara Caputo,et al.  Looking beyond appearances: Synthetic training data for deep CNNs in re-identification , 2017, Comput. Vis. Image Underst..

[38]  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).

[39]  Hantao Yao,et al.  Deep Representation Learning With Part Loss for Person Re-Identification , 2017, IEEE Transactions on Image Processing.

[40]  Shiliang Zhang,et al.  Pose-Driven Deep Convolutional Model for Person Re-identification , 2017, 2017 IEEE International Conference on Computer Vision (ICCV).

[41]  Abir Das,et al.  Consistent Re-identification in a Camera Network , 2014, ECCV.

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

[43]  Tao Mei,et al.  Supplementary Material : Part-Aligned Bilinear Representations for Person Re-Identification , 2018 .

[44]  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).

[45]  P. Cochat,et al.  Et al , 2008, Archives de pediatrie : organe officiel de la Societe francaise de pediatrie.

[46]  Chao Zhang,et al.  Hard-Aware Deeply Cascaded Embedding , 2016, 2017 IEEE International Conference on Computer Vision (ICCV).

[47]  Yan Wang,et al.  Resource Aware Person Re-identification Across Multiple Resolutions , 2018, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

[48]  Horst Possegger,et al.  Deep Metric Learning with BIER: Boosting Independent Embeddings Robustly , 2018, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[49]  Shaogang Gong,et al.  Harmonious Attention Network for Person Re-identification , 2018, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

[50]  Pietro Perona,et al.  The Caltech-UCSD Birds-200-2011 Dataset , 2011 .

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

[52]  Chen Huang,et al.  Local Similarity-Aware Deep Feature Embedding , 2016, NIPS.

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

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

[55]  Frédéric Jurie,et al.  PCCA: A new approach for distance learning from sparse pairwise constraints , 2012, 2012 IEEE Conference on Computer Vision and Pattern Recognition.

[56]  Alexander J. Smola,et al.  Sampling Matters in Deep Embedding Learning , 2017, 2017 IEEE International Conference on Computer Vision (ICCV).

[57]  Tao Xiang,et al.  Deep Transfer Learning for Person Re-Identification , 2016, 2018 IEEE Fourth International Conference on Multimedia Big Data (BigMM).

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

[59]  Xu Lan,et al.  Deep Reinforcement Learning Attention Selection For Person Re-Identification , 2017, BMVC.

[60]  Q. Tian,et al.  GLAD: Global-Local-Alignment Descriptor for Pedestrian Retrieval , 2017, ACM Multimedia.

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

[62]  Shuicheng Yan,et al.  End-to-End Comparative Attention Networks for Person Re-Identification , 2016, IEEE Transactions on Image Processing.

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

[64]  Quoc V. Le,et al.  DropBlock: A regularization method for convolutional networks , 2018, NeurIPS.

[65]  Jianxin Wu,et al.  Person Re-Identification with Correspondence Structure Learning , 2015, 2015 IEEE International Conference on Computer Vision (ICCV).

[66]  Sergio A. Velastin,et al.  Local Fisher Discriminant Analysis for Pedestrian Re-identification , 2013, 2013 IEEE Conference on Computer Vision and Pattern Recognition.

[67]  Alessandro Perina,et al.  Person re-identification by symmetry-driven accumulation of local features , 2010, 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[68]  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).

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

[70]  Gang Wang,et al.  Dual Attention Matching Network for Context-Aware Feature Sequence Based Person Re-identification , 2018, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

[71]  Gang Wang,et al.  A Siamese Long Short-Term Memory Architecture for Human Re-identification , 2016, ECCV.

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

[73]  Nicu Sebe,et al.  Group Consistent Similarity Learning via Deep CRF for Person Re-identification , 2018, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

[74]  Shaogang Gong,et al.  Reidentification by Relative Distance Comparison , 2013, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[75]  Nanning Zheng,et al.  Person Re-identification by Multi-Channel Parts-Based CNN with Improved Triplet Loss Function , 2016, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[76]  Stefanie Jegelka,et al.  Deep Metric Learning via Facility Location , 2016, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

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

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

[79]  Chi Zhang,et al.  Margin Sample Mining Loss: A Deep Learning Based Method for Person Re-identification , 2017, ArXiv.

[80]  Pong C. Yuen,et al.  Domain Transfer Support Vector Ranking for Person Re-identification without Target Camera Label Information , 2013, 2013 IEEE International Conference on Computer Vision.

[81]  Kaiqi Huang,et al.  Beyond Triplet Loss: A Deep Quadruplet Network for Person Re-identification , 2017, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[82]  Ling Shao,et al.  Learning Cross-View Binary Identities for Fast Person Re-Identification , 2016, IJCAI.

[83]  Jian Sun,et al.  AlignedReID: Surpassing Human-Level Performance in Person Re-Identification , 2017, ArXiv.

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