An improved deep learning architecture for person re-identification

In this work, we propose a method for simultaneously learning features and a corresponding similarity metric for person re-identification. We present a deep convolutional architecture with layers specially designed to address the problem of re-identification. Given a pair of images as input, our network outputs a similarity value indicating whether the two input images depict the same person. Novel elements of our architecture include a layer that computes cross-input neighborhood differences, which capture local relationships between the two input images based on mid-level features from each input image. A high-level summary of the outputs of this layer is computed by a layer of patch summary features, which are then spatially integrated in subsequent layers. Our method significantly outperforms the state of the art on both a large data set (CUHK03) and a medium-sized data set (CUHK01), and is resistant to over-fitting. We also demonstrate that by initially training on an unrelated large data set before fine-tuning on a small target data set, our network can achieve results comparable to the state of the art even on a small data set (VIPeR).

[1]  Stan Z. Li,et al.  Deep Metric Learning for Practical Person Re-Identification , 2014, ArXiv.

[2]  Horst Bischof,et al.  Large scale metric learning from equivalence constraints , 2012, 2012 IEEE Conference on Computer Vision and Pattern Recognition.

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

[4]  Slawomir Bak,et al.  Multiple-shot human re-identification by Mean Riemannian Covariance Grid , 2011, 2011 8th IEEE International Conference on Advanced Video and Signal Based Surveillance (AVSS).

[5]  Cordelia Schmid,et al.  Is that you? Metric learning approaches for face identification , 2009, 2009 IEEE 12th International Conference on Computer Vision.

[6]  Kilian Q. Weinberger,et al.  Distance Metric Learning for Large Margin Nearest Neighbor Classification , 2005, NIPS.

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

[8]  Xiaogang Wang,et al.  Human Reidentification with Transferred Metric Learning , 2012, ACCV.

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

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

[11]  Trevor Darrell,et al.  Caffe: Convolutional Architecture for Fast Feature Embedding , 2014, ACM Multimedia.

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

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

[14]  Chunxiao Liu,et al.  Person Re-identification: What Features Are Important? , 2012, ECCV Workshops.

[15]  Larry S. Davis,et al.  Joint Learning for Attribute-Consistent Person Re-Identification , 2014, ECCV Workshops.

[16]  Gert R. G. Lanckriet,et al.  Metric Learning to Rank , 2010, ICML.

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

[18]  Inderjit S. Dhillon,et al.  Information-theoretic metric learning , 2006, ICML '07.

[19]  Shaogang Gong,et al.  Person re-identification by probabilistic relative distance comparison , 2011, CVPR 2011.

[20]  Bingpeng Ma,et al.  BiCov: a novel image representation for person re-identification and face verification , 2012, BMVC.

[21]  Xiaogang Wang,et al.  Person Re-identification by Salience Matching , 2013, 2013 IEEE International Conference on Computer Vision.

[22]  Léon Bottou,et al.  Stochastic Gradient Descent Tricks , 2012, Neural Networks: Tricks of the Trade.

[23]  Alessandro Perina,et al.  Multiple-shot person re-identification by chromatic and epitomic analyses , 2012, Pattern Recognit. Lett..

[24]  Xiaogang Wang,et al.  Locally Aligned Feature Transforms across Views , 2013, 2013 IEEE Conference on Computer Vision and Pattern Recognition.

[25]  Hai Tao,et al.  Evaluating Appearance Models for Recognition, Reacquisition, and Tracking , 2007 .

[26]  Venkatesh Saligrama,et al.  A Novel Visual Word Co-occurrence Model for Person Re-identification , 2014, ECCV Workshops.

[27]  Xiaogang Wang,et al.  Learning Mid-level Filters for Person Re-identification , 2014, 2014 IEEE Conference on Computer Vision and Pattern Recognition.

[28]  Fei Xiong,et al.  Person Re-Identification Using Kernel-Based Metric Learning Methods , 2014, ECCV.

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

[30]  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.

[31]  Gian Luca Foresti,et al.  Saliency Weighted Features for Person Re-identification , 2014, ECCV Workshops.

[32]  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.