An improved deep learning architecture for person re-identification
Top Cited Papers
- 1 June 2015
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- No. 10636919,p. 3908-3916
- https://doi.org/10.1109/cvpr.2015.7299016
Abstract
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).Keywords
This publication has 19 references indexed in Scilit:
- CaffePublished by Association for Computing Machinery (ACM) ,2014
- DeepReID: Deep Filter Pairing Neural Network for Person Re-identificationPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2014
- Learning Mid-level Filters for Person Re-identificationPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2014
- Unsupervised Salience Learning for Person Re-identificationPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2013
- Learning Locally-Adaptive Decision Functions for Person VerificationPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2013
- Locally Aligned Feature Transforms across ViewsPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2013
- Large scale metric learning from equivalence constraintsPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2012
- BiCov: a novel image representation for person re-identification and face verificationPublished by British Machine Vision Association and Society for Pattern Recognition ,2012
- Person re-identification by probabilistic relative distance comparisonPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2011
- Information-theoretic metric learningPublished by Association for Computing Machinery (ACM) ,2007