Multi-Manifold Deep Metric Learning for Image Set Classification

Jiwen Lu, Gang Wang, Weihong Deng, Pierre Moulin, Jie Zhou; Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2015, pp. 1137-1145

Abstract


In this paper, we propose a multi-manifold deep metric learning (MMDML) method for image set classification, which aims to recognize an object of interest from a set of image instances captured from varying viewpoints or under varying illuminations. Motivated by the fact that manifold can be effectively used to model the nonlinearity of samples in each image set and deep learning has demonstrated superb capability to model the nonlinearity of samples, we propose a MMDML method to learn multiple sets of nonlinear transformations, one set for each object class, to nonlinearly map multiple sets of image instances into a shared feature subspace, under which the manifold margin of different class is maximized, so that both discriminative and class-specific information can be exploited, simultaneously. Our method achieves the state-of-the-art performance on five widely used datasets.

Related Material


[pdf]
[bibtex]
@InProceedings{Lu_2015_CVPR,
author = {Lu, Jiwen and Wang, Gang and Deng, Weihong and Moulin, Pierre and Zhou, Jie},
title = {Multi-Manifold Deep Metric Learning for Image Set Classification},
booktitle = {Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
month = {June},
year = {2015}
}