Multi-manifold deep metric learning for image set classification
Multi-manifold deep metric learning for image set classification
复制标题
DOI：
10.1109/cvpr.2015.7298717
复制
发表时间：
2015-06
期刊：
影响因子：
--
通讯作者：
Jiwen Lu;G. Wang;Weihong Deng;P. Moulin;Jie Zhou
中科院分区：
文献类型：
--
作者：
Jiwen Lu;G. Wang;Weihong Deng;P. Moulin;Jie Zhou
在本文中，我们提出了一种用于图像集分类的多流形深度度量学习（MMDML）方法，其目的是从不同视角或不同光照下捕获的一组图像实例中识别感兴趣的对象。由于流形可以有效地用于对每个图像集中的样本的非线性进行建模，并且深度学习已经证明了对样本的非线性进行建模的卓越能力，因此我们提出了一种MMDML方法来学习多组非线性变换，每个对象类一组，将多组图像实例非线性映射到共享特征子空间，在该方法下，不同类别的流形边缘被最大化，从而可以同时利用区分性和类别特定的信息。我们的方法在五个广泛使用的数据集上实现了最先进的性能。
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.