期刊
IEEE TRANSACTIONS ON IMAGE PROCESSING
卷 27, 期 1, 页码 281-292出版社
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/TIP.2017.2760512
关键词
Image set classification; metric learning; feature learning; deep learning
资金
- National Science Foundation of China [61772425, 61401357, 61522207, 61473231]
- Natural Science Basic Research Plan in Shaanxi Province of China [2017JM6044]
- Science and Technology Foundation
- Fundamental Research Funds for the Central Universities [3102016ZY023]
Image set classification has attracted much attention because of its broad applications. Despite the success made so far, the problems of intra-class diversity and inter-class similarity still remain two major challenges. To explore a possible solution to these challenges, this paper proposes a novel approach, termed duplex metric learning (DML), for image set classification. The proposed DML consists of two progressive metric learning stages with different objectives used for feature learning and image classification, respectively. The metric learning regularization is not only used to learn powerful feature representations but also well explored to train an effective classifier. At the first stage, we first train a discriminative stacked autoencoder (DSAE) by layer-wisely imposing a metric learning regularization term on the neurons in the hidden layers and meanwhile minimizing the reconstruction error to obtain new feature mappings in which similar samples are mapped closely to each other and dissimilar samples are mapped farther apart. At the second stage, we discriminatively train a classifier and simultaneously fine-tune the DSAE by optimizing a new objective function, which consists of a classification error term and a metric learning regularization term. Finally, two simple voting strategies are devised for image set classification based on the learnt classifier. In the experiments, we extensively evaluate the proposed framework for the tasks of face recognition, object recognition, and face verification on several commonly-used data sets and state-of-the-art results are achieved in comparison with existing methods.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据