DEEP ACTIVE LEARNING FOR IMAGE CLASSIFICATION

被引：0

作者：

Ranganathan, Hiranmayi ^{[1
]}

Venkateswara, Hemanth ^{[1
]}

Chakraborty, Shayok ^{[1
]}

Panchanathan, Sethuraman ^{[1
]}

机构：

[1] Arizona State Univ, Ctr Cognit Ubiquitous Comp CUbiC, Tempe, AZ 85287 USA

来源：

2017 24TH IEEE INTERNATIONAL CONFERENCE ON IMAGE PROCESSING (ICIP) | 2017年

关键词：

Computer vision; deep learning; deep belief networks; active learning; entropy;

D O I：

暂无

中图分类号：

TB8 [摄影技术];

学科分类号：

0804 ;

摘要：

In the recent years, deep learning algorithms have achieved state-of-the-art performance in a variety of computer vision applications. In this paper, we propose a novel active learning framework to select the most informative unlabeled samples to train a deep belief network model. We introduce a loss function specific to the active learning task and train the model to minimize the loss function. To the best of our knowledge, this is the first research effort to integrate an active learning based criterion in the loss function used to train a deep belief network. Our extensive empirical studies on a wide variety of uni-modal and multi-modal vision datasets corroborate the potential of the method for real-world image recognition applications.

引用

页码：3934 / 3938

页数：5