Multi-view semi-supervised learning for image classification

Songhao Zhu

doi:10.1016/j.neucom.2016.02.072

Multi-view semi-supervised learning for image classification

2016-10-01

36

PRE

AI

DOI：10.1016/j.neucom.2016.02.072

Original

Original request for help

Save

Abstract

En 中文

With the massive growth of digital image data uploaded to the Internet, classifying each image into appropriate semantic category with respect to its image content for image index and image retrieval has become an increasingly difficult and laborious task. To deal with this issue, we propose a novel multi view semi-supervised learning framework which leverages the information contained in pseudo-labeled images to improve the prediction performance of image classification using multiple views of an image. In the training process, labeled images are first adopted to train view-specific classifiers independently using uncorrelated and sufficient views, and each view-specific classifier is then iteratively re-trained with respect to a measure of confidence using initial labeled samples and additional pseudo-labeled samples. In the classification process, the maximum entropy principle is utilized to assign appropriate category labels to unlabeled images via optimally trained view-specific classifiers. Experimental results on a general-purpose image database demonstrate the effectiveness and efficiency of the proposed multi-view semi-supervised image classification scheme. (C) 2016 Elsevier B.V. All rights reserved.

Keywords:

Multi-view semi-supervised learning

Maximum entropy

Multi-view fusion

Image classification

Multi-view semi-supervised learning for image classification

Abstract

AI Summary

Journal

Organization