Share Email Print

Proceedings Paper • new

Semi-supervised image classification via attention mechanism and generative adversarial network
Author(s): Xuezhi Xiang; Zeting Yu; Ning Lv; Xiangdong Kong; Abdulmotaleb El Saddik
Format Member Price Non-Member Price
PDF $17.00 $21.00

Paper Abstract

Image classification plays a vital role in the field of computer vision. Many existing image classification methods with high accuracy are based on supervised learning, which requires a great number of labeled images. However, the labeling of images requires a lot of human and material resources. In this paper, we focus on semi-supervised image classification, which can build a classifier using a few labeled images and plenty of unlabeled images. We propose an attention-based generative adversarial network (GAN) for semi-supervised image classification, which can capture global dependencies and adaptively extract important information. Furthermore, we apply spectral normalization, which can stabilize the training of attention-based GAN. The experimental results obtained with the CIFAR-10 dataset show that the proposed method is comparable with the state-of-the-art GAN-based semi-supervised image classification methods.

Paper Details

Date Published: 3 January 2020
PDF: 7 pages
Proc. SPIE 11373, Eleventh International Conference on Graphics and Image Processing (ICGIP 2019), 113731J (3 January 2020); doi: 10.1117/12.2557747
Show Author Affiliations
Xuezhi Xiang, Harbin Engineering Univ. (China)
Zeting Yu, Harbin Engineering Univ. (China)
Ning Lv, Harbin Engineering Univ. (China)
Xiangdong Kong, Harbin Engineering Univ. (China)
Abdulmotaleb El Saddik, Univ. of Ottawa (Canada)

Published in SPIE Proceedings Vol. 11373:
Eleventh International Conference on Graphics and Image Processing (ICGIP 2019)
Zhigeng Pan; Xun Wang, Editor(s)

© SPIE. Terms of Use
Back to Top