Research Article
Research on Image Binary Classification Based on Fast Style Transfer Data Enhancement
2 downloads
@INPROCEEDINGS{10.1007/978-3-031-04409-0_8, author={Shuang Zheng and Junfeng Wu and Fugang Liu and Jingyi Pan and Zhuang Qiao}, title={Research on Image Binary Classification Based on Fast Style Transfer Data Enhancement}, proceedings={Machine Learning and Intelligent Communications. 6th EAI International Conference, MLICOM 2021, Virtual Event, November 2021, Proceedings}, proceedings_a={MLICOM}, year={2022}, month={5}, keywords={Convolutional neural network Data enhancement Style transfer Image classification}, doi={10.1007/978-3-031-04409-0_8} }- Shuang Zheng
Junfeng Wu
Fugang Liu
Jingyi Pan
Zhuang Qiao
Year: 2022
Research on Image Binary Classification Based on Fast Style Transfer Data Enhancement
MLICOM
Springer
DOI: 10.1007/978-3-031-04409-0_8
Abstract
The essence of image classification task is to extract high-level semantic content features of images. The traditional data enhancement methods based on convolutional neural network (CNN) are translation, rotation, clipping, noise adding, etc. These methods have not changed the content and style of image data. This paper proposes a fast style migration data enhancement method, which can quickly apply the style art of one image to another image without changing the high-level semantic content characteristics of the image. Through the experimental comparison, it is found that the method of fast style migration data enhancement proposed here can further improve the accuracy of the model compared with the traditional data.
Copyright © 2021–2025 ICST
