Resolving intra-class imbalance for GAN-based image augmentation

研究成果: Conference contribution同行評審

6 引文 斯高帕斯(Scopus)

摘要

Advanced machine learning and deep learning techniques have increasingly improved accuracy of image classification. Most existing studies have investigated the data imbalance problem among classes to further enhance classification accuracy. However, less attention has been paid to data imbalance within every single class. In this work, we present AC-GAN (Actor-Critic Generative Adversarial Network), a data augmentation framework that explicitly considers heterogeneity of intra-class data. AC-GAN exploits a novel loss function to weigh the impacts of different subclasses of data in a class on GAN training. It hence can effectively generate fake data of both majority and minority subclasses, which help train a more accurate classifier. We use defect detection as an example application to evaluate our design. The results demonstrate that the intra-class distribution of fake data generated by our AC-GAN can be more similar to that of raw data. With balanced training for various subclasses, AC-GAN enhances classification accuracy for no matter uniformly or non-uniformly distributed intra-class data.

原文English
主出版物標題Proceedings - 2019 IEEE International Conference on Multimedia and Expo, ICME 2019
發行者IEEE Computer Society
頁面970-975
頁數6
ISBN(電子)9781538695524
DOIs
出版狀態Published - 8 7月 2019
事件2019 IEEE International Conference on Multimedia and Expo, ICME 2019 - Shanghai, China
持續時間: 8 7月 201912 7月 2019

出版系列

名字Proceedings - IEEE International Conference on Multimedia and Expo
2019-July
ISSN(列印)1945-7871
ISSN(電子)1945-788X

Conference

Conference2019 IEEE International Conference on Multimedia and Expo, ICME 2019
國家/地區China
城市Shanghai
期間8/07/1912/07/19

指紋

深入研究「Resolving intra-class imbalance for GAN-based image augmentation」主題。共同形成了獨特的指紋。

引用此