Resolving intra-class imbalance for GAN-based image augmentation

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

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.

Original languageEnglish
Title of host publicationProceedings - 2019 IEEE International Conference on Multimedia and Expo, ICME 2019
PublisherIEEE Computer Society
Pages970-975
Number of pages6
ISBN (Electronic)9781538695524
DOIs
StatePublished - 1 Jul 2019
Event2019 IEEE International Conference on Multimedia and Expo, ICME 2019 - Shanghai, China
Duration: 8 Jul 201912 Jul 2019

Publication series

NameProceedings - IEEE International Conference on Multimedia and Expo
Volume2019-July
ISSN (Print)1945-7871
ISSN (Electronic)1945-788X

Conference

Conference2019 IEEE International Conference on Multimedia and Expo, ICME 2019
CountryChina
CityShanghai
Period8/07/1912/07/19

Keywords

  • Data imbalance
  • Generative adversarial network
  • Image augmentation

Fingerprint Dive into the research topics of 'Resolving intra-class imbalance for GAN-based image augmentation'. Together they form a unique fingerprint.

Cite this