Imbalanced data learning by minority class augmentation using capsule adversarial networks

Pourya Shamsolmoali, Masoumeh Zareapoor, Linlin Shen, Abdul Hamid Sadka, Jie Yang

Research output: Journal PublicationArticlepeer-review

10 Citations (Scopus)

Abstract

The fact that image datasets are often imbalanced poses an intense challenge for deep learning techniques. In this paper, we propose a method to restore the balance in imbalanced images, by coalescing two concurrent methods, generative adversarial networks (GANs) and capsule network. In our model, generative and discriminative networks play a novel competitive game, in which the generator generates samples towards specific classes from multivariate probabilities distribution. The discriminator of our model is designed in a way that while recognizing the real and fake samples, it is also requires to assign classes to the inputs. Since GAN approaches require fully observed data during training, when the training samples are imbalanced, the approaches might generate similar samples which leading to data overfitting. This problem is addressed by providing all the available information from both the class components jointly in the adversarial training. It improves learning from imbalanced data by incorporating the majority distribution structure in the generation of new minority samples. Furthermore, the generator is trained with feature matching loss function to improve the training convergence. In addition, prevents generation of outliers and does not affect majority class space. The evaluations show the effectiveness of our proposed methodology; in particular, the coalescing of capsule-GAN is effective at recognizing highly overlapping classes with much fewer parameters compared with the convolutional-GAN.

Original languageEnglish
Pages (from-to)481-493
Number of pages13
JournalNeurocomputing
Volume459
DOIs
Publication statusPublished - 12 Oct 2021
Externally publishedYes

Keywords

  • Adversarial network
  • Capsule network
  • Data generation
  • Imbalanced learning
  • Multiclass discriminator

ASJC Scopus subject areas

  • Computer Science Applications
  • Cognitive Neuroscience
  • Artificial Intelligence

Fingerprint

Dive into the research topics of 'Imbalanced data learning by minority class augmentation using capsule adversarial networks'. Together they form a unique fingerprint.

Cite this