Abstract

Class imbalance frequently arises in the context of image classification. Conventional generative adversarial networks (GANs) have a tendency to produce samples from the majority class when trained on class-imbalanced datasets. To address this issue, the Balancing GAN with gradient penalty (BAGAN-GP) has been proposed, but the outcomes may still exhibit a bias toward the majority categories when the similarity between images from different categories is substantial. In this study, we introduce a novel approach called the Pre-trained Gated Variational Autoencoder with Self-attention for Balancing Generative Adversarial Network (SGBGAN) as an image augmentation technique for generating high-quality images. The proposed method utilizes a Gated Variational Autoencoder with Self-attention (SA-GVAE) to initialize the GAN and transfers pre-trained SA-GVAE weights to the GAN. Our experimental results on Fashion-MNIST, CIFAR-10, and a highly unbalanced medical image dataset demonstrate that the SGBGAN outperforms other state-of-the-art methods. Results on Fréchet inception distance (FID) and structural similarity measures (SSIM) show that our model overcomes the instability problems that exist in other GANs. Especially on the Cells dataset, the FID of a minority class increases up to 23.09% compared to the latest BAGAN-GP, and the SSIM of a minority class increases up to 10.81%. It is proved that SGBGAN overcomes the class imbalance restriction and generates high-quality minority class images.

Graphical abstract

The diagram provides an overview of the technical approach employed in this research paper. To address the issue of class imbalance within the dataset, a novel technique called the Gated Variational Autoencoder with Self-attention (SA-GVAE) is proposed. This SA-GVAE is utilized to initialize the Generative Adversarial Network (GAN), with the pre-trained weights from SA-GVAE being transferred to the GAN. Consequently, a Pre-trained Gated Variational Autoencoder with Self-attention for Balancing GAN (SGBGAN) is formed, serving as an image augmentation tool to generate high-quality images. Ultimately, the generation of minority samples is employed to restore class balance within the dataset.

中文翻译：

---

SGBGAN：类不平衡数据集的少数类图像生成

摘要

图像分类中经常出现类别不平衡。传统的生成对抗网络（GAN）在类不平衡数据集上进行训练时倾向于从多数类中生成样本。为了解决这个问题，人们提出了带有梯度惩罚的平衡 GAN（BAGAN-GP），但是当不同类别的图像之间的相似性很大时，结果可能仍然会表现出对大多数类别的偏见。在这项研究中，我们引入了一种称为“具有自注意力的预训练门控变分自动编码器用于平衡生成对抗网络（SGBGAN）”的新颖方法，作为生成高质量图像的图像增强技术。该方法利用具有自注意力的门控变分自动编码器（SA-GVAE）来初始化 GAN 并将预训练的 SA-GVAE 权重传输到 GAN。我们在 Fashion-MNIST、CIFAR-10 和高度不平衡的医学图像数据集上的实验结果表明，SGBGAN 优于其他最先进的方法。Fréchet 起始距离（FID）和结构相似性度量（SSIM）的结果表明，我们的模型克服了其他 GAN 中存在的不稳定问题。特别是在Cells数据集上，与最新的BAGAN-GP相比，少数类别的FID增加了23.09%，少数类别的SSIM增加了10.81%。事实证明，SGBGAN克服了类不平衡的限制，生成了高质量的少数类图像。

图形概要

该图概述了本研究论文中采用的技术方法。为了解决数据集中的类别不平衡问题，提出了一种称为自注意力门控变分自动编码器（SA-GVAE）的新技术。该 SA-GVAE 用于初始化生成对抗网络 (GAN)，并将 SA-GVAE 中的预训练权重转移到 GAN。因此，形成了具有自注意力平衡 GAN 的预训练门控变分自动编码器（SGBGAN），作为图像增强工具来生成高质量图像。最终，少数样本的生成用于恢复数据集中的类平衡。