arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2102.12033cs.LG
收藏

自诊断GAN:诊断生成对抗网络中的代表性不足样本

Self-Diagnosing GAN: Diagnosing Underrepresented Samples in Generative Adversarial Networks

KAIST(韩国科学技术院);Samsung Research(三星研究院);Samsung Electronics(三星电子);NAVER AI Lab(NAVER AI实验室);NAVER

Jinhee Lee, Haeri Kim, Youngkyu Hong, Hye Won Chung

摘要:

尽管生成对抗网络(GANs)在生成真实样本方面表现出色,但它经常在数据流形的低密度区域附近生成低质量样本,例如,少数群体的样本。已经开发了许多技术来提高所生成的样本的质量,或者通过后处理所生成的样本,或者通过预处理经验数据分布,但是以降低多样性为代价。为了在不降低整体质量的情况下促进样本生成的多样性,我们提出了一种简单而有效的方法来诊断和强调GAN训练期间代表性不足的样本。其主要思想是在每个数据实例上使用数据分布和模型分布之间的差异统计。基于观察到代表性不足的样本具有高平均差异或差异的高变异性,我们提出了一种在GAN训练期间强调这些样本的方法。实验结果表明,该方法提高了GAN在不同数据集上的性能,特别是在提高少数群体样本生成的质量和多样性方面效果显著.

英文摘要:

Despite remarkable performance in producing realistic samples, Generative Adversarial Networks (GANs) often produce low-quality samples near low-density regions of the data manifold, e.g., samples of minor groups. Many techniques have been developed to improve the quality of generated samples, either by post-processing generated samples or by pre-processing the empirical data distribution, but at the cost of reduced diversity. To promote diversity in sample generation without degrading the overall quality, we propose a simple yet effective method to diagnose and emphasize underrepresented samples during training of a GAN. The main idea is to use the statistics of the discrepancy between the data distribution and the model distribution at each data instance. Based on the observation that the underrepresented samples have a high average discrepancy or high variability in discrepancy, we propose a method to emphasize those samples during training of a GAN. Our experimental results demonstrate that the proposed method improves GAN performance on various datasets, and it is especially effective in improving the quality and diversity of sample generation for minor groups.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑