論文題目：Label-Noise Robust Generative Adversarial Networks
論文地址：Label-Noise_Robust_Generative_Adversarial_Networks_CVPR_2019
作者博客：https://takuhirok.github.io/rGAN/
開源代碼：https://github.com/takuhirok/rGAN/
we propose a novel family of GANs called label-noise robust GANs (rGANs), which, by incorporating a noise transition model, can learn a clean label conditional generative distribution even when training labels are noisy.
這里只簡單記錄作者的核心思想，如果后面的研究需要借鑒，將會(huì)更新此篇文章。
