美文网首页文献阅读
[论文]Label-Noise Robust Generativ

[论文]Label-Noise Robust Generativ

作者: wangxiaoguang | 来源:发表于2020-03-08 11:21 被阅读0次

论文题目:Label-Noise Robust Generative Adversarial Networks
论文地址:Label-Noise_Robust_Generative_Adversarial_Networks_CVPR_2019
作者博客:https://takuhirok.github.io/rGAN/
开源代码: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.

这里只简单记录作者的核心思想,如果后面的研究需要借鉴,将会更新此篇文章。

相关文章

网友评论

    本文标题:[论文]Label-Noise Robust Generativ

    本文链接:https://www.haomeiwen.com/subject/dicddhtx.html