按年被提到
20202020 · 1 次2026
视觉、语音与图像生成›生成对抗网络·arXiv:2006.06676 · cs.CV

Training Generative Adversarial Networks with Limited Data

Tero Karras, Miika Aittala, Janne Hellsten, Samuli Laine, Jaakko Lehtinen, Timo Aila · 2020
开始阅读 ↗PDFalphaXiv 讨论
被提及 · 2 人首次 2020-06-15 · 最近 2021-06-24
2不同的人
2活跃月份
2讨论串
1,170被引(OpenAlex)
arXiv 摘要(候选层不写导读)

Training generative adversarial networks (GAN) using too little data typically leads to discriminator overfitting, causing training to diverge. We propose an adaptive discriminator augmentation mechanism that significantly stabilizes training in limited data regimes. The approach does not require changes to loss functions or network architectures, and is applicable both when training from scratch and when fine-tuning an existing GAN on another dataset. We demonstrate, on several datasets, that good results are now possible using only a few thousand training images, often matching StyleGAN2 results with an order of magnitude fewer images. We expect this to open up new application domains for GANs. We also find that the widely used CIFAR-10 is, in fact, a limited data benchmark, and improve the record FID from 5.59 to 2.42.

候选层:至少 2 个不同的人、在 2 个不同月份提到过,还没到主书架的 3 人 3 个月。没有做立场标注,所以只写“被提及”。

HN 书评

推荐在前,同类按时间 · 每篇最多保留 20 条,统计用全部提及
评论godelski · 2021-06

“To be honest I don't think the StyleGAN papers are benchmark chasing. If you read StyleGAN[0], StyleGAN2[1], StyleGAN2-ADA[2], and this paper there is a clear story. They call out the mistakes in the previous papers and resolve them. The papers themselves even admit to where they fall short. But it is research. Problems don't get solved all at once. But i…”

Alias-Free GAN原评论 ↗
被提交为 story · 1 次