HackerPapers

arXiv:1710.10196cs.NE

Progressive Growing of GANs for Improved Quality, Stability, and Variation

Tero Karras, Timo Aila, Samuli Laine, Jaakko Lehtinen

Abstract

We describe a new training methodology for generative adversarial networks. The key idea is to grow both the generator and discriminator progressively: starting from a low resolution, we add new layers that model increasingly fine details as training progresses. This both speeds the training up and greatly stabilizes it, allowing us to produce images of unprecedented quality, e.g., CelebA images at 1024^2. We also propose a simple way to increase the variation in generated images, and achieve a record inception score of 8.80 in unsupervised CIFAR10. Additionally, we describe several implementation details that are important for discouraging unhealthy competition between the generator and discriminator. Finally, we suggest a new metric for evaluating GAN results, both in terms of image quality and variation. As an additional contribution, we construct a higher-quality version of the CelebA dataset.

arXiv comments
Final ICLR 2018 version
Journal reference
DOI
Subjects
cs.NENeural and Evolutionary Computing cs.LGMachine Learning stat.MLMachine Learning (Statistics)

On Hacker News

Linked by 4 identifiable commenters in 4 comments across 4 threads, from Jan 2018 to Nov 2023. Found in 1 HN submission from Nov 2018 to Nov 2018. Open submission discussions.

Comments linking this paper, per year.

Discussed in comments4 threads

  1. SDXL Turbo: A Real-Time Text-to-Image Generation Model 1 comment

    • > I'm disgusted, but not surprised, that teenage kids are generating CSAM like this. Even before we had diffusion models, we had GANs and deepfakes, which were almost immediately used for generating shittons of nonconsensual porn I think the big difference now is that 1) it's…

      godelskiView on HNParent context

  2. Christie’s sells its first AI portrait for $432k 1 comment

    • I don't know exactly what was used to upscale here, but Progressive Growing of GANs[0] was a breakthrough last year that proved at least 1024x1024 was viably producable. The short explanation is: Train and freeze the most basic layer of the model progressively to "let the…

      NegatioNView on HNParent context

  3. A.I. Researchers Are Making More Than $1M, Even at a Nonprofit 1 comment

    • GANs (which he invented) are a game changer, and have enabled things to be built which I thought were 20 years away. For example, the life-like faces NVidia research created in Progressive Growing of GANs for Improved Quality, Stability, and Variation[1] are just an incredible…

      nlView on HNParent context

  4. AI and Deep Learning in 2017 – A Year in Review 1 comment

    • I think for most people that hurdle of understanding is immense, and isn't likely to get any better. ML/DL infrastructure will continue to improve and deploying AI systems will become more accessible as time goes on. But I don't see familiarity with (non) convex optimization…

      nealeratzlaffView on HNParent context

Submitted to Hacker News

Connected through shared HN threads, not inferred similarity or a recommendation.