top | item 31086897

(no title)

mdda | 3 years ago

Or the two can be combined : https://nvlabs.github.io/denoising-diffusion-gan/index.html

discuss

order

oofbey|3 years ago

Sounds like it gets the worst of both worlds? The difficult training of a GAN with the slow runtime of a diffusion model.

mdda|3 years ago

Could be... Except their page (should you choose to believe it, of course) specifically addresses the advantages:

"""

"Advantages over Traditional GANs" : Thus, we observe that our model exhibits _better training stability_ and mode coverage.

"Why is Sampling from Denoising Diffusion Models so Slow?" : After training, we generate novel instances by sampling from noise and iteratively denoising it _in a few steps_ using our denoising diffusion GAN generator.

"""