REVIEW 3 cited by
Training Generative Adversarial Networks with Limited Data
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
read the original abstract
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.
Forward citations
Cited by 3 Pith papers
-
Discrete Markov Bridge
Discrete Markov Bridge learns the forward rate matrix and the reverse score in a continuous-time Markov chain, achieving BPC 1.38 on Text8 and FID 11.63 on CIFAR-10.
-
Case Studies of Generative Machine Learning Models for Dynamical Systems
Physics-informed VAEs with Hamiltonian-based losses generate trajectories that match training distributions and satisfy optimal-control equations from as few as 200 to 500 samples.
-
Learning from Limited and Imperfect Data
A doctoral thesis compiling nine peer-reviewed papers on long-tailed image generation, long-tailed recognition, semi-supervised learning, and domain adaptation.
Discussion (0). Continue with ORCID to comment.