Pith. sign in

REVIEW 7 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

arxiv 2006.06676 v2 pith:V2KQA76Q submitted 2020-06-11 cs.CV cs.LGcs.NEstat.ML

Training Generative Adversarial Networks with Limited Data

classification cs.CV cs.LGcs.NEstat.ML
keywords trainingdatalimitedadversarialdiscriminatorgenerativeimagesnetworks
verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved
0 comments
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.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 7 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. Denoising Diffusion Probabilistic Models

    cs.LG 2020-06 accept novelty 8.0

    Denoising diffusion probabilistic models generate high-quality images by learning to reverse a fixed forward diffusion process, achieving FID 3.17 on CIFAR10.

  2. SPRINT: Robust Model Attribution of Generated Images via Secret Pixel Reconstruction

    cs.CR 2025-08 unverdicted novelty 7.0

    SPRINT achieves over 99% attribution accuracy on FFHQ images across multiple model pools while reducing adaptive attack success rates to 1% or below by keeping verification targets secret.

  3. SDEdit: Guided Image Synthesis and Editing with Stochastic Differential Equations

    cs.CV 2021-08 conditional novelty 7.0

    SDEdit performs guided image synthesis and editing by adding noise to inputs and refining them via denoising with a diffusion model's SDE prior, outperforming GAN methods in human studies without task-specific training.

  4. Generating Financial Time Series by Matching Random Convolutional Features

    cs.LG 2026-06 unverdicted novelty 6.0

    Introduces SOCK (SOft Competing Kernels), a differentiable random convolutional feature map, to train generative models of financial time series via feature matching and shows outperformance over signature and diffusi...

  5. Mitigating Data Scarcity in Spaceflight Applications for Offline Reinforcement Learning Using Physics-Informed Deep Generative Models

    cs.LG 2026-04 unverdicted novelty 6.0

    MI-VAE generates physics-constrained synthetic trajectories from scarce real data to improve offline RL policy performance on planetary lander tasks over standard VAEs.

  6. Knowledge Distillation in Iterative Generative Models for Improved Sampling Speed

    cs.LG 2021-01 unverdicted novelty 6.0

    Denoising Student distills the multi-step denoising process of score-based and diffusion models into a single forward pass, matching GAN sampling speed while producing comparable sample quality on CIFAR-10, CelebA, an...

  7. A Wasserstein GAN-based climate scenario generator for risk management and insurance: the case of soil subsidence

    cs.LG 2026-04 unverdicted novelty 4.0

    A conditional Wasserstein GAN generates plausible future SWI drought trajectories for French insurance risk management under climate change.