Pith. sign in

REVIEW 5 cited by

Diffusion-GAN: Training GANs with Diffusion

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

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 2206.02262 v4 pith:LS5Q64AG submitted 2022-06-05 cs.LG stat.ML

Diffusion-GAN: Training GANs with Diffusion

Zhendong Wang , Huangjie Zheng , Pengcheng He , Weizhu Chen , Mingyuan Zhou This is my paper
classification cs.LG stat.ML
keywords diffusiondatadiscriminatordiffusion-gandiffusedgansgeneratornoise
verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved
0 comments
read the original abstract

Generative adversarial networks (GANs) are challenging to train stably, and a promising remedy of injecting instance noise into the discriminator input has not been very effective in practice. In this paper, we propose Diffusion-GAN, a novel GAN framework that leverages a forward diffusion chain to generate Gaussian-mixture distributed instance noise. Diffusion-GAN consists of three components, including an adaptive diffusion process, a diffusion timestep-dependent discriminator, and a generator. Both the observed and generated data are diffused by the same adaptive diffusion process. At each diffusion timestep, there is a different noise-to-data ratio and the timestep-dependent discriminator learns to distinguish the diffused real data from the diffused generated data. The generator learns from the discriminator's feedback by backpropagating through the forward diffusion chain, whose length is adaptively adjusted to balance the noise and data levels. We theoretically show that the discriminator's timestep-dependent strategy gives consistent and helpful guidance to the generator, enabling it to match the true data distribution. We demonstrate the advantages of Diffusion-GAN over strong GAN baselines on various datasets, showing that it can produce more realistic images with higher stability and data efficiency than state-of-the-art GANs.

discussion (0)

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

Forward citations

Cited by 5 Pith papers

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

  1. Diffusion Policies as an Expressive Policy Class for Offline Reinforcement Learning

    cs.LG 2022-08 unverdicted novelty 7.0

    Diffusion-QL uses conditional diffusion models as expressive policies in offline RL by coupling behavior cloning with Q-value maximization, achieving SOTA on most D4RL tasks.

  2. Efficient Diffusion Distillation via Embedding Loss

    cs.CV 2026-04 unverdicted novelty 6.0

    Embedding Loss aligns feature distributions via MMD in random network embeddings to boost one-step diffusion distillation, reaching SOTA FID of 1.475 on CIFAR-10 unconditional generation.

  3. Pairing Regularization for Mitigating Many-to-One Collapse in GANs

    cs.LG 2026-04 unverdicted novelty 6.0

    Pairing regularization mitigates intra-mode collapse in GANs by penalizing redundant latent-to-sample mappings, improving recall under collapse-prone conditions or precision under stabilized training.

  4. DPM-Solver++: Fast Solver for Guided Sampling of Diffusion Probabilistic Models

    cs.LG 2022-11 conditional novelty 6.0

    DPM-Solver++ enables high-quality guided sampling of diffusion models in 15-20 steps via data-prediction ODE solving and multistep stabilization.

  5. SpiS-GAN: Spiral-Modulated Handwriting Synthesis with Star Operation

    cs.CV 2026-07 conditional novelty 5.0

    A GAN with elliptical-spiral feature mixing, star-operation blocks, and Sobel edge loss produces more realistic synthetic handwriting and lowers HTR error rates on English and Vietnamese datasets.