Pith. sign in

REVIEW 5 cited by

Refining Generative Process with Discriminator Guidance in Score-based Diffusion Models

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 2211.17091 v4 pith:GD4OUBIZ submitted 2022-11-28 cs.CV cs.AIcs.LG

Dongjun Kim , Yeongmin Kim , Se Jung Kwon , Wanmo Kang , Il-Chul Moon This is my paper · ORCID
classification cs.CVcs.AIcs.LG
keywords discriminatorscoresampletrainingapproachdatadiffusiongeneration
verification ladder T0 review T1 audit T2 compute T3 formal

Signed reviews

No signed human review yet.

0 comments
read the original abstract

The proposed method, Discriminator Guidance, aims to improve sample generation of pre-trained diffusion models. The approach introduces a discriminator that gives explicit supervision to a denoising sample path whether it is realistic or not. Unlike GANs, our approach does not require joint training of score and discriminator networks. Instead, we train the discriminator after score training, making discriminator training stable and fast to converge. In sample generation, we add an auxiliary term to the pre-trained score to deceive the discriminator. This term corrects the model score to the data score at the optimal discriminator, which implies that the discriminator helps better score estimation in a complementary way. Using our algorithm, we achive state-of-the-art results on ImageNet 256x256 with FID 1.83 and recall 0.64, similar to the validation data's FID (1.68) and recall (0.66). We release the code at https://github.com/alsdudrla10/DG.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 5 Pith papers

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

  1. Unifying Generative Models with Path Integrals

    cs.LG 2026-08 conditional novelty 6.0 of 10

    A one-loop correction, computed from two auxiliary ODEs, brings deterministic generative samplers close to the stochastic reference (53% error reduced to 1.6% on a cubic drift), within a path-integral framework that u...

  2. Improving Compositional Generation with Diffusion Models Using Lift Scores

    cs.LG 2025-05 conditional novelty 6.0 of 10

    CompLift accepts or rejects generated samples by computing lift scores from conditional and unconditional denoising errors, improving compositional alignment without retraining.

  3. Generating time-consistent dynamics with discriminator-guided image diffusion models

    cs.LG 2025-05 conditional novelty 6.0 of 10

    A time-consistency discriminator guides a pretrained image diffusion model at inference time to generate realistic, stable spatiotemporal sequences without finetuning the diffusion model.

  4. Integration Flow Models

    cs.CV 2025-04 conditional novelty 6.0 of 10

    Integration Flow learns the integrated denoising map of an ODE generative model and reports competitive one-step FID on CIFAR-10 and ImageNet for VE diffusion, rectified flow, and PFGM++.

  5. Visual Generation Without Guidance

    cs.CV 2025-01 conditional novelty 6.0 of 10

    GFT trains a single β-conditioned network that reproduces Classifier-Free Guidance's sampling distribution, matching CFG FID scores across five model families with half the inference cost.

Pith tools