Pith. sign in

REVIEW 1 cited by

Why Are Conditional Generative Models Better Than Unconditional Ones?

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 2212.00362 v1 pith:GABRRTTV submitted 2022-12-01 cs.LG

classification cs.LG
keywords conditionalmodelsbettermodelscdmunconditionalachievesdata
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Extensive empirical evidence demonstrates that conditional generative models are easier to train and perform better than unconditional ones by exploiting the labels of data. So do score-based diffusion models. In this paper, we analyze the phenomenon formally and identify that the key of conditional learning is to partition the data properly. Inspired by the analyses, we propose self-conditioned diffusion models (SCDM), which is trained conditioned on indices clustered by the k-means algorithm on the features extracted by a model pre-trained in a self-supervised manner. SCDM significantly improves the unconditional model across various datasets and achieves a record-breaking FID of 3.94 on ImageNet 64x64 without labels. Besides, SCDM achieves a slightly better FID than the corresponding conditional model on CIFAR10.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 1 Pith paper

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

  1. Versatile Cardiovascular Signal Generation with a Unified Diffusion Transformer

    cs.LG 2025-05 conditional novelty 6.0 of 10

    One diffusion transformer, trained across PPG, ECG, and blood pressure signals, handles denoising, imputation, and cross-modal synthesis in a single framework.

Pith tools