AI Paper Atlas

Research map / Image generation / Fast diffusion sampling

Denoising Likelihood Score Matching for Conditional Score-based Data Generation

Chen-Hao Chao, Wei-Fang Sun, Bo-Wun Cheng, Yi-Chen Lo, Chia-Che Chang, Yu-Lun Liu, Yu-Lin Chang, Chia-Ping Chen, Chun-Yi Lee

ICLR 2022 · Image generation › Fast diffusion sampling · approach: Distributional control of diffusion · 6 citations (OpenAlex)

This paper tried a common change: Add a reconstruction / auxiliary loss

Add cross-entropy as an auxiliary loss to DLSM' · Inter-twining moon · training stability Improved

What 987 accepted papers report for this change

See this change in detailMatched by the wording of each paper's own result, read by AI from the full text. Papers report gains more often than failures, so this shows what gets published, not the chance a change works.

Read the paper

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
Train the classifier with DLSM and cross-entropy instead of cross-entropy aloneConditional score-based generation · Cifar-10FID: 4.10 -> 2.25Improved
Train the classifier with DLSM and cross-entropy instead of cross-entropy aloneConditional score-based generation · Cifar-100FID: 4.52 -> 3.86Improved
Train the classifier with DLSM and cross-entropy instead of cross-entropy aloneConditional score-based generation · Cifar-10IS: 9.08 -> 9.90Improved
Train the classifier with DLSM and cross-entropy instead of cross-entropy aloneConditional score-based generation · Cifar-100IS: 11.53 -> 11.62Improved
Scale the likelihood scoreBase conditional score-based method · Cifar-10FID: 4.10 -> 12.48Hurt
Scale the likelihood scoreBase conditional score-based method · Cifar-100Recall: 0.62 -> 0.52Hurt
Add DLSM to cross-entropy classifier trainingClassifier in conditional score-based generation · Inter-twining moonlikelihood score error: 0.190 -> 0.052 (c1); 0.181 -> 0.052 (c2)Improved
Add cross-entropy as an auxiliary loss to DLSM' (ablation)DLSM'-trained classifier · Inter-twining moontraining stabilityImproved
Use cross-entropy alone instead of adding the DLSM' score-matching objective (ablation)Classifier in conditional score-based generation · Inter-twining moonlikelihood score errorHurt
Add the DLSM' score-matching objective to cross-entropy training (ablation)Classifier in conditional score-based generation · Inter-twining moonlikelihood score errorImproved
Use DLSM' alone without the cross-entropy auxiliary loss (ablation)Classifier in conditional score-based generation · Inter-twining moontraining stabilityHurt

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy