AI Paper Atlas

Research map / Image generation / Fast diffusion sampling

Diffusion Models as Plug-and-Play Priors

Alexandros Graikos, Nikolay Malkin, Nebojsa Jojic, Dimitris Samaras

NeurIPS 2022 · Image generation › Fast diffusion sampling · approach: Diffusion theory and design space · 64 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

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
increase DDPM inference steps from 4 to 256 (ablation)DDPM TSP solver · TSP N=50optimality gap (%): 2.86 -> 1.28Improved
increase DDPM inference steps from 16 to 256 (ablation)DDPM TSP solver · TSP N=100optimality gap (%): 3.78 -> 2.19Improved
increase DDPM inference steps from 4 to 16 (ablation)DDPM TSP solver · TSP N=50optimality gap (%): 2.86 -> 2.98Mixed
train on 20-50 vertex instances instead of 50 only (ablation)DDPM TSP solver · TSP N=100optimality gap (%): 2.19 -> 2.11No clear effect
use DDPM-inferred tours plus 2-opt vs 2-opt aloneDDPM TSP solver · TSP N=50optimality gap (%): 2.95 -> 1.28Improved
fine-tune U-Net on diffusion-inferred segmentations vs training from scratch on them (ablation)segmentation network · EnviroAtlas Durham, NCaccuracy (%): 76.0 -> 79.8Improved
fine-tune U-Net on diffusion-inferred segmentations vs PA supervisedsegmentation network · EnviroAtlas Phoenix, AZaccuracy (%): 6.7 -> 69.6Improved
fine-tune on diffusion-inferred segmentations vs implicit posterior [34]segmentation network · EnviroAtlas Phoenix, AZaccuracy (%): 76.2 -> 69.6Hurt
fine-tune on diffusion-inferred segmentations vs implicit posterior [34]segmentation network · EnviroAtlas Durham, NCclass mean IoU (%): 48.4 -> 46.4Hurt
provide weak labels as input to PA supervised modelU-Net · EnviroAtlas Phoenix, AZaccuracy (%): 6.7 -> 62.8Improved

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