AI Paper Atlas

Research map / Probabilistic and scientific modeling / Uncertainty and Gaussian processes

CARD: Classification and Regression Diffusion Models

Xizewen Han, Huangjie Zheng, Mingyuan Zhou

NeurIPS 2022 · Probabilistic and scientific modeling › Uncertainty and Gaussian processes · approach: Priors and functional variational uncertainty · 33 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
wrap a pre-trained classifier with CARD diffusion and majority voteResNet-18 classifier · CIFAR-10accuracy (%): 90.39 -> 90.93Improved
wrap a pre-trained classifier with CARD diffusionLeNet classifier · FashionMNISTaccuracy (%): 91.12 -> 91.79Improved
use CARD diffusion instead of Deep Ensemblesregression · UCI Kin8nmRMSE: 8.65 -> 6.32Improved
use CARD diffusion instead of MC Dropoutregression · UCI WineRMSE: 0.62 -> 0.63No clear effect
use CARD diffusion instead of Deep Ensemblesregression · UCI ConcreteNLL: 2.93 -> 2.96No clear effect
use CARD diffusion instead of PBP/MC Dropoutregression · UCI WineQICE (%): 2.79 -> 3.39Hurt
use CARD diffusion instead of MC Dropoutregression · UCI NavalQICE (%): 12.50 -> 0.80Improved
use CARD instead of CM-MF-VI BNNclassification · CIFAR-10NLL: 0.39 -> 0.46Hurt
use CARD instead of MAPclassification · CIFAR-10accuracy (%): 84.69 -> 90.93Improved
pick class by narrowest PIW rather than majority vote (ablation)CARD · CIFAR-10accuracy (%): 90.93 -> 87.84Hurt

Later papers that compared with this method

4 later accepted papers report CARD as a baseline in their results tables; 2 of them report a better number on most of the results they share with it.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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