AI Paper Atlas

Research map / Image generation / Autoregressive and latent generation

CONAN: Complementary Pattern Augmentation for Rare Disease Detection

Limeng Cui, Siddharth Biswal, Lucas M. Glass, Greg Lever, Jimeng Sun, Cao Xiao

AAAI 2020 · Image generation › Autoregressive and latent generation · approach: Generalizable fake image detection · 39 citations (OpenAlex)

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
use CONAN instead of medGANRare and low-prevalence disease detection · IBDPR-AUC: 0.6385 -> 0.9584Improved
use CONAN instead of nnPURare and low-prevalence disease detection · IPFPR-AUC: 0.1578 -> 0.2229Improved
use CONAN instead of SMOTE_LRImbalanced disease detection · NASHPR-AUC: 0.6123 -> 0.6186Improved
add GAN-based augmentation to the hierarchical patient embedding network (ablation)CONAN · IBDPR-AUC: 0.8097 -> 0.9584Improved
add GAN-based augmentation to the hierarchical patient embedding network (ablation)CONAN · IPFPR-AUC: 0.1796 -> 0.2229Improved
replace regular GAN augmentation with complementary GAN augmentation (ablation)CONAN · IBDPR-AUC: 0.9323 -> 0.9584Improved
replace regular GAN augmentation with complementary GAN augmentation (ablation)CONAN · IPFPR-AUC: 0.2023 -> 0.2229Improved

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