AI Paper Atlas

Research map / Label-efficient and robust learning / Recognition and long-tail

Learning With Unsure Data for Medical Image Diagnosis

Botong Wu, Xinwei Sun, Lingjing Hu, Yizhou Wang

ICCV 2019 · Label-efficient and robust learning › Recognition and long-tail · approach: Group-robust classification · 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
add cost-sensitive parameters to UDM (ablation)UDM · LIDC-IDRImacro-F1: 69.34 -> 71.47Improved
add cost-sensitive parameters to UDM (ablation)UDM · ADNImacro-F1: 39.63 -> 40.91Improved
add conservative-aggressive strategy parameters to UDM+CS (ablation)UDM+CS · LIDC-IDRIF-beta macro (c-a): 71.47 -> 73.61Improved
add conservative-aggressive strategy parameters to UDM+CS (ablation)UDM+CS · ADNIF-beta macro (c-a): 38.38 -> 49.41Improved
add conservative-conservative strategy parameters to UDM+CS (ablation)UDM+CS · LIDC-IDRIF-beta macro (c-c): 67.87 -> 68.72Improved
add conservative-conservative strategy parameters to UDM+CS (ablation)UDM+CS · ADNIF-beta macro (c-c): 39.68 -> 42.03Improved
model unsure data as ordinal class (UDM) instead of cross-entropyDenseNet-3D · LIDC-IDRImacro-F1: 65.60 -> 69.34Improved
model unsure data as ordinal class (UDM) instead of cross-entropyDenseNet-3D · ADNImacro-F1: 32.62 -> 39.63Improved
train with unsure data instead of binary classifier without itUDM+CS+CA · ADNI sure datamacro-F1: 79.13 -> 84.95Improved
train with unsure data instead of binary classifier without itUDM+CS+CA · LIDC-IDRI sure datamacro-F1: 88.54 -> 88.92Improved
add cost-sensitive parameters to UDM (ablation)UDM · LIDC-IDRInumber predicted as unsure: 467 -> 446Improved
add c-a strategy parameters (gamma) (ablation)UDM+CS · LIDC-IDRInumber predicted positive: 153 -> 185Improved

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