AI Paper Atlas

Research map / Learning theory and algorithms / Prediction and decision losses

Large-Scale Robust Deep AUC Maximization: A New Surrogate Loss and Empirical Studies on Medical Image Classification

Zhuoning Yuan, Yan Yan, Milan Sonka, Tianbao Yang

ICCV 2021 · Learning theory and algorithms › Prediction and decision losses · approach: Ranking-based loss optimization · 155 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
use AUC margin loss instead of AUC square lossDAM · C10 (imratio 1%, DenseNet121)test AUC: 0.745 -> 0.760Improved
use AUC margin loss instead of AUC square lossDAM · S10 (imratio 1%, DenseNet121)test AUC: 0.669 -> 0.703Improved
use AUC margin loss instead of cross-entropyDenseNet121 · C2 (imratio 1%)test AUC: 0.718 -> 0.809Improved
use AUC margin loss instead of cross-entropy at imratio 10%ResNet20 · C10 (imratio 10%)test AUC: 0.898 -> 0.898No clear effect
use AUC margin loss instead of cross-entropy at imratio 10%DenseNet121 · C10 (imratio 10%)test AUC: 0.898 -> 0.887Hurt
use AUC margin loss instead of AUC square lossDAM · Melanoma private (w/ TTA 30)test AUC: 0.9364 -> 0.9393Improved
add patient metadata networkDAM AUC-M · Melanoma private (w/ TTA 30)test AUC: 0.9393 -> 0.9423Improved
use AUC margin loss instead of cross-entropyEfficientNet-B5 · Melanoma private (w/ TTA 30)test AUC: 0.9345 -> 0.9393Improved
use AUC margin loss instead of cross-entropyDenseNet121 · PatchCamelyon (imratio 1%)test AUC: 0.8394 -> 0.8896Improved
add batch score normalization (ablation)DAM DenseNet121 · benchmark datasets (imratio 1% and 10%)test AUCImproved
use AUC margin loss instead of AUC square loss with noisy and easy data added (ablation)DAM DenseNet121 · C2-IB with noisy and easy datatest AUCImproved
add non-negative constraint on alpha (ablation)AUC-M · C2-IB (imratio 1%, 40% easy and 1% noisy added)test AUCImproved

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