English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Deep AUC Maximization (DAM) is a new paradigm for learning a deep neuralnetwork by maximizing the AUC score of the model on a dataset. Most previousworks of AUC maximization focus on the perspective of optimization by designingefficient stochastic algorithms, and studies on generalization performance oflarge-scale DAM on difficult tasks are missing. In this work, we aim to makeDAM more practical for interesting real-world applications (e.g., medical imageclassification). First, we propose a new margin-based min-max surrogate lossfunction for the AUC score (named as AUC min-max-margin loss or simply AUCmargin loss for short). It is more robust than the commonly used AUC squareloss, while enjoying the same advantage in terms of large-scale stochasticoptimization. Second, we conduct extensive empirical studies of our DAM methodon four difficult medical image classification tasks, namely (i) classificationof chest x-ray images for identifying many threatening diseases, (ii)classification of images of skin lesions for identifying melanoma, (iii)classification of mammogram for breast cancer screening, and (iv)classification of microscopic images for identifying tumor tissue. Our studiesdemonstrate that the proposed DAM method improves the performance of optimizingcross-entropy loss by a large margin, and also achieves better performance thanoptimizing the existing AUC square loss on these medical image classificationtasks. Specifically, our DAM method has achieved the 1st place on StanfordCheXpert competition on Aug. 31, 2020. To the best of our knowledge, this isthe first work that makes DAM succeed on large-scale medical image datasets. Wealso conduct extensive ablation studies to demonstrate the advantages of thenew AUC margin loss over the AUC square loss on benchmark datasets. Theproposed method is implemented in our open-sourced library LibAUC(www.libauc.org).

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