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

Uncertainty estimation of the trained deep learning networks is valuable foroptimizing learning efficiency and evaluating the reliability of networkpredictions. In this paper, we propose a method for estimating uncertainty indeep learning image classification using test-time mixup augmentation (TTMA).To improve the ability to distinguish correct and incorrect predictions inexisting aleatoric uncertainty, we introduce the TTMA data uncertainty(TTMA-DU) by applying mixup augmentation to test data and measuring the entropyof the predicted label histogram. In addition to TTMA-DU, we propose the TTMAclass-dependent uncertainty (TTMA-CDU), which captures aleatoric uncertaintyspecific to individual classes and provides insight into class confusion andclass similarity within the trained network. We validate our proposed methodson the ISIC-18 skin lesion diagnosis dataset and the CIFAR-100 real-world imageclassification dataset. Our experiments show that (1) TTMA-DU more effectivelydifferentiates correct and incorrect predictions compared to existinguncertainty measures due to mixup perturbation, and (2) TTMA-CDU providesinformation on class confusion and class similarity for both datasets.

Test-Time Mixup Augmentation for Data and Class-Dependent Uncertainty Estimation in Deep Learning Image Classification