G4 - Test-Time Mixup Augmentation for Uncertainty Estimation in Skin Lesion Diagnosis
Hansang Lee, Haeil Lee, Helen Hong, Junmo Kim
Uncertainty is considered to be an important measure that provides valuable information on the learning behavior of deep neural networks. In this paper, we propose an uncertainty estimation method using test-time mixup augmentation (TTMA). The TTMA uncertainty is obtained by replacing affine augmentation with the mixup in the existing test-time augmentation (TTA) method. In addition to the data uncertainty, we propose TTMA-based class-specific uncertainty, which can provide information on between-class confusion. In experiments on the skin lesion diagnosis dataset, we confirmed that the proposed TTMA not only provides better epistemic uncertainty than TTA but also provides information on between-class confusion through class-specific uncertainty.
Thursday 8th July
G1-9 (short): Interpretability and Explainable AI - 16:45 - 17:30 (UTC+2)