Deep learning has achieved the state-of-the-art performance across medical imaging tasks; however, model calibration is often not considered. Uncalibrated models are potentially dangerous in high-risk applications since the user does not know when they will fail. Therefore, this paper proposes a novel domain-aware loss function to calibrate deep learning models. The proposed loss function applies a class-wise penalty based on the similarity between classes within a given target domain. Thus, the approach improves the calibration while also ensuring that the model makes less risky errors even when incorrect. The code for this software is available at https://github.com/lab-smile/DOMINO.
@article{arxiv.2302.05142,
title = {DOMINO: Domain-aware Loss for Deep Learning Calibration},
author = {Skylar E. Stolte and Kyle Volle and Aprinda Indahlastari and Alejandro Albizu and Adam J. Woods and Kevin Brink and Matthew Hale and Ruogu Fang},
journal= {arXiv preprint arXiv:2302.05142},
year = {2023}
}
Comments
7 pages, 1 figure, 1 table, accepted by the Software Impacts journal