TY - CONF
T1 - Improved Trainable Calibration Method for Neural Networks on Medical Imaging Classification
AU - Liang, Gongbo
AU - Zhang, Yu
AU - Wang, Xiaoqin
AU - Jacobs, Nathan
N1 - Publisher Copyright:
© 2020. The copyright of this document resides with its authors. It may be distributed unchanged freely in print or electronic forms.
PY - 2020
Y1 - 2020
N2 - Recent works have shown that deep neural networks can achieve super-human performance in a wide range of image classification tasks in the medical imaging domain. However, these works have primarily focused on classification accuracy, ignoring the important role of uncertainty quantification. Empirically, neural networks are often miscalibrated and overconfident in their predictions. This miscalibration could be problematic in any automatic decision-making system, but we focus on the medical field in which neural network miscalibration has the potential to lead to significant treatment errors. We propose a novel calibration approach that maintains the overall classification accuracy while significantly improving model calibration. The proposed approach is based on expected calibration error, which is a common metric for quantifying miscalibration. Our approach can be easily integrated into any classification task as an auxiliary loss term, thus not requiring an explicit training round for calibration. We show that our approach reduces calibration error significantly across various architectures and datasets.
AB - Recent works have shown that deep neural networks can achieve super-human performance in a wide range of image classification tasks in the medical imaging domain. However, these works have primarily focused on classification accuracy, ignoring the important role of uncertainty quantification. Empirically, neural networks are often miscalibrated and overconfident in their predictions. This miscalibration could be problematic in any automatic decision-making system, but we focus on the medical field in which neural network miscalibration has the potential to lead to significant treatment errors. We propose a novel calibration approach that maintains the overall classification accuracy while significantly improving model calibration. The proposed approach is based on expected calibration error, which is a common metric for quantifying miscalibration. Our approach can be easily integrated into any classification task as an auxiliary loss term, thus not requiring an explicit training round for calibration. We show that our approach reduces calibration error significantly across various architectures and datasets.
UR - http://www.scopus.com/inward/record.url?scp=85098419826&partnerID=8YFLogxK
M3 - Paper
AN - SCOPUS:85098419826
T2 - 31st British Machine Vision Conference, BMVC 2020
Y2 - 7 September 2020 through 10 September 2020
ER -