The prediction reliability of neural networks is important in many applications. Specifically, in safety-critical domains, such as cancer prediction or autonomous driving, a reliable confidence of model's prediction is critical for the interpretation of the results. Modern deep neural networks have achieved a significant improvement in performance for many different image classification tasks. However, these networks tend to be poorly calibrated in terms of output confidence. Temperature scaling is an efficient post-processing-based calibration scheme and obtains well calibrated results. In this study, we leverage the concept of temperature scaling to build a sophisticated bin-wise scaling. Furthermore, we adopt augmentation of validation samples for elaborated scaling. The proposed methods consistently improve calibration performance with various datasets and deep convolutional neural network models.
@article{arxiv.1908.11528,
title = {Bin-wise Temperature Scaling (BTS): Improvement in Confidence Calibration Performance through Simple Scaling Techniques},
author = {Byeongmoon Ji and Hyemin Jung and Jihyeun Yoon and Kyungyul Kim and Younghak Shin},
journal= {arXiv preprint arXiv:1908.11528},
year = {2019}
}