Calibrating Deep Neural Network using Euclidean Distance
This addresses reliability issues in machine learning models, particularly for high-stakes applications like healthcare, though it is incremental as it builds on existing loss functions.
The paper tackles the problem of poor probability calibration in deep neural networks, which leads to overconfident or underconfident predictions, by introducing Focal Calibration Loss (FCL) to improve calibration while maintaining accuracy, achieving state-of-the-art performance in both metrics.
Uncertainty is a fundamental aspect of real-world scenarios, where perfect information is rarely available. Humans naturally develop complex internal models to navigate incomplete data and effectively respond to unforeseen or partially observed events. In machine learning, Focal Loss is commonly used to reduce misclassification rates by emphasizing hard-to-classify samples. However, it does not guarantee well-calibrated predicted probabilities and may result in models that are overconfident or underconfident. High calibration error indicates a misalignment between predicted probabilities and actual outcomes, affecting model reliability. This research introduces a novel loss function called Focal Calibration Loss (FCL), designed to improve probability calibration while retaining the advantages of Focal Loss in handling difficult samples. By minimizing the Euclidean norm through a strictly proper loss, FCL penalizes the instance-wise calibration error and constrains bounds. We provide theoretical validation for proposed method and apply it to calibrate CheXNet for potential deployment in web-based health-care systems. Extensive evaluations on various models and datasets demonstrate that our method achieves SOTA performance in both calibration and accuracy metrics.