Balancing Two Classifiers via A Simplex ETF Structure for Model Calibration
This work addresses calibration problems in deep learning for safety-critical domains like autonomous driving and healthcare, offering a novel solution that is incremental in its approach.
The paper tackles model calibration issues in deep neural networks, which cause unreliable predictions in safety-critical applications, by proposing a method that balances learnable and ETF classifiers to address overconfidence or underconfidence, resulting in significant improvements in calibration performance while maintaining high predictive accuracy.
In recent years, deep neural networks (DNNs) have demonstrated state-of-the-art performance across various domains. However, despite their success, they often face calibration issues, particularly in safety-critical applications such as autonomous driving and healthcare, where unreliable predictions can have serious consequences. Recent research has started to improve model calibration from the view of the classifier. However, the exploration of designing the classifier to solve the model calibration problem is insufficient. Let alone most of the existing methods ignore the calibration errors arising from underconfidence. In this work, we propose a novel method by balancing learnable and ETF classifiers to solve the overconfidence or underconfidence problem for model Calibration named BalCAL. By introducing a confidence-tunable module and a dynamic adjustment method, we ensure better alignment between model confidence and its true accuracy. Extensive experimental validation shows that ours significantly improves model calibration performance while maintaining high predictive accuracy, outperforming existing techniques. This provides a novel solution to the calibration challenges commonly encountered in deep learning.