LS+: Informed Label Smoothing for Improving Calibration in Medical Image Classification

Deep Neural Networks (DNNs) exhibit exceptional performance in various tasks; however, their susceptibility to miscalibration poses challenges in healthcare applications, impacting reliability and trustworthiness. Label smoothing, which prefers soft targets based on uniform distribution over labels, is a widely used strategy to improve model calibration. We propose an improved strategy, Label Smoothing Plus (LS \(+\) ), which uses class-specific prior that is estimated from validation set to account for current model calibration level. We evaluate the effectiveness of our approach by comparing it with state-of-the-art methods on three benchmark medical imaging datasets, using two different architectures and several performance and calibration metrics for the classification task. Experimental results show notable reduction in calibration error metrics with nominal improvement in performance compared to other approaches, suggesting that our proposed method provides more reliable prediction probabilities. Code is available at https://github.com/abhisheksambyal/lsplus .