Geometric Insights into Focal Loss: Reducing Curvature for Enhanced Model Calibration

arXiv:2405.00442v1 Announce Type: cross
Abstract: The key factor in implementing machine learning algorithms in decision-making situations is not only the accuracy of the model but also its confidence level. The confidence level of a model in a classification problem is often given by the output vector of a softmax function for convenience. However, these values are known to deviate significantly from the actual expected model confidence. This problem is called model calibration and has been studied extensively. One of the …

abstract accuracy algorithms arxiv calibration classification confidence cs.ai cs.lg decision insights key loss machine machine learning machine learning algorithms making softmax stat.ml the key type vector