TEDL: A Two-stage Evidential Deep Learning Method for Classification Uncertainty Quantification. (arXiv:2209.05522v1 [cs.LG])

In this paper, we propose TEDL, a two-stage learning approach to quantify
uncertainty for deep learning models in classification tasks, inspired by our
findings in experimenting with Evidential Deep Learning (EDL) method, a
recently proposed uncertainty quantification approach based on the
Dempster-Shafer theory. More specifically, we observe that EDL tends to yield
inferior AUC compared with models learnt by cross-entropy loss and is highly
sensitive in training. Such sensitivity is likely to cause unreliable
uncertainty estimation, making it risky for …

arxiv classification deep learning quantification stage uncertainty