Elucidating robust learning with uncertainty-aware corruption pattern estimation

Robust learning methods aim to learn a clean target distribution from noisy and corrupted training data where a specific corruption pattern is often assumed a priori. Our proposed method can not only success-fully learn the clean target distribution from a dirty dataset but also can estimate the underlying noise pattern. To this end, we leverage a mixture-of-experts model that can distinguish two different types of predictive uncertainty, aleatoric and epistemic uncertainty. We show that the ability to estimate the un-certainty plays a significant role in elucidating the corruption patterns as these two objectives are tightly intertwined. We also present a novel validation scheme for evaluating the performance of the corrup-tion pattern estimation. Our proposed method is extensively assessed in terms of both robustness and corruption pattern estimation in the computer vision domain. Code has been made publicly available at https://github.com/jeongeun980906/Uncertainty-Aware-Robust-Learning . (c) 2023 The Authors. Published by Elsevier Ltd. This is an open access article under the CC BY license ( http://creativecommons.org/licenses/by/4.0/ )

Automated summary

This article proposes a robust learning method that can learn a clean target distribution from noisy and corrupted training data while estimating the underlying noise pattern. By using a mixture-of-experts model to distinguish different types of predictive uncertainty, it demonstrates the importance of estimating uncertainty in elucidating corruption patterns. The article also introduces a novel validation scheme for evaluating the performance of corruption pattern estimation. The proposed method is extensively assessed in the field of computer vision.