Elucidating robust learning with uncertainty-aware corruption pattern estimation

•We propose a simple yet effective robust learning method leveraging a mixture-of-experts model on various noise settings.•The proposed method can not only robustly learn from noisy data but can also discover the setdependent underlying noise pattern (i.e., the noise transition matrix) as well as the two types of predictive uncertainties (i.e., aleatoric and epistemic uncertainty) within the dataset.•We present a novel evaluation scheme for validating the set-dependent corruption pattern estimation performance. 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 successfully 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 uncertainty 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 corruption 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.