3 citations · 5 across the 2 of their papers we have counts for
3 papers
cs.LG2021★ 2 cited
Consistency Regularization Can Improve Robustness to Label Noise
Erik Englesson, Hossein Azizpour
Consistency regularization is a commonly-used technique for semi-supervised and self-supervised learning. It is an auxiliary objective function that encourages the prediction of th…
cs.LG2021
Generalized Jensen-Shannon Divergence Loss for Learning with Noisy Labels
Erik Englesson, Hossein Azizpour
Prior works have found it beneficial to combine provably noise-robust loss functions e.g., mean absolute error (MAE) with standard categorical loss function e.g. cross entropy (CE)…
cs.LG2019★ 3 cited
Efficient Evaluation-Time Uncertainty Estimation by Improved Distillation
Erik Englesson, Hossein Azizpour
In this work we aim to obtain computationally-efficient uncertainty estimates with deep networks. For this, we propose a modified knowledge distillation procedure that achieves sta…