3 citations · 7 across the 4 of their papers we have counts for
4 papers · 1 filter
On Spectral Properties of Gradient-based Explanation Methods
Amir Mehrpanah, Erik Englesson, Hossein Azizpour
Understanding the behavior of deep networks is crucial to increase our confidence in their results. Despite an extensive body of work for explaining their predictions, researchers…
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…
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)…
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…