research
∙
04/06/2023
Logistic-Normal Likelihoods for Heteroscedastic Label Noise in Classification
A natural way of estimating heteroscedastic label noise in regression is...
research
∙
09/21/2022
Deep Double Descent via Smooth Interpolation
Overparameterized deep networks are known to be able to perfectly fit th...
research
∙
10/04/2021
Consistency Regularization Can Improve Robustness to Label Noise
Consistency regularization is a commonly-used technique for semi-supervi...
research
∙
05/10/2021
Generalized Jensen-Shannon Divergence Loss for Learning with Noisy Labels
We propose two novel loss functions based on Jensen-Shannon divergence f...
research
∙
06/12/2019