Isotropic Maximization Loss and Entropic Score: Fast, Accurate, Scalable, Unexposed, Turnkey, and Native Neural Networks Out-of-Distribution Detection.

By David Macêdo, Tsang Ing Ren, Cleber Zanchettin, Adriano Oliveira, Alain Tapp, Teresa B Ludermir. 2019

3 citations recorded by the source corpus.

Subfields: Safety, Robustness & Interpretability, Anomaly & Outlier Detection

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Safety, Robustness & Interpretability

1. Shreyas Padhy
2. Balaji Lakshminarayanan
3. Zi Lin
4. Tania Bedrax-Weiss
5. Jeremiah Zhe Liu
6. Dustin Tran

In Anomaly & Outlier Detection

1. Stanislav Fort

Citations in the corpus

• Simple and Principled Uncertainty Estimation with Deterministic Deep Learning via Distance Awareness (2020, methodology): “These are achieved by either replacing the loss function [33, 49, 50, 66, 67], modifying the output layer [6, 70, 11, 48], or computing a closed-form posterior for the last dense layer only [60, 68, 39].”