CEB Improves Model Robustness

Authors: Ian Fischer, Alexander A. Alemi
Published: 2020-02-13

Source: https://arxiv.org/abs/2002.05380

PDF: https://arxiv.org/pdf/2002.05380

Labels Predicted by AI

ロバスト性評価 ポイズニング モデル選択手法

Please note that these labels were automatically added by AI. Therefore, they may not be entirely accurate.
For more details, please see the About the Literature Database page.

Abstract

We demonstrate that the Conditional Entropy Bottleneck (CEB) can improve model robustness. CEB is an easy strategy to implement and works in tandem with data augmentation procedures. We report results of a large scale adversarial robustness study on CIFAR-10, as well as the ImageNet-C Common Corruptions Benchmark, ImageNet-A, and PGD attacks.