Search Results for author:
Found 5 papers, 1 papers with code
Using Synthetic Corruptions to Measure Robustness to Natural Distribution Shifts
Using the overlapping criterion, we split synthetic corruptions into categories that help to better understand neural network robustness.
Using the Overlapping Score to Improve Corruption Benchmarks
To estimate the robustness of neural networks to these common corruptions, we generally use a group of modeled corruptions gathered into a benchmark.
Increasing the Coverage and Balance of Robustness Benchmarks by Using Non-Overlapping Corruptions
In this paper, we propose to build corruption benchmarks with only non-overlapping corruptions, to improve their coverage and their balance.
Addressing Neural Network Robustness with Mixup and Targeted Labeling Adversarial Training
Despite their performance, Artificial Neural Networks are not reliable enough for most of industrial applications.
Are Adversarial Robustness and Common Perturbation Robustness Independent Attributes ?
We intend to study the links between the robustnesses of neural networks to both perturbations.
