A simple way to make neural networks robust against diverse image corruptions
The human visual system is remarkably robust against a wide range of naturally occurring
variations and corruptions like rain or snow. In contrast, the performance of modern image …
variations and corruptions like rain or snow. In contrast, the performance of modern image …
[PDF][PDF] Increasing the robustness of dnns against im-age corruptions by playing the game of noise
The human visual system is remarkably robust against a wide range of naturally occurring
variations and corruptions like rain or snow. In contrast, the performance of modern image …
variations and corruptions like rain or snow. In contrast, the performance of modern image …
Defending against image corruptions through adversarial augmentations
Modern neural networks excel at image classification, yet they remain vulnerable to common
image corruptions such as blur, speckle noise or fog. Recent methods that focus on this …
image corruptions such as blur, speckle noise or fog. Recent methods that focus on this …
Benchmarking neural network robustness to common corruptions and surface variations
D Hendrycks, TG Dietterich - arXiv preprint arXiv:1807.01697, 2018 - arxiv.org
In this paper we establish rigorous benchmarks for image classifier robustness. Our first
benchmark, ImageNet-C, standardizes and expands the corruption robustness topic, while …
benchmark, ImageNet-C, standardizes and expands the corruption robustness topic, while …
Revisiting batch normalization for improving corruption robustness
The performance of DNNs trained on clean images has been shown to decrease when the
test images have common corruptions. In this work, we interpret corruption robustness as a …
test images have common corruptions. In this work, we interpret corruption robustness as a …
Enhanced robustness of convolutional networks with a push–pull inhibition layer
Convolutional neural networks (CNNs) lack robustness to test image corruptions that are not
seen during training. In this paper, we propose a new layer for CNNs that increases their …
seen during training. In this paper, we propose a new layer for CNNs that increases their …
Improving robustness against common corruptions with frequency biased models
CNNs perform remarkably well when the training and test distributions are iid, but unseen
image corruptions can cause a surprisingly large drop in performance. In various real …
image corruptions can cause a surprisingly large drop in performance. In various real …
Benchmarking neural network robustness to common corruptions and perturbations
D Hendrycks, T Dietterich - arXiv preprint arXiv:1903.12261, 2019 - arxiv.org
In this paper we establish rigorous benchmarks for image classifier robustness. Our first
benchmark, ImageNet-C, standardizes and expands the corruption robustness topic, while …
benchmark, ImageNet-C, standardizes and expands the corruption robustness topic, while …
Smoothmix: a simple yet effective data augmentation to train robust classifiers
Data augmentation has been proven effective which, by preventing overfitting, can not only
enhances the performance of a deep neural network but also leads to a better …
enhances the performance of a deep neural network but also leads to a better …
A systematic review of robustness in deep learning for computer vision: Mind the gap?
Deep neural networks for computer vision are deployed in increasingly safety-critical and
socially-impactful applications, motivating the need to close the gap in model performance …
socially-impactful applications, motivating the need to close the gap in model performance …