DeepAI
Log In Sign Up

Increasing the robustness of DNNs against image corruptions by playing the Game of Noise

01/16/2020
by   Evgenia Rusak, et al.
14

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 recognition models strongly degrades when evaluated on previously unseen corruptions. Here, we demonstrate that a simple but properly tuned training with additive Gaussian and Speckle noise generalizes surprisingly well to unseen corruptions, easily reaching the previous state of the art on the corruption benchmark ImageNet-C (with ResNet50) and on MNIST-C. We build on top of these strong baseline results and show that an adversarial training of the recognition model against uncorrelated worst-case noise distributions leads to an additional increase in performance. This regularization can be combined with previously proposed defense methods for further improvement.

READ FULL TEXT

page 3

page 12

page 27

page 29

page 30

05/13/2018

Curriculum Adversarial Training

Recently, deep learning has been applied to many security-sensitive appl...
11/21/2019

Adversarial Examples Improve Image Recognition

Adversarial examples are commonly viewed as a threat to ConvNets. Here w...
10/11/2022

Boosting Adversarial Robustness From The Perspective of Effective Margin Regularization

The adversarial vulnerability of deep neural networks (DNNs) has been ac...
05/28/2021

SafeAMC: Adversarial training for robust modulation recognition models

In communication systems, there are many tasks, like modulation recognit...
03/08/2021

Consistency Regularization for Adversarial Robustness

Adversarial training (AT) is currently one of the most successful method...
06/05/2019

MNIST-C: A Robustness Benchmark for Computer Vision

We introduce the MNIST-C dataset, a comprehensive suite of 15 corruption...

Code Repositories

game-of-noise

Trained model weights, training and evaluation code from the paper "Increasing the robustness of DNNs against image corruptions by playing the Game of Noise"


view repo