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 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.
Code (3)
Similar Papers 제목 키워드 기반
Diverse Gaussian Noise Consistency Regularization for Robustness and Uncertainty Calibration
Deep neural networks achieve high prediction accuracy when the train and test distributions coincide. In practice though, various types of corruptions occur which deviate from this setup and cause severe performance degr…
Data AugmentationImage ClassificationFrequency-Based Vulnerability Analysis of Deep Learning Models against Image Corruptions
Deep learning models often face challenges when handling real-world image corruptions. In response, researchers have developed image corruption datasets to evaluate the performance of deep neural networks in handling suc…
ClassificationRobust classificationAR2: Attention-Guided Repair for the Robustness of CNNs Against Common Corruptions
Deep neural networks suffer from significant performance degradation when exposed to common corruptions such as noise, blur, weather, and digital distortions, limiting their reliability in real-world applications. In thi…
Fourier-Based Augmentations for Improved Robustness and Uncertainty Calibration
Diverse data augmentation strategies are a natural approach to improving robustness in computer vision models against unforeseen shifts in data distribution. However, the ability to tailor such strategies to inoculate a …
Data AugmentationImage AugmentationPDA: Progressive Data Augmentation for General Robustness of Deep Neural Networks
Adversarial images are designed to mislead deep neural networks (DNNs), attracting great attention in recent years. Although several defense strategies achieved encouraging robustness against adversarial samples, most of…
Data Augmentation