Universal Adversarial Perturbations to Understand Robustness of Texture vs. Shape-biased Training

Convolutional Neural Networks (CNNs) used on image classification tasks such as ImageNet have been shown to be biased towards recognizing textures rather than shapes. Recent work has attempted to alleviate this by augmenting the training dataset with shape-based examples to create Stylized-ImageNet. However, in this paper we show that models trained on this dataset remain vulnerable to Universal Adversarial Perturbations (UAPs). We use UAPs to evaluate and compare the robustness of CNN models with varying degrees of shape-based training. We also find that a posteriori fine-tuning on ImageNet negates features learned from training on Stylized-ImageNet. This study reveals an important limitation and reiterates the need for further research into understanding the robustness of CNNs for visual recognition.