Robust deep learning object recognition models rely on low frequency information in natural images

Zhe Li, Josue Ortega Caro, Evgenia Rusak, Wieland Brendel, Matthias Bethge, Fabio Anselmi, Ankit B. Patel, Andreas S. Tolias, Xaq Pitkow

Abstract: Author summary Though artificial intelligence has achieved high performance on various vision tasks, its ability to generalize to out-of-distribution data is limited. Most remarkably, machine learning models are extremely sensitive to input perturbations such as adversarial attacks and common corruptions. Previous studies have observed that imposing an inductive bias towards brain-like representations can improve the robustness of models, but the reasons underlying this benefit were left unknown. In this work, we propose and test the hypothesis that the robustness of brain-like models can be accounted for by a low frequency feature preference inherited from the neural representation. We designed a novel machine learning task to probe the frequency bias of different models and observed a strong correlation between that and model robustness. We believe this work serves as a first step towards understanding why biological visual systems generalize well to out-of-distribution data and provides an explanation for the robustness of state-of-the-art machine learning models trained with various methods. It also opens the door to applying computational principles of the brain in artificial intelligence, hence helping to overcome the fundamental difficulties faced by current AI methods.