Deep convolutional neural networks (DCNNs) have revolutionized computer vision and are often advocated as good models of the human visual system. However, there are currently many shortcomings of DCNNs, which preclude them as a model of human vision. There are continuous attempts to use features of the human visual system to improve the robustness of neural networks to data perturbations. We provide a detailed analysis of such bio-inspired models and their properties. To this end, we benchmark the robustness of several bio-inspired models against their most comparable baseline DCNN models. We find that bio-inspired models tend to be adversarially robust without requiring any special data augmentation. Additionally, we find that bio-inspired models beat adversarially trained models in the presence of more real-world common corruptions. Interestingly, we also find that bio-inspired models tend to use both low and mid-frequency information, in contrast to other DCNN models. We find that this mix of frequency information makes them robust to both adversarial perturbations and common corruptions.
翻译:深相神经网络(DCNNS)已经使计算机视野发生革命,并常常被提倡为人类视觉系统的良好模型。然而,DCNNS目前有许多缺点,无法把它们作为人类视觉的模型。有人不断试图利用人类视觉系统的特征来提高神经网络对数据扰动的坚固性。我们对这种生物启发模型及其特性进行了详细分析。为此,我们参照其最可比较的DCNN模型,将一些生物启发模型的坚固性作为基准基准。我们发现,生物启发模型往往具有对抗性强力,而不需要任何特殊的数据增强。此外,我们发现,在更现实世界常见的腐败面前,由生物启发的模型战胜了经过对抗训练的模型。有趣的是,我们还发现,生物启发模型往往使用低频和中频信息,而其他的模型则不同。我们发现,这种频率信息组合使得这些模型既具有对抗性,又具有共同的腐败。