论文标题
生物启发的模型的经验倡导，以实现强大图像识别
Empirical Advocacy of Bio-inspired Models for Robust Image Recognition
论文作者
论文摘要
深度卷积神经网络（DCNN）已彻底改变了计算机视觉，并经常被提倡作为人类视觉系统的良好模型。但是，目前有许多DCNN的缺点，这些缺点排除了它们作为人类视野的模型。有持续尝试使用人类视觉系统的特征来改善神经网络的鲁棒性到数据扰动。我们提供了此类生物启发的模型及其特性的详细分析。为此，我们对几种生物启发的模型的鲁棒性对其最可比的基线DCNN模型进行了基准测试。我们发现，生物启发的模型在不需要任何特殊数据增强的情况下往往具有对抗性。此外，我们发现，在存在更真实的常见腐败的情况下，以生物启发的模型击败了受对抗训练的模型。有趣的是，我们还发现，与其他DCNN模型相比，以生物启发的模型倾向于同时使用低频和中频信息。我们发现，这种频率信息的组合使它们对对抗性扰动和常见损坏都具有鲁棒性。
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.
