Empirical Advocacy of Bio-inspired Models for Robust Image Recognition
This work addresses robustness issues in computer vision for applications requiring reliable performance under data perturbations, but it is incremental as it builds on existing bio-inspired approaches.
The paper tackled the problem of improving robustness in image recognition by analyzing bio-inspired models, finding that they outperform baseline deep convolutional neural networks and adversarially trained models in adversarial robustness and real-world corruptions without special data augmentation.
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.