Bio-inspired Robustness: A Review

TL;DR

This review examines the robustness of deep convolutional neural networks (DCNNs) inspired by human vision, analyzing various models and proposing criteria for evaluating their effectiveness against adversarial attacks.

Contribution

The paper introduces evaluation criteria for human vision-inspired models and analyzes their effectiveness in improving DCNN robustness.

Findings

Current human-inspired models show inconclusive improvements in robustness.

Proper evaluation criteria are essential for assessing model effectiveness.

Future research directions are proposed to enhance DCNNs towards human-like vision.

Abstract

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. For example, in the case of adversarial attacks, where adding small amounts of noise to an image, including an object, can lead to strong misclassification of that object. But for humans, the noise is often invisible. If vulnerability to adversarial noise cannot be fixed, DCNNs cannot be taken as serious models of human vision. Many studies have tried to add features of the human visual system to DCNNs to make them robust against adversarial attacks. However, it is not fully clear whether human vision inspired components increase robustness because performance evaluations of these novel components in DCNNs are often inconclusive. We propose a set of criteria for proper evaluation and analyze different models according to these criteria. We finally sketch future efforts to make DCCNs one step closer to the model of human vision.