Bio-inspired Robustness: A Review
Not on the map. Why?
Abstract (arXiv)
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.
Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Builds on 32 of its 96 references that are in the map. First posted on arXiv 16 Mar 2021.
Builds on
32 of 96 references.
References · 32
- 2015Deep Residual Learning for Image Recognitioncited by 51,809
- 2017Mask R-CNNcited by 7,259
- 2016Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localizationcited by 6,690
- 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,326
- 2016Towards Evaluating the Robustness of Neural Networkscited by 2,976
- 2016Adversarial examples in the physical worldcited by 1,762
- 2015DeepFool: a simple and accurate method to fool deep neural networkscited by 1,315
- 2018Obfuscated Gradients Give a False Sense of Security: Circumventing Defenses to Adversarial Examplescited by 1,259
- 2019StarGAN v2: Diverse Image Synthesis for Multiple Domainscited by 1,095
- 2019Adversarial Examples Are Not Bugs, They Are Featurescited by 950
- 2018Robustness May Be at Odds with Accuracycited by 873
- 2020On Adaptive Attacks to Adversarial Example Defensescited by 547
20 more
- 2017Decision-Based Adversarial Attacks: Reliable Attacks Against Black-Box Machine Learning Modelscited by 459
- 2018Threat of Adversarial Attacks on Deep Learning in Computer Vision: A Surveycited by 459
- 2020Do Adversarially Robust ImageNet Models Transfer Better?cited by 315
- 2018Feature Denoising for Improving Adversarial Robustnesscited by 312
- 2019Adversarial Examples Improve Image Recognitioncited by 283
- 2019Adversarial Training and Robustness for Multiple Perturbationscited by 182
- 2016Robustness of classifiers: from adversarial to random noisecited by 87
- 2020Beyond accuracy: quantifying trial-by-trial behaviour of CNNs and humans by measuring error consistencycited by 77
- 2018Adversarial Examples that Fool both Computer Vision and Time-Limited Humanscited by 73
- 2019Adversarially robust transfer learningcited by 66
- 2019Recurrence is required to capture the representational dynamics of the human visual systemcited by 58
- 2019Accurate, reliable and fast robustness evaluationcited by 43
- 2019Are Perceptually-Aligned Gradients a General Property of Robust Classifiers?cited by 42
- 2019Learning From Brains How to Regularize Machinescited by 37
- 2019Robust Local Features for Improving the Generalization of Adversarial Trainingcited by 30
- 2020Biologically Inspired Mechanisms for Adversarial Robustnesscited by 29
- 2020Optimism in the Face of Adversity: Understanding and Improving Deep Learning through Adversarial Robustnesscited by 28
- 2019Towards Robust Image Classification Using Sequential Attention Modelscited by 27
- 2020Crowding Reveals Fundamental Differences in Local vs. Global Processing in Humans and Machinescited by 9
- 2019Dropping Pixels for Adversarial Robustnesscited by 4
Built on by
Citing papers per year: 2022: 1.
1 paper.