mlsanityData to 14 Oct 2026

Combining Different V1 Brain Model Variants to Improve Robustness to Image Corruptions in CNNs

arXiv 2110.10645 ↗First posted 20 Oct 2021eess.IV cs.CV q-bio.NCcited by 5

Not on the map. Why?

Abstract (arXiv)

While some convolutional neural networks (CNNs) have surpassed human visual abilities in object classification, they often struggle to recognize objects in images corrupted with different types of common noise patterns, highlighting a major limitation of this family of models. Recently, it has been shown that simulating a primary visual cortex (V1) at the front of CNNs leads to small improvements in robustness to these image perturbations. In this study, we start with the observation that different variants of the V1 model show gains for specific corruption types. We then build a new model using an ensembling technique, which combines multiple individual models with different V1 front-end variants. The model ensemble leverages the strengths of each individual model, leading to significant improvements in robustness across all corruption categories and outperforming the base model by 38% on average. Finally, we show that using distillation, it is possible to partially compress the knowledge in the ensemble model into a single model with a V1 front-end. While the ensembling and distillation techniques used here are hardly biologically-plausible, the results presented here demonstrate that by combining the specific strengths of different neuronal circuits in V1 it is possible to improve the robustness of CNNs for a wide range of perturbations.

Key facts. Cited by 5 papers in the map (data through 14 Oct 2026). Builds on 31 of its 57 references that are in the map. First posted on arXiv 20 Oct 2021.

Builds on

31 of 57 references.

References · 31

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,364
  3. 2015Distilling the Knowledge in a Neural Networkcited by 10,324
  4. 2013Intriguing properties of neural networkscited by 5,155
  5. 2014Going Deeper with Convolutionscited by 4,241
  6. 2016Simple and Scalable Predictive Uncertainty Estimation using Deep Ensemblescited by 3,926
  7. 2019Benchmarking Neural Network Robustness to Common Corruptions and Perturbationscited by 2,877
  8. 2020The Many Faces of Robustness: A Critical Analysis of Out-of-Distribution Generalizationcited by 1,850
  9. 2018ImageNet-trained CNNs are biased towards texture; increasing shape bias improves accuracy and robustnesscited by 1,432
  10. 2019Can You Trust Your Model's Uncertainty? Evaluating Predictive Uncertainty Under Dataset Shiftcited by 1,287
  11. 2019AugMix: A Simple Data Processing Method to Improve Robustness and Uncertaintycited by 901
  12. 2019On Evaluating Adversarial Robustnesscited by 447
19 more
  1. 2019Deep Ensembles: A Loss Landscape Perspectivecited by 443
  2. 2020BatchEnsemble: An Alternative Approach to Efficient Ensemble and Lifelong Learningcited by 371
  3. 2020Towards Understanding Ensemble, Knowledge Distillation and Self-Distillation in Deep Learningcited by 297
  4. 2019A Fourier Perspective on Model Robustness in Computer Visioncited by 288
  5. 2018Generalisation in humans and deep neural networkscited by 237
  6. 2019Improving Adversarial Robustness via Promoting Ensemble Diversitycited by 213
  7. 2018Knowledge Distillation by On-the-Fly Native Ensemblecited by 186
  8. 2020Hyperparameter Ensembles for Robustness and Uncertainty Quantificationcited by 150
  9. 2017A Study and Comparison of Human and Deep Learning Recognition Performance Under Visual Distortionscited by 108
  10. 2019Improving Robustness Without Sacrificing Accuracy with Patch Gaussian Augmentationcited by 105
  11. 2020Neural Ensemble Search for Uncertainty Estimation and Dataset Shiftcited by 56
  12. 2019Accurate, reliable and fast robustness evaluationcited by 43
  13. 2019Learning From Brains How to Regularize Machinescited by 38
  14. 2020Noisy Self-Knowledge Distillation for Text Summarizationcited by 31
  15. 2021Towards robust vision by multi-task learning on monkey visual cortexcited by 28
  16. 2020Compounding the Performance Improvements of Assembled Techniques in a Convolutional Neural Networkcited by 24
  17. 2020Diverse Ensembles Improve Calibrationcited by 23
  18. 2020An Effective Anti-Aliasing Approach for Residual Networkscited by 23
  19. 2019Achieving Generalizable Robustness of Deep Neural Networks by Stability Trainingcited by 7

Built on by

Cited by year

Citing papers per year: 2022: 1; 2023: 2; 2024: 2.

5 papers.

  1. 2022A.I. Robustness: a Human-Centered Perspective on Technological Challenges and Opportunitiescited by 9
  2. 2024Improving deep learning with prior knowledge and cognitive models: A survey on enhancing explainability, adversarial robustness and zero-shot learningcited by 4
  3. 2023Matching the Neuronal Representations of V1 is Necessary to Improve Robustness in CNNs with V1-like Front-endscited by 1
  4. 2024Explicitly Modeling Pre-Cortical Vision with a Neuro-Inspired Front-End Improves CNN Robustnesscited by 1
  5. 2023Modularity Trumps Invariance for Compositional Robustnesscited by 0