Empirical Advocacy of Bio-inspired Models for Robust Image Recognition

Bio-Inspired Image Recognition (BIIR) is official source code repository for the paper NeuroVision2022 paper: "Empirical Advocacy of Bio-inspired Models for Robust Image Recognition" by Harshitha Machiraju*, Oh-Hyeon Choung*, Pascal Frossard, and Michael. H. Herzog.

project_title

project_description
Explore the docs »

View Demo · Report Bug · Request Feature

Table of Contents

Abstract
- Built With
Getting Started
- Prerequisites
- Installation
Usage
Roadmap
Contributing
License
Contact
Acknowledgments

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. 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.

Built With

Wandb

(back to top)

Getting Started

Prerequisites

npm install npm@latest -g

-->

Contributing

Contributions are what make the open source community such an amazing place to learn, inspire, and create. Any contributions you make are greatly appreciated.

If you have a suggestion that would make this better, please fork the repo and create a pull request. You can also simply open an issue with the tag "enhancement". Don't forget to give the project a star! Thanks again!

Fork the Project
Create your Feature Branch (git checkout -b feature/AmazingFeature)
Commit your Changes (git commit -m 'Add some AmazingFeature')
Push to the Branch (git push origin feature/AmazingFeature)
Open a Pull Request

(back to top)

Citing this work

@article{BioRobust,
  author = {Machiraju, Harshitha and Choung, Oh-Hyeon and Herzog, Michael H. and Frossard, Pascal},
  title = {Empirical Advocacy of Bio-inspired Models for Robust Image Recognition},
  journal = {arXiv preprint arXiv:2205.09037}
  year = {2022},
}