Skip to content

[CogSci'21] Study of human inductive biases in CNNs and Transformers.

Notifications You must be signed in to change notification settings

shikhartuli/cnn_txf_bias

Repository files navigation

Are Convolutional Neural Networks or Transformers more like human vision?

Python Version Tensorflow Hits

This repository contains the code and fine-tuned models of popular Convolutional Neural Networks (CNNs) and the recently proposed Vision Transformer (ViT) on the augmented Imagenet dataset and the shape/texture bias tests run on the Stylized Imagenet dataset.

This work compares CNNs and the ViT against humans in terms of error consistency beyond traditional metrics. Through these tests, we were able to show that recently proposed self-attention based Transformer models have more human-like errors that traditional CNNs.

Illustration

Colab

You can directly run tests on the results using a Google Colaboratory without needing to install anything on your local machine. Click "Open in Colab" below:

Open In Colab

Developer

Shikhar Tuli. For any questions, comments or suggestions, please reach me at stuli@princeton.edu.

Cite this work

If you use our experimental results or fine-tuned models, please cite:

@article{tuli2021cogsci,
      title={Are Convolutional Neural Networks or Transformers more like human vision?}, 
      author={Shikhar Tuli and Ishita Dasgupta and Erin Grant and Thomas L. Griffiths},
      year={2021},
      eprint={2105.07197},
      archivePrefix={arXiv},
      primaryClass={cs.CV}
}

About

[CogSci'21] Study of human inductive biases in CNNs and Transformers.

Topics

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published