# Clarifying Myths About the Relationship Between Shape Bias, Accuracy, and Robustness

arXiv: https://arxiv.org/abs/2406.05006 · HTML: https://mlsanity.com/paper/2406.05006/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 20 of its 28 references that are in the map.
- First posted on arXiv 7 Jun 2024.

## Builds on (most cited first, 20 of 20)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Intriguing properties of neural networks](https://mlsanity.com/paper/1312.6199/) (2013)
- [ImageNet-trained CNNs are biased towards texture; increasing shape bias improves accuracy and robustness](https://mlsanity.com/paper/1811.12231/) (2018)
- [Adversarial Discriminative Domain Adaptation](https://mlsanity.com/paper/1702.05464/) (2017)
- [Adversarial Machine Learning at Scale](https://mlsanity.com/paper/1611.01236/) (2016)
- [AutoAugment: Learning Augmentation Policies from Data](https://mlsanity.com/paper/1805.09501/) (2018)
- [Albumentations: fast and flexible image augmentations](https://mlsanity.com/paper/1809.06839/) (2018)
- [Using Self-Supervised Learning Can Improve Model Robustness and Uncertainty](https://mlsanity.com/paper/1906.12340/) (2019)
- [Intriguing Properties of Vision Transformers](https://mlsanity.com/paper/2105.10497/) (2021)
- [Partial success in closing the gap between human and machine vision](https://mlsanity.com/paper/2106.07411/) (2021)
- [Adversarial Robustness: From Self-Supervised Pre-Training to Fine-Tuning](https://mlsanity.com/paper/2003.12862/) (2020)
- [Effects of Degradations on Deep Neural Network Architectures](https://mlsanity.com/paper/1807.10108/) (2018)
- [Pyramid Adversarial Training Improves ViT Performance](https://mlsanity.com/paper/2111.15121/) (2021)
- [AugLy: Data Augmentations for Robustness](https://mlsanity.com/paper/2201.06494/) (2022)
- [Does enhanced shape bias improve neural network robustness to common corruptions?](https://mlsanity.com/paper/2104.09789/) (2021)
- [On Classification of Distorted Images with Deep Convolutional Neural Networks](https://mlsanity.com/paper/1701.01924/) (2017)
- [A Direct Approach to Robust Deep Learning Using Adversarial Networks](https://mlsanity.com/paper/1905.09591/) (2019)
- [DeepCorrect: Correcting DNN models against Image Distortions](https://mlsanity.com/paper/1705.02406/) (2017)
- [Adversarial Feature Desensitization](https://mlsanity.com/paper/2006.04621/) (2020)

## Built on by (most cited first, 1 of 1)

- [Robusto-1 Dataset: Comparing Humans and VLMs on real out-of-distribution Autonomous Driving VQA from Peru](https://mlsanity.com/paper/2503.07587/) (2025)

## Abstract (arXiv)

Deep learning models can perform well when evaluated on images from the same distribution as the training set. However, applying small perturbations in the forms of noise, artifacts, occlusions, blurring, etc. to a model's input image and feeding the model with out-of-distribution (OOD) data can significantly drop the model's accuracy, making it not applicable to real-world scenarios. Data augmentation is one of the well-practiced methods to improve model robustness against OOD data; however, examining which augmentation type to choose and how it affects the OOD robustness remains understudied. There is a growing belief that augmenting datasets using data augmentations that improve a model's bias to shape-based features rather than texture-based features results in increased OOD robustness for Convolutional Neural Networks trained on the ImageNet-1K dataset. This is usually stated as ``an increase in the model's shape bias results in an increase in its OOD robustness". Based on this hypothesis, some works in the literature aim to find augmentations with higher effects on model shape bias and use those for data augmentation. By evaluating 39 types of data augmentations on a widely used OOD dataset, we demonstrate the impact of each data augmentation on the model's robustness to OOD data and further show that the mentioned hypothesis is not true; an increase in shape bias does not necessarily result in higher OOD robustness. By analyzing the results, we also find some biases in the ImageNet-1K dataset that can easily be reduced using proper data augmentation. Our evaluation results further show that there is not necessarily a trade-off between in-domain accuracy and OOD robustness, and choosing the proper augmentations can help increase both in-domain accuracy and OOD robustness simultaneously.