# Signal Strength and Noise Drive Feature Preference in CNN Image Classifiers

arXiv: https://arxiv.org/abs/2201.08893 · HTML: https://mlsanity.com/paper/2201.08893/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 8 of its 13 references that are in the map.
- First posted on arXiv 19 Jan 2022.

## Builds on (most cited first, 8 of 8)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Benchmarking Neural Network Robustness to Common Corruptions and Perturbations](https://mlsanity.com/paper/1903.12261/) (2019)
- [Shortcut Learning in Deep Neural Networks](https://mlsanity.com/paper/2004.07780/) (2020)
- [ImageNet-trained CNNs are biased towards texture; increasing shape bias improves accuracy and robustness](https://mlsanity.com/paper/1811.12231/) (2018)
- [Adversarial Examples Are Not Bugs, They Are Features](https://mlsanity.com/paper/1905.02175/) (2019)
- [The Pitfalls of Simplicity Bias in Neural Networks](https://mlsanity.com/paper/2006.07710/) (2020)
- [What shapes feature representations? Exploring datasets, architectures, and training](https://mlsanity.com/paper/2006.12433/) (2020)
- [Excessive Invariance Causes Adversarial Vulnerability](https://mlsanity.com/paper/1811.00401/) (2018)

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

- [On the Foundations of Shortcut Learning](https://mlsanity.com/paper/2310.16228/) (2023)

## Abstract (arXiv)

Feature preference in Convolutional Neural Network (CNN) image classifiers is integral to their decision making process, and while the topic has been well studied, it is still not understood at a fundamental level. We test a range of task relevant feature attributes (including shape, texture, and color) with varying degrees of signal and noise in highly controlled CNN image classification experiments using synthetic datasets to determine feature preferences. We find that CNNs will prefer features with stronger signal strength and lower noise irrespective of whether the feature is texture, shape, or color. This provides guidance for a predictive model for task relevant feature preferences, demonstrates pathways for bias in machine models that can be avoided with careful controls on experimental setup, and suggests that comparisons between how humans and machines prefer task relevant features in vision classification tasks should be revisited. Code to reproduce experiments in this paper can be found at urlhttps://github.com/mwolff31/signalpreference.