# Explorations in Texture Learning

arXiv: https://arxiv.org/abs/2403.09543 · HTML: https://mlsanity.com/paper/2403.09543/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 2 of its 6 references that are in the map.
- First posted on arXiv 14 Mar 2024.

## Builds on (most cited first, 2 of 2)

- [ImageNet-trained CNNs are biased towards texture; increasing shape bias improves accuracy and robustness](https://mlsanity.com/paper/1811.12231/) (2018)
- [Partial success in closing the gap between human and machine vision](https://mlsanity.com/paper/2106.07411/) (2021)

## Built on by (most cited first, 3 of 3)

- [Alignment and Adversarial Robustness: Are More Human-Like Models More Secure?](https://mlsanity.com/paper/2502.12377/) (2025)
- [Err on the Side of Texture: Texture Bias on Real Data](https://mlsanity.com/paper/2412.10597/) (2024)
- [On Synthetic Texture Datasets: Challenges, Creation, and Curation](https://mlsanity.com/paper/2409.10297/) (2024)

## Abstract (arXiv)

In this work, we investigate textittexture learning: the identification of textures learned by object classification models, and the extent to which they rely on these textures. We build texture-object associations that uncover new insights about the relationships between texture and object classes in CNNs and find three classes of results: associations that are strong and expected, strong and not expected, and expected but not present. Our analysis demonstrates that investigations in texture learning enable new methods for interpretability and have the potential to uncover unexpected biases.