# A Developmentally-Inspired Examination of Shape versus Texture Bias in Machines

arXiv: https://arxiv.org/abs/2202.08340 · HTML: https://mlsanity.com/paper/2202.08340/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- Builds on 13 of its 31 references that are in the map.
- First posted on arXiv 16 Feb 2022.

## Builds on (most cited first, 13 of 13)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Emerging Properties in Self-Supervised Vision Transformers](https://mlsanity.com/paper/2104.14294/) (2021)
- [Aggregated Residual Transformations for Deep Neural Networks](https://mlsanity.com/paper/1611.05431/) (2016)
- [ImageNet-trained CNNs are biased towards texture; increasing shape bias improves accuracy and robustness](https://mlsanity.com/paper/1811.12231/) (2018)
- [Approximating CNNs with Bag-of-local-Features models works surprisingly well on ImageNet](https://mlsanity.com/paper/1904.00760/) (2019)
- [Generalisation in humans and deep neural networks](https://mlsanity.com/paper/1808.08750/) (2018)
- [Partial success in closing the gap between human and machine vision](https://mlsanity.com/paper/2106.07411/) (2021)
- [Are Convolutional Neural Networks or Transformers more like human vision?](https://mlsanity.com/paper/2105.07197/) (2021)
- [Self-supervised learning through the eyes of a child](https://mlsanity.com/paper/2007.16189/) (2020)
- [Cognitive Psychology for Deep Neural Networks: A Shape Bias Case Study](https://mlsanity.com/paper/1706.08606/) (2017)
- [Learning Inductive Biases with Simple Neural Networks](https://mlsanity.com/paper/1802.02745/) (2018)

## Built on by (most cited first, 10 of 10)

- [On the Foundations of Shortcut Learning](https://mlsanity.com/paper/2310.16228/) (2023)
- [When does compositional structure yield compositional generalization? A kernel theory](https://mlsanity.com/paper/2405.16391/) (2024)
- [MEWL: Few-shot multimodal word learning with referential uncertainty](https://mlsanity.com/paper/2306.00503/) (2023)
- [Representation Learning by Detecting Incorrect Location Embeddings](https://mlsanity.com/paper/2204.04788/) (2022)
- [Deep Neural Networks Can Learn Generalizable Same-Different Visual Relations](https://mlsanity.com/paper/2310.09612/) (2023)
- [Visual Anagrams Reveal Hidden Differences in Holistic Shape Processing Across Vision Models](https://mlsanity.com/paper/2507.00493/) (2025)
- [A novel feature-scrambling approach reveals the capacity of convolutional neural networks to learn spatial relations](https://mlsanity.com/paper/2212.06021/) (2022)
- [On the Reliability of Cue Conflict and Beyond](https://mlsanity.com/paper/2603.10834/) (2026)
- [Balancing Frequencies and Pixels in Flow Matching](https://mlsanity.com/paper/2609.02748/) (2026)
- [Feature, Alignment, and Supervision in Category Learning: A Comparative Approach with Children and Neural Networks](https://mlsanity.com/paper/2602.03124/) (2026)

## Abstract (arXiv)

Early in development, children learn to extend novel category labels to objects with the same shape, a phenomenon known as the shape bias. Inspired by these findings, Geirhos et al. (2019) examined whether deep neural networks show a shape or texture bias by constructing images with conflicting shape and texture cues. They found that convolutional neural networks strongly preferred to classify familiar objects based on texture as opposed to shape, suggesting a texture bias. However, there are a number of differences between how the networks were tested in this study versus how children are typically tested. In this work, we re-examine the inductive biases of neural networks by adapting the stimuli and procedure from Geirhos et al. (2019) to more closely follow the developmental paradigm and test on a wide range of pre-trained neural networks. Across three experiments, we find that deep neural networks exhibit a preference for shape rather than texture when tested under conditions that more closely replicate the developmental procedure.