A Developmentally-Inspired Examination of Shape versus Texture Bias in Machines
This addresses the problem of understanding inductive biases in AI models for researchers in machine learning and cognitive science, but it is incremental as it builds on existing studies.
The paper re-examines whether deep neural networks show a shape or texture bias by adapting stimuli and procedures from prior work to more closely follow developmental paradigms, finding that networks exhibit a shape preference under these conditions.
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.