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

Understand

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.