Supplementary Material for The Origins and Prevalence of Texture Bias in Neural Networks

Higher learning rates produce greater shape bias. As shown in Figure A.1, higher values of learning rate and weight decay were associated with greater We found that random-crop augmentation biases models towards texture (Section 5). We did not change the aspect ratio or other data augmentation settings. Networks with limited receptive fields learn texture more easily than shape. Shape is persistently more decodable through the convolutional layers of AlexNet than is texture, which rises through them.