2 papers
cs.LG2020
What shapes feature representations? Exploring datasets, architectures, and training
Katherine L. Hermann, Andrew K. Lampinen
In naturalistic learning problems, a model's input contains a wide range of features, some useful for the task at hand, and others not. Of the useful features, which ones does the…
cs.CV2019
The Origins and Prevalence of Texture Bias in Convolutional Neural Networks
Katherine L. Hermann, Ting Chen, Simon Kornblith
Recent work has indicated that, unlike humans, ImageNet-trained CNNs tend to classify images by texture rather than by shape. How pervasive is this bias, and where does it come fro…