Katherine L. Hermann

The Origins and Prevalence of Texture Bias in Convolutional Neural Networks

2019 · arXiv (Cornell University)

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 from? We find that, when trained …

Understanding Visual Feature Reliance through the Lens of Complexity

2024 · arXiv (Cornell University)

Recent studies suggest that deep learning models inductive bias towards favoring simpler features may be one of the sources of shortcut learning. Yet, there has been limited focus on understanding the complexity of the myriad …