Search Results for author:
Found 4 papers, 0 papers with code
On the Foundations of Shortcut Learning
Deep-learning models can extract a rich assortment of features from data.
Getting aligned on representational alignment
Finally, we lay out open problems in representational alignment where progress can benefit all three of these fields.
What shapes feature representations? Exploring datasets, architectures, and training
Answers to these questions are important for understanding the basis of models' decisions, as well as for building models that learn versatile, adaptable representations useful beyond the original training task.
The Origins and Prevalence of Texture Bias in Convolutional Neural Networks
By taking less aggressive random crops at training time and applying simple, naturalistic augmentation (color distortion, noise, and blur), we train models that classify ambiguous images by shape a majority of the time, and outperform baselines on out-of-distribution test sets.
