23 citations · 23 across the 2 of their papers we have counts for
2 papers
cs.CV2022
Do Deep Networks Transfer Invariances Across Classes?
Allan Zhou, Fahim Tajwar, Alexander Robey +4
To generalize well, classifiers must learn to be invariant to nuisance transformations that do not alter an input's class. Many problems have "class-agnostic" nuisance transformati…
cs.LG2020★ 23 cited
Meta-Learning Symmetries by Reparameterization
Allan Zhou, Tom Knowles, Chelsea Finn
Many successful deep learning architectures are equivariant to certain transformations in order to conserve parameters and improve generalization: most famously, convolution layers…