← Search

Tom Knowles

2 accepted papers

2022

Do deep networks transfer invariances across classes?

ICLR 2022poster

In order 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 transformations that apply similarly to all classes, such as lighting and background changes for image classification. Neur…