Fredrik Kahl

In Search of Projectively Equivariant Networks

2022 · arXiv (Cornell University)

Equivariance of linear neural network layers is well studied. In this work, we relax the equivariance condition to only be true in a projective sense. We propose a way to construct a projectively equivariant neural …

ProHOC: Probabilistic Hierarchical Out-of-Distribution Classification via Multi-Depth Networks

2025

Out-of-distribution (OOD) detection in deep learning has traditionally been framed as a binary task, where samples are either classified as belonging to the known classes or marked as OOD, with little attention given to the …