Inducing Early Neural Collapse in Deep Neural Networks for Improved Out-of-Distribution Detection. (arXiv:2209.08378v2 [cs.LG] UPDATED)

We propose a simple modification to standard ResNet architectures--L2
regularization over feature space--that substantially improves
out-of-distribution (OoD) performance on the previously proposed Deep
Deterministic Uncertainty (DDU) benchmark. This change also induces early
Neural Collapse (NC), which we show is an effect under which better OoD
performance is more probable. Our method achieves comparable or superior OoD
detection scores and classification accuracy in a small fraction of the
training time of the benchmark. Additionally, it substantially improves worst
case OoD performance …

arxiv detection distribution networks neural collapse neural networks