Preventing Arbitrarily High Confidence on Far-Away Data in Point-Estimated Discriminative Neural Networks

arXiv:2311.03683v2 Announce Type: replace
Abstract: Discriminatively trained, deterministic neural networks are the de facto choice for classification problems. However, even though they achieve state-of-the-art results on in-domain test sets, they tend to be overconfident on out-of-distribution (OOD) data. For instance, ReLU networks - a popular class of neural network architectures - have been shown to almost always yield high confidence predictions when the test data are far away from the training set, even when they are trained with OOD data. …

abstract art arxiv class classification confidence cs.lg data distribution domain however instance networks neural networks popular relu results state test type