Back to the Basics: Revisiting Out-of-Distribution Detection Baselines. (arXiv:2207.03061v1 [cs.LG])

We study simple methods for out-of-distribution (OOD) image detection that
are compatible with any already trained classifier, relying on only its
predictions or learned representations. Evaluating the OOD detection
performance of various methods when utilized with ResNet-50 and Swin
Transformer models, we find methods that solely consider the model's
predictions can be easily outperformed by also considering the learned
representations. Based on our analysis, we advocate for a dead-simple approach
that has been neglected in other studies: simply flag as …

arxiv basics detection distribution lg