NECO: NEural Collapse Based Out-of-distribution detection

arXiv:2310.06823v3 Announce Type: replace-cross
Abstract: Detecting out-of-distribution (OOD) data is a critical challenge in machine learning due to model overconfidence, often without awareness of their epistemological limits. We hypothesize that ``neural collapse'', a phenomenon affecting in-distribution data for models trained beyond loss convergence, also influences OOD data. To benefit from this interplay, we introduce NECO, a novel post-hoc method for OOD detection, which leverages the geometric properties of ``neural collapse'' and of principal component spaces to identify OOD data. Our …

arxiv cs.ai cs.cv cs.lg detection distribution neural collapse stat.ml type