3 papers
cs.LG2026
MahaVar: OOD Detection via Class-wise Mahalanobis Distance Variance under Neural Collapse
Donghwan Kim, Hyunsoo Yoon
Out-of-distribution (OOD) detection is a critical component for ensuring the reliability of deep neural networks in safety-critical applications. In this work, we present a key emp…
cs.LG2026
Why Does Counterintuitive Likelihood Behavior Rarely Emerge in Tabular Anomaly Detection?
Donghwan Kim, Junghun Phee, Hyunsoo Yoon
Deep generative models with tractable likelihoods, exemplified by normalizing flows, offer an effective basis for anomaly detection through likelihood-based scoring. We demonstrate…
cs.LG2026
Mitigating the Likelihood Paradox in Flow-based OOD Detection: An Entropic Perspective
Donghwan Kim, Hyunsoo Yoon
Deep generative models that can tractably compute input likelihoods, including normalizing flows, often assign unexpectedly high likelihoods to out-of-distribution (OOD) inputs. We…