Mitigating the Likelihood Paradox in Flow-based OOD Detection via Entropy Manipulation

Documenti analoghi

• MahaVar: OOD Detection via Class-wise Mahalanobis Distance Variance under Neural Collapse
  di: Kim, Donghwan, et al.
  Pubblicazione: (2026)
• Why the Counterintuitive Phenomenon of Likelihood Rarely Appears in Tabular Anomaly Detection with Deep Generative Models?
  di: Kim, Donghwan, et al.
  Pubblicazione: (2026)
• A Geometric Explanation of the Likelihood OOD Detection Paradox
  di: Kamkari, Hamidreza, et al.
  Pubblicazione: (2024)
• Log-Likelihood, Simpson's Paradox, and the Detection of Machine-Generated Text
  di: Kempton, Tom, et al.
  Pubblicazione: (2026)
• ODIM: Outlier Detection via Likelihood of Under-Fitted Generative Models
  di: Kim, Dongha, et al.
  Pubblicazione: (2023)