AI RESEARCH

ConjNorm: Tractable Density Estimation for Out-of-Distribution Detection

arXiv CS.AI

ArXi:2402.17888v4 Announce Type: replace-cross Post-hoc out-of-distribution (OOD) detection has garnered intensive attention in reliable machine learning. Many efforts have been dedicated to deriving score functions based on logits, distances, or rigorous data distribution assumptions to identify low-scoring OOD samples. Nevertheless, these estimate scores may fail to accurately reflect the true data density or impose impractical constraints.