AI RESEARCH
VNDUQE: Information-Theoretic Novelty Detection using Deep Variational Information Bottleneck
arXiv CS.LG
•
ArXi:2605.11551v1 Announce Type: new Detecting out-of-distribution (OOD) samples is critical for safe deployment of neural networks in safety-critical applications. While maximum softmax probability (MSP) provides a simple baseline, it lacks theoretical grounding and suffers from miscalibration. We propose VNDUQE (VIB-based Novelty Detection and Uncertainty Quantification for Nondestructive Evaluation), which investigates novelty detection through the Deep Variational Information Bottleneck (VIB), which explicitly constrains information flow through learned representations.