2 papers
cs.CV2026
A Robust Out-of-Distribution Detection Framework via Synergistic Smoothing
Maria Stoica, Abdelrahman Hekal, Alessio Lomuscio
Reliable out-of-distribution (OOD) detection is a critical requirement for the safe deployment of machine learning systems. Despite recent progress, state-of-the-art OOD detectors…
cs.LG2025
Out-of-Distribution Detection using Counterfactual Distance
Maria Stoica, Francesco Leofante, Alessio Lomuscio
Accurate and explainable out-of-distribution (OOD) detection is required to use machine learning systems safely. Previous work has shown that feature distance to decision boundarie…