ICML

Our paper Improving Out-of-Distribution Detection with Markov Logic Network has been accepted at the ICML. In it, we propose a probabilistic extension of Out-of-Distribution Detection with Logical Reasoning, as well as a simple algorithm to mine logical constraints for OOD detection from a dataset. Abstract § Out-of-distribution (OOD) detection is essential for ensuring the reliability of deep learning models operating in open-world scenarios. Current OOD detectors mainly rely on statistical …