Multi-Label Out-of-Distribution Detection with Spectral Normalized Joint Energy

arXiv:2405.04759v1 Announce Type: cross
Abstract: In today's interconnected world, achieving reliable out-of-distribution (OOD) detection poses a significant challenge for machine learning models. While numerous studies have introduced improved approaches for multi-class OOD detection tasks, the investigation into multi-label OOD detection tasks has been notably limited. We introduce Spectral Normalized Joint Energy (SNoJoE), a method that consolidates label-specific information across multiple labels through the theoretically justified concept of an energy-based function. Throughout the training process, we employ spectral normalization to manage …

abstract arxiv challenge class cs.cv cs.lg detection distribution energy investigation machine machine learning machine learning models studies tasks type while world