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 the model's feature space, thereby enhancing model efficacy and generalization, in addition to bolstering robustness. Our findings indicate that the application of spectral normalization to joint energy scores notably amplifies the model's capability for OOD detection. We perform OOD detection experiments utilizing PASCAL-VOC as the in-distribution dataset and ImageNet-22K or Texture as the out-of-distribution datasets. Our experimental results reveal that, in comparison to prior top performances, SNoJoE achieves 11% and 54% relative reductions in FPR95 on the respective OOD datasets, thereby defining the new state of the art in this field of study.

翻译：在当今互联互通的世界中，实现可靠的分布外（OOD）检测对机器学习模型构成重大挑战。尽管已有众多研究提出了改进的多类别OOD检测方法，但对多标签OOD检测任务的探索仍显不足。我们提出谱归一化联合能量（SNoJoE）方法，该方法通过基于能量函数的理论论证框架，整合跨多标签的标签特定信息。在训练过程中，我们采用谱归一化来管理模型的特征空间，从而在增强鲁棒性的同时提升模型效能与泛化能力。研究结果表明，将谱归一化应用于联合能量得分可显著增强模型的OOD检测能力。我们以PASCAL-VOC作为内分布数据集，ImageNet-22K或Texture作为外分布数据集开展OOD检测实验。实验结果显示，与先前最优性能相比，SNoJoE在对应OOD数据集上的FPR95指标分别实现11%和54%的相对降低，由此确立了该研究领域的新标杆。