Out-of-distribution (OOD) inputs can compromise the performance and safety of real world machine learning systems. While many methods exist for OOD detection and work well on small scale datasets with lower resolution and few classes, few methods have been developed for large-scale OOD detection. Existing large-scale methods generally depend on maximum classification probability, such as the state-of-the-art grouped softmax method. In this work, we develop a novel approach that calculates the probability of the predicted class label based on label distributions learned during the training process. Our method performs better than current state-of-the-art methods with only a negligible increase in compute cost. We evaluate our method against contemporary methods across $14$ datasets and achieve a statistically significant improvement with respect to AUROC (84.2 vs 82.4) and AUPR (96.2 vs 93.7).

翻译：外部分配(OOD)投入可能损害现实世界机器学习系统的性能和安全性。虽然OOD检测和很好地处理分辨率较低和几类的小规模数据集有许多方法,但很少开发出大规模OOOD检测方法。现有的大规模方法一般取决于最大分类概率,例如最先进的组合软体法。在这项工作中,我们开发了一种新颖的方法,根据培训过程中所学的标签分布,计算预测等级标签的概率。我们的方法比目前最先进的方法表现得更好,而计算成本仅略有增加。我们对照14万美元的现代方法评估我们的方法,并在统计上显著改进了AUROC(84.2对82.4)和AUPR(96.2对93.7)和AULUD(96.2对93.7)。</s>