论文标题
旨在最大化内域和分布范围之间的表示差距
Towards Maximizing the Representation Gap between In-Domain & Out-of-Distribution Examples
论文作者
论文摘要
在现有的不确定性估计方法中，Dirichlet先验网络（DPN）明显模型不同的预测不确定性类型。但是，对于多个类别中具有高数据不确定性的较高数据不确定性的示例，即使是DPN模型，也常常与分布（OOD）示例无可分割的表示，从而损害了其OOD检测性能。我们通过提出DPN的新型损失函数来解决这一缺点，以最大程度地提高内域和OOD示例之间的\ textit {表示{表示差距}。实验结果表明，我们提出的方法始终提高OOD检测性能。
Among existing uncertainty estimation approaches, Dirichlet Prior Network (DPN) distinctly models different predictive uncertainty types. However, for in-domain examples with high data uncertainties among multiple classes, even a DPN model often produces indistinguishable representations from the out-of-distribution (OOD) examples, compromising their OOD detection performance. We address this shortcoming by proposing a novel loss function for DPN to maximize the \textit{representation gap} between in-domain and OOD examples. Experimental results demonstrate that our proposed approach consistently improves OOD detection performance.
