Machine learning models deployed in the wild can be challenged by
out-of-distribution (OOD) data from unknown classes. Recent advances in OOD
detection rely on distance measures to distinguish samples that are relatively
far away from the in-distribution (ID) data. Despite the promise,
distance-based methods can suffer from the curse-of-dimensionality problem,
which limits the efficacy in high-dimensional feature space. To combat this
problem, we propose a novel framework, Subspace Nearest Neighbor (SNN), for OOD
detection. In training, our method regularizes the model and its feature
representation by leveraging the most relevant subset of dimensions (i.e.
subspace). Subspace learning yields highly distinguishable distance measures
between ID and OOD data. We provide comprehensive experiments and ablations to
validate the efficacy of SNN. Compared to the current best distance-based
method, SNN reduces the average FPR95 by 15.96% on the CIFAR-100 benchmark.

机器学习模型在野外部署时可能会受到未知类别的离群数据的挑战。最近对 OOD 检测的进展依赖于距离度量，以区分相对于内部分布数据而言相对较远的样本。尽管有前景，但基于距离的方法可能受到维度灾难问题的困扰，从而限制了在高维特征空间中的功效。为解决这个问题，我们提出了一种新颖的框架 Subspace Nearest Neighbor（SNN）用于 OOD 检测。在训练中，我们的方法通过利用最相关的子维度（即子空间）来规范化模型及其特征表示。子空间学习产生了 ID 和 OOD 数据之间高度可区分的距离度量。我们提供了全面的实验证明 SNN 的有效性。与当前最佳的基于距离的方法相比，SNN 在 CIFAR-100 基准测试中将平均 FPR95 降低了 15.96%。