Abstract
Recent advances in the field of out-of-distribution (OOD) detection have placed great emphasis on learning better representations suited to this task. While there are distance-based approaches, distributional awareness has seldom been exploited for better performance. We present HAC$_k$-OOD, a novel OOD detection method that makes no distributional assumption about the data, but automatically adapts to its distribution. Specifically, HAC$_k$-OOD constructs a set of hypercones by maximizing the angular distance to neighbors in a given data-point's vicinity to approximate the contour within which in-distribution (ID) data-points lie. Experimental results show state-of-the-art FPR@95 and AUROC performance on Near-OOD detection and on Far-OOD detection on the challenging CIFAR-100 benchmark without explicitly training for OOD performance.
Abstract (translated)
最近在分布外（OOD）检测领域取得的进展，强调了学习更适合该任务的表示方法的重要性。虽然存在基于距离的方法，但分佈感知性很少被利用来提高性能。我们提出了HAC$_k$-OOD，这是一种新颖的OOD检测方法，它不对数据做出任何分布假设，而是自动适应其分布特性。具体来说，HAC$_k$-OOD通过最大化给定点邻域内样本之间的角度距离来构建一组双曲锥体（hypercones），以此近似包含内部分布（ID）数据点的边界轮廓。 实验结果表明，在不特意针对OOD性能进行训练的情况下，HAC$_k$-OOD在Near-OOD检测和具有挑战性的CIFAR-100基准测试中的Far-OOD检测上达到了最先进的FPR@95和AUROC性能。
URL
https://arxiv.org/abs/2501.10209
