通过构建超锥体自动捕捉数据边界，实现无需分布假设的高效异常检测。
Hypercone Assisted Contour Generation for Out-of-Distribution Detection
- 利用邻域最大夹角构造超锥体，逼近正常数据分布边界
- 在CIFAR-100上实现Near-OOD与Far-OOD检测的顶尖性能
- 无需专门训练即可达到领先效果，适合实际部署场景
近期的分布外（OOD）检测研究聚焦于学习更适配该任务的表示。尽管已有基于距离的方法，但对数据分布特性的利用仍较不足。本文提出HAC$_k$-OOD，一种新型无分布假设的OOD检测方法，可自动适应数据分布。具体地，该方法通过最大化某数据点邻域内邻居的夹角距离，构建一组超锥体，以近似正常数据点所处的轮廓范围。实验表明，在无需显式训练用于OOD检测的情况下，该方法在具有挑战性的CIFAR-100基准上，于Near-OOD和Far-OOD检测任务中均取得当前最优的FPR@95与AUROC表现。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。