Hypercone Assisted Contour Generation for Out-of-Distribution Detection
This addresses the problem of reliable OOD detection for machine learning systems, particularly in safety-critical applications, by offering a novel approach that improves performance without explicit training.
The paper tackles out-of-distribution (OOD) detection by introducing HAC$_k$-OOD, a method that constructs hypercones to approximate in-distribution contours without distributional assumptions, achieving state-of-the-art FPR@95 and AUROC on CIFAR-100 benchmarks for both near and far OOD detection.
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.