English

Hypercone Assisted Contour Generation for Out-of-Distribution Detection

Computer Vision and Pattern Recognition 2025-02-19 v2 Machine Learning

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 HACk_k-OOD, a novel OOD detection method that makes no distributional assumption about the data, but automatically adapts to its distribution. Specifically, HACk_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.

Keywords

Cite

@article{arxiv.2501.10209,
  title  = {Hypercone Assisted Contour Generation for Out-of-Distribution Detection},
  author = {Annita Vapsi and Andrés Muñoz and Nancy Thomas and Keshav Ramani and Daniel Borrajo},
  journal= {arXiv preprint arXiv:2501.10209},
  year   = {2025}
}