Saved in:
Bibliographic Details
Main Authors: Fu, Hao, Krishnamurthy, Prashanth, Garg, Siddharth, Khorrami, Farshad
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2412.06168
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912149255749632
author Fu, Hao
Krishnamurthy, Prashanth
Garg, Siddharth
Khorrami, Farshad
author_facet Fu, Hao
Krishnamurthy, Prashanth
Garg, Siddharth
Khorrami, Farshad
contents Out-of-distribution (OOD) detection is crucial for the deployment of machine learning models in the open world. While existing OOD detectors are effective in identifying OOD samples that deviate significantly from in-distribution (ID) data, they often come with trade-offs. For instance, deep OOD detectors usually suffer from high computational costs, require tuning hyperparameters, and have limited interpretability, whereas traditional OOD detectors may have a low accuracy on large high-dimensional datasets. To address these limitations, we propose a novel effective OOD detection approach that employs an overlap index (OI)-based confidence score function to evaluate the likelihood of a given input belonging to the same distribution as the available ID samples. The proposed OI-based confidence score function is non-parametric, lightweight, and easy to interpret, hence providing strong flexibility and generality. Extensive empirical evaluations indicate that our OI-based OOD detector is competitive with state-of-the-art OOD detectors in terms of detection accuracy on a wide range of datasets while requiring less computation and memory costs. Lastly, we show that the proposed OI-based confidence score function inherits nice properties from OI (e.g., insensitivity to small distributional variations and robustness against Huber $ε$-contamination) and is a versatile tool for estimating OI and model accuracy in specific contexts.
format Preprint
id arxiv_https___arxiv_org_abs_2412_06168
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Out-of-Distribution Detection with Overlap Index
Fu, Hao
Krishnamurthy, Prashanth
Garg, Siddharth
Khorrami, Farshad
Machine Learning
Out-of-distribution (OOD) detection is crucial for the deployment of machine learning models in the open world. While existing OOD detectors are effective in identifying OOD samples that deviate significantly from in-distribution (ID) data, they often come with trade-offs. For instance, deep OOD detectors usually suffer from high computational costs, require tuning hyperparameters, and have limited interpretability, whereas traditional OOD detectors may have a low accuracy on large high-dimensional datasets. To address these limitations, we propose a novel effective OOD detection approach that employs an overlap index (OI)-based confidence score function to evaluate the likelihood of a given input belonging to the same distribution as the available ID samples. The proposed OI-based confidence score function is non-parametric, lightweight, and easy to interpret, hence providing strong flexibility and generality. Extensive empirical evaluations indicate that our OI-based OOD detector is competitive with state-of-the-art OOD detectors in terms of detection accuracy on a wide range of datasets while requiring less computation and memory costs. Lastly, we show that the proposed OI-based confidence score function inherits nice properties from OI (e.g., insensitivity to small distributional variations and robustness against Huber $ε$-contamination) and is a versatile tool for estimating OI and model accuracy in specific contexts.
title Out-of-Distribution Detection with Overlap Index
topic Machine Learning
url https://arxiv.org/abs/2412.06168