MetaOOD: Automatic Selection of OOD Detection Models

TL;DR

MetaOOD is a novel zero-shot, unsupervised meta-learning framework that automatically selects the most suitable out-of-distribution detection model for new tasks without requiring labeled data, improving reliability in critical applications.

Contribution

It introduces MetaOOD, the first framework using meta-learning and language model embeddings for automatic OOD model selection without ground truth labels.

Findings

MetaOOD outperforms 11 baseline methods across 24 dataset pairs.

It achieves significant improvements with minimal additional computational overhead.

Validated by statistical tests, MetaOOD reliably enhances OOD detection model selection.

Abstract

How can we automatically select an out-of-distribution (OOD) detection model for various underlying tasks? This is crucial for maintaining the reliability of open-world applications by identifying data distribution shifts, particularly in critical domains such as online transactions, autonomous driving, and real-time patient diagnosis. Despite the availability of numerous OOD detection methods, the challenge of selecting an optimal model for diverse tasks remains largely underexplored, especially in scenarios lacking ground truth labels. In this work, we introduce MetaOOD, the first zero-shot, unsupervised framework that utilizes meta-learning to select an OOD detection model automatically. As a meta-learning approach, MetaOOD leverages historical performance data of existing methods across various benchmark OOD detection datasets, enabling the effective selection of a suitable model for new datasets without the need for labeled data at the test time. To quantify task similarities more accurately, we introduce language model-based embeddings that capture the distinctive OOD characteristics of both datasets and detection models. Through extensive experimentation with 24 unique test dataset pairs to choose from among 11 OOD detection models, we demonstrate that MetaOOD significantly outperforms existing methods and only brings marginal time overhead. Our results, validated by Wilcoxon statistical tests, show that MetaOOD surpasses a diverse group of 11 baselines, including established OOD detectors and advanced unsupervised selection methods.