Spurious-Aware Prototype Refinement for Reliable Out-of-Distribution Detection

Reihaneh Zohrabi, Hosein Hasani, Mahdieh Soleymani Baghshah, Anna Rohrbach, Marcus Rohrbach, Mohammad Hossein Rohban

Keywords: Out-of-Distribution Detection, Spurious Correlations, Prototype Refinement, Robustness, Post-hoc Methods, Trustworthy AI

TL;DR: We introduce a novel, post-hoc prototypical OOD detection method that counteracts unknown spurious correlations by refining class prototypes, achieving state-of-the-art performance for reliable, trustworthy AI.

Abstract:

Out-of-distribution (OOD) detection is crucial for ensuring the reliability and safety of machine learning models in real-world applications, where they frequently face data distributions unseen during training.
Despite progress, existing methods are often vulnerable to spurious correlations that mislead models and compromise robustness. To address this, we propose SPROD, a novel prototype-based OOD detection approach that explicitly addresses the challenge posed by unknown spurious correlations.
Our post-hoc method refines class prototypes to mitigate bias from spurious features without additional data or hyperparameter tuning, and is broadly applicable across diverse backbones and OOD detection settings.
We conduct a comprehensive spurious correlation OOD detection benchmarking, comparing our method against existing approaches and demonstrating its superior performance across challenging OOD datasets, such as CelebA, Waterbirds, UrbanCars, Spurious Imagenet, and the newly introduced Animals MetaCoCo. On average, SPROD improves AUROC by 4.8% and FPR@95 by 9.4% over the second best.

Primary Area: Social and economic aspects of machine learning (e.g., fairness, interpretability, human-AI interaction, privacy, safety, strategic behavior)

Submission Number: 23214