OODD: Test-time Out-of-Distribution Detection with Dynamic Dictionary
This addresses the challenge of detecting OOD samples that differ significantly from training outliers, which is crucial for reliable AI deployment, though it appears incremental as it builds on existing OOD detection frameworks.
The paper tackles the problem of out-of-distribution detection in deep learning by proposing OODD, a test-time method that dynamically updates an OOD dictionary without fine-tuning, resulting in a 26.0% improvement in FPR95 on CIFAR-100 Far OOD detection compared to state-of-the-art methods.
Out-of-distribution (OOD) detection remains challenging for deep learning models, particularly when test-time OOD samples differ significantly from training outliers. We propose OODD, a novel test-time OOD detection method that dynamically maintains and updates an OOD dictionary without fine-tuning. Our approach leverages a priority queue-based dictionary that accumulates representative OOD features during testing, combined with an informative inlier sampling strategy for in-distribution (ID) samples. To ensure stable performance during early testing, we propose a dual OOD stabilization mechanism that leverages strategically generated outliers derived from ID data. To our best knowledge, extensive experiments on the OpenOOD benchmark demonstrate that OODD significantly outperforms existing methods, achieving a 26.0% improvement in FPR95 on CIFAR-100 Far OOD detection compared to the state-of-the-art approach. Furthermore, we present an optimized variant of the KNN-based OOD detection framework that achieves a 3x speedup while maintaining detection performance.