OODD: Test-time Out-of-Distribution Detection with Dynamic Dictionary

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Yang, Yifeng, Zhu, Lin, Sun, Zewen, Liu, Hengyu, Gu, Qinying, Ye, Nanyang
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915196223619072
author Yang, Yifeng
Zhu, Lin
Sun, Zewen
Liu, Hengyu
Gu, Qinying
Ye, Nanyang
author_facet Yang, Yifeng
Zhu, Lin
Sun, Zewen
Liu, Hengyu
Gu, Qinying
Ye, Nanyang
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2503_10468
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle OODD: Test-time Out-of-Distribution Detection with Dynamic Dictionary
Yang, Yifeng
Zhu, Lin
Sun, Zewen
Liu, Hengyu
Gu, Qinying
Ye, Nanyang
Computer Vision and Pattern Recognition
Machine Learning
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.
title OODD: Test-time Out-of-Distribution Detection with Dynamic Dictionary
topic Computer Vision and Pattern Recognition
Machine Learning
url https://arxiv.org/abs/2503.10468