测试时动态构建异常样本字典，无需微调即可精准识别分布外数据。
OODD: Test-time Out-of-Distribution Detection with Dynamic Dictionary
- 用优先队列动态维护测试中收集的异常特征字典。
- 在CIFAR-100远端分布检测上FPR95提升26.0%优于当前最优方法。
- 适合部署在无法重新训练模型的实时检测场景中使用。
分布外（OOD）检测对深度学习模型仍是挑战，尤其当测试阶段的分布外样本与训练阶段的异常样本差异显著时。本文提出 OODD，一种新颖的测试时分布外检测方法，可在不进行微调的情况下动态维护和更新分布外特征字典。该方法采用基于优先队列的字典结构，在测试过程中累积具有代表性的分布外特征，并结合有信息量的分布内样本采样策略。为保障早期测试阶段性能稳定，我们设计了双重分布外稳定机制，利用从分布内数据中生成的策略性异常样本。据我们所知，在 OpenOOD 基准上的大量实验表明，OODD 显著优于现有方法，在 CIFAR-100 远端分布外检测任务上相较当前最优方法实现 26.0% 的 FPR95 改进。此外，我们还提出一种优化的基于 KNN 的分布外检测框架，速度提升 3 倍而检测性能保持不变。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。