让模型在未见领域中精准识别异常数据，无需测试时调整。
MADOD: Generalizing OOD Detection to Unseen Domains via G-Invariance Meta-Learning
- 用元学习和伪异常任务模拟未知领域中的异常情况。
- 在未见领域上检测异常的性能提升8.48%至20.81%（AUPR）。
- 适合部署在无法获取测试数据的真实场景中。
现实世界机器学习应用常面临协变量与语义分布的同时漂移，传统领域泛化与分布外（OOD）检测方法难以应对。本文提出元学习跨域分布外检测（MADOD），同时应对两类漂移。其核心在于任务设计：在每个元学习任务中随机将分布内类别设为伪分布外，利用现有数据模拟分布外场景。结合能量正则化，学习鲁棒且域不变的特征，并校准决策边界以实现有效检测。该方法在测试阶段无需适应，适用于测试数据不可得的场景。在真实与合成数据集上的实验表明，MADOD在未见领域上实现了显著的语义分布外检测性能提升，AUPR提高8.48%至20.81%，同时保持了良好的分布内分类准确率，是应对协变量与语义漂移的重要进展。
原文摘要 · Abstract (English)
Real-world machine learning applications often face simultaneous covariate and semantic shifts, challenging traditional domain generalization and out-of-distribution (OOD) detection methods. We introduce Meta-learned Across Domain Out-of-distribution Detection (MADOD), a novel framework designed to address both shifts concurrently. MADOD leverages meta-learning and G-invariance to enhance model generalizability and OOD detection in unseen domains. Our key innovation lies in task construction: we randomly designate in-distribution classes as pseudo-OODs within each meta-learning task, simulating OOD scenarios using existing data. This approach, combined with energy-based regularization, enables the learning of robust, domain-invariant features while calibrating decision boundaries for effective OOD detection. Operating in a test domain-agnostic setting, MADOD eliminates the need for adaptation during inference, making it suitable for scenarios where test data is unavailable. Extensive experiments on real-world and synthetic datasets demonstrate MADOD's superior performance in semantic OOD detection across unseen domains, achieving an AUPR improvement of 8.48% to 20.81%, while maintaining competitive in-distribution classification accuracy, representing a significant advancement in handling both covariate and semantic shifts.
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。