arXiv 2303.122672025-05-17cs.LGcs.CV

AUTO：面向测试时分布外（OOD）检测的自适应异常值优化

AUTO: Adaptive Outlier Optimization for Test-Time OOD Detection

State Key Laboratory of Multimodal Artificial Intelligence Systems, CASIA（多模态人工智能系统国家重点实验室，CASIA）；Center for Research on Intelligent Perception and Computing, CASIA（智能感知与计算研究中心，CASIA）；Center for Excellence in Brain Science and Intelligence Technology, CAS（脑科学与智能技术卓越中心，CAS）；School of Artificial Intelligence, University of Chinese Academy of Sciences（中国科学院大学人工智能学院）

Puning Yang, Jian Liang, Jie Cao, Ran He

备注：: 14 pages

阅读 PDF

arXiv 页面 ↗HTML 原文 ↗

AI总结：

针对预收集任务特定异常值的隐私与性能难题，该研究提出测试时OOD检测新设置及AUTO方法，通过三组件实现检测器持续自适应，在多种场景下性能优于现有最优方法。

摘要：

分布外（OOD）检测旨在检测不属于任何训练分布内（ID）类别的测试样本。以往研究仅聚焦于用ID数据对模型进行正则化，其性能远不及利用辅助异常值的方法。然而，数据安全与隐私问题使得无法为不同场景预先收集任务特定的异常值；此外，使用与任务无关的异常值会导致OOD检测性能不佳。为解决上述问题，我们提出一种名为测试时OOD检测的新设置，允许已部署的模型在测试期间利用来自无标签数据流的真实OOD数据。我们提出自适应异常值优化（AUTO）方法，可实现OOD检测器的持续自适应。具体而言，AUTO包含三个核心组件：1）内外感知滤波器，用于为测试样本选择性标注伪ID和伪OOD标签，并在遇到每个伪OOD样本时巧妙触发更新流程；2）动态更新存储器，用于克服频繁参数更新导致的灾难性遗忘；3）预测对齐目标，用于在测试期间校准粗略的OOD目标。大量实验表明，AUTO相比现有最优方法显著提升了OOD检测性能。此外，在复杂场景（如多OOD、时序OOD）下的评估也验证了AUTO的优越性。

英文摘要：

Out-of-distribution (OOD) detection aims to detect test samples that do not fall into any training in-distribution (ID) classes. Prior efforts focus on regularizing models with ID data only, largely underperforming counterparts that utilize auxiliary outliers. However, data safety and privacy make it infeasible to collect task-specific outliers in advance for different scenarios. Besides, using task-irrelevant outliers leads to inferior OOD detection performance. To address the above issue, we present a new setup called test-time OOD detection, which allows the deployed model to utilize real OOD data from the unlabeled data stream during testing. We propose Adaptive Outlier Optimization (AUTO) which allows for continuous adaptation of the OOD detector. Specifically, AUTO consists of three key components: 1) an in-out-aware filter to selectively annotate test samples with pseudo-ID and pseudo-OOD and ingeniously trigger the updating process while encountering each pseudo-OOD sample; 2) a dynamic-updated memory to overcome the catastrophic forgetting led by frequent parameter updates; 3) a prediction-aligning objective to calibrate the rough OOD objective during testing. Extensive experiments show that AUTO significantly improves OOD detection performance over state-of-the-art methods. Besides, evaluations on complicated scenarios (e.g. multi-OOD, time-series OOD) also conduct the superiority of AUTO.

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。