arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2202.03299cs.LGcs.AI
收藏

培训OOD探测器的自然环境

Training OOD Detectors in their Natural Habitats

University of Wisconsin, Madison(威斯康星大学麦迪逊分校)

Julian Katz-Samuels, Julia Nakhleh, Robert Nowak, Yixuan Li

摘要:

分发外(OOD)检测对于部署在野外的机器学习模型很重要。最近的方法使用辅助离群数据来正则化模型,以改进OOD检测。然而,这些方法做出了很强的分布假设,即辅助离群值数据与分布(ID)数据完全分离。在本文中,我们提出了一个新的框架,利用野生混合数据,自然包括ID和OOD样本。这样的野生数据是丰富的,并且在它们的自然栖息地中部署机器学习分类器时自由产生。我们的主要思想是制定一个约束优化问题,并显示如何tractably solvedit.OOD检测率最大化,受约束的分类错误的ID数据和OOD出错率的ID的例子。我们广泛评估我们的方法对常见的OOD检测任务,并表现出卓越的性能。

英文摘要:

Out-of-distribution (OOD) detection is important for machine learning models deployed in the wild. Recent methods use auxiliary outlier data to regularize the model for improved OOD detection. However, these approaches make a strong distributional assumption that the auxiliary outlier data is completely separable from the in-distribution (ID) data. In this paper, we propose a novel framework that leverages wild mixture data, which naturally consists of both ID and OOD samples. Such wild data is abundant and arises freely upon deploying a machine learning classifier in their natural habitats. Our key idea is to formulate a constrained optimization problem and to show how to tractably solve it. Our learning objective maximizes the OOD detection rate, subject to constraints on the classification error of ID data and on the OOD error rate of ID examples. We extensively evaluate our approach on common OOD detection tasks and demonstrate superior performance.

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。

↑