通过信息性外推实现分布外检测的多样化离群点暴露
Diversified Outlier Exposure for Out-of-Distribution Detection via Informative Extrapolation
AI总结：
本文提出DivOE框架，通过多步优化合成更多信息性离群点以多样化辅助分布，从而在无需大量代表性离群点的条件下提升OOD检测性能。
摘要：
分布外（OOD）检测对于在现实应用中部署可靠的机器学习模型至关重要。离群点暴露（outlier exposure）的最新进展表明，通过使用经过信息性采样的辅助离群点对模型进行微调，可以在OOD检测上取得有前景的结果。然而，以往方法假设收集到的离群点数量足够大且具有代表性，能够覆盖分布内（ID）数据与OOD数据之间的边界，而这在实际中可能不切实际且具有挑战性。在本工作中，我们提出了一种新的框架，称为多样化离群点暴露（DivOE），通过基于给定辅助离群点的信息性外推来实现有效的OOD检测。具体而言，DivOE引入了一个新的学习目标，该目标通过在训练过程中显式合成更多信息性离群点进行外推，从而使辅助分布多样化。它利用多步优化方法生成超出原始离群点范围的新离群点，并且与多种离群点暴露变体兼容。我们进行了大量实验和分析，以刻画并证明所提出的DivOE的有效性。代码已公开，地址为：https://github.com/tmlr-group/DivOE。
英文摘要：
Out-of-distribution (OOD) detection is important for deploying reliable machine learning models on real-world applications. Recent advances in outlier exposure have shown promising results on OOD detection via fine-tuning model with informatively sampled auxiliary outliers. However, previous methods assume that the collected outliers can be sufficiently large and representative to cover the boundary between ID and OOD data, which might be impractical and challenging. In this work, we propose a novel framework, namely, Diversified Outlier Exposure (DivOE), for effective OOD detection via informative extrapolation based on the given auxiliary outliers. Specifically, DivOE introduces a new learning objective, which diversifies the auxiliary distribution by explicitly synthesizing more informative outliers for extrapolation during training. It leverages a multi-step optimization method to generate novel outliers beyond the original ones, which is compatible with many variants of outlier exposure. Extensive experiments and analyses have been conducted to characterize and demonstrate the effectiveness of the proposed DivOE. The code is publicly available at: https://github.com/tmlr-group/DivOE.
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。
