引入“内部”分布外样本
Introducing 'Inside' Out of Distribution
AI总结：
该研究提出将分布外（OOD）样本分为内部和外部两类的新视角，通过合成数据集实验验证二者对机器学习模型性能影响不同，外部OOD平均造成的性能下降更显著，为开发针对性OOD应对方法提供依据。
摘要：
在机器学习（ML）领域，检测并理解分布外（OOD）样本对保障模型性能的可靠性至关重要。当前OOD研究主要聚焦于外推型（外部）OOD，忽略了内插型（内部）OOD的潜在情形。本研究提出一种关于OOD的全新视角，认为OOD可划分为内部与外部两类。我们在同时包含内部和外部OOD的合成数据集上，以归一化均方根误差（RMSE）和F1值作为性能指标，探究了数据集的内外部OOD分布特征及其对ML模型性能的影响。分析表明，不同的内外部OOD分布特征会对ML模型性能产生差异化影响，平均而言外部OOD通常会导致更严重的性能下降。这些发现凸显了区分内外部OOD对于开发有效的OOD应对方法的重要性。
英文摘要：
Detecting and understanding out-of-distribution (OOD) samples is crucial in machine learning (ML) to ensure reliable model performance. Current OOD studies primarily focus on extrapolatory (outside) OOD, neglecting potential cases of interpolatory (inside) OOD. In this study, we introduce a novel perspective on OOD by suggesting it can be divided into inside and outside cases. We examine the inside-outside OOD profiles of datasets and their impact on ML model performance, using normalized Root Mean Squared Error (RMSE) and F1 score as the performance metrics on syntetically-generated datasets with both inside and outside OOD. Our analysis demonstrates that different inside-outside OOD profiles lead to unique effects on ML model performance, with outside OOD generally causing greater performance degradation, on average. These findings highlight the importance of distinguishing between inside and outside OOD for developing effective counter-OOD methods.
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。
