Taylor Outlier Exposure（泰勒离群点暴露）
Taylor Outlier Exposure
AI总结：
针对辅助 OOD 数据常被 ID 样本污染的问题，提出 TaylorOE，通过 Taylor 展开构造可调阶数的正则化项，在干净与含噪 OOD 设置下均提升检测性能。
摘要：
分布外（OOD）检测是识别来自训练期间未使用分布的数据的任务。该任务对于可靠的机器学习以及更好地理解其泛化能力至关重要。在 OOD 检测方法中，Outlier Exposure（OE，离群点暴露）通过向模型暴露辅助 OOD 数据，显著提升 OOD 检测性能和泛化能力。然而，构建未被分布内（ID）样本污染的干净辅助 OOD 数据集对于 OE 至关重要；通常，被 ID 样本污染的含噪 OOD 数据集会对 OE 训练动态和最终检测性能产生负面影响。此外，随着数据集规模增大，构建干净 OOD 数据变得越来越具有挑战性且成本高昂。为应对这些挑战，我们提出 Taylor Outlier Exposure（TaylorOE），这是一种基于 OE 并带有正则化的方法，允许在被 ID 样本污染的含噪 OOD 数据集上进行训练。具体而言，我们通过 Taylor 展开将 OE 正则化项表示为多项式函数，使我们能够通过调整 Taylor 展开的阶数来控制辅助 OOD 数据集中 ID 数据的正则化强度。在使用干净和含噪 OOD 数据集进行的 OOD 检测任务实验中，我们证明所提出方法始终优于传统方法，并分析了正则化项以展示其有效性。TaylorOE 的实现代码可在 https://github.com/fukuchan41/TaylorOE 获取。
英文摘要：
Out-of-distribution (OOD) detection is the task of identifying data sampled from distributions that were not used during training. This task is essential for reliable machine learning and a better understanding of their generalization capabilities. Among OOD detection methods, Outlier Exposure (OE) significantly enhances OOD detection performance and generalization ability by exposing auxiliary OOD data to the model. However, constructing clean auxiliary OOD datasets, uncontaminated by in-distribution (ID) samples, is essential for OE; generally, a noisy OOD dataset contaminated with ID samples negatively impacts OE training dynamics and final detection performance. Furthermore, as dataset scale increases, constructing clean OOD data becomes increasingly challenging and costly. To address these challenges, we propose Taylor Outlier Exposure (TaylorOE), an OE-based approach with regularization that allows training on noisy OOD datasets contaminated with ID samples. Specifically, we represent the OE regularization term as a polynomial function via a Taylor expansion, allowing us to control the regularization strength for ID data in the auxiliary OOD dataset by adjusting the order of Taylor expansion. In our experiments on the OOD detection task with clean and noisy OOD datasets, we demonstrate that the proposed method consistently outperforms conventional methods and analyze our regularization term to show its effectiveness. Our implementation code of TaylorOE is available at \url{https://github.com/fukuchan41/TaylorOE}.
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。
