面向分布外检测的基于扩散的干扰感知语义异常样本生成
Diffusion based Semantic Outlier Generation via Nuisance Awareness for Out-of-Distribution Detection
AI总结：
针对现有OOD检测合成异常样本与ID距离过远、难捕捉细微差异的问题，提出SONA框架，通过扩散模型结合干扰感知引导生成兼具语义差异和不同干扰相似性的难异常样本，显著提升近OOD检测性能。
摘要：
分布外（OOD）检测旨在判断给定样本是否属于分布内（ID），近期通过合成OOD数据集训练已展现出可观效果。但现有方法生成的异常样本通常与ID距离过远，在捕捉ID与OOD间的细微差异方面效果有限。为解决这些问题，我们提出了一种名为Semantic Outlier generation via Nuisance Awareness（SONA，干扰感知语义异常生成）的新型框架，它通过扩散模型直接利用像素空间的ID样本，生成具有挑战性的异常样本。我们的方法引入SONA引导，可分别控制ID样本的语义区域与干扰区域。由此生成的异常样本具备两个关键特性：（i）呈现明确的语义差异信息，同时（ii）与ID保持不同程度的干扰相似性。此外，使用SONA生成的异常样本训练改进的OOD检测器，能让模型聚焦于语义差异进行学习。大量实验证明了该框架的有效性，在近OOD数据集上取得了88%的出色AUROC，比基线方法的性能高出约6%的显著幅度。
英文摘要：
Out-of-distribution (OOD) detection, which determines whether a given sample is part of the in-distribution (ID), has recently shown promising results through training with synthetic OOD datasets. Nonetheless, existing methods often produce outliers that are considerably distant from the ID, showing limited efficacy for capturing subtle distinctions between ID and OOD. To address these issues, we propose a novel framework, Semantic Outlier generation via Nuisance Awareness (SONA), which notably produces challenging outliers by directly leveraging pixel-space ID samples through diffusion models. Our approach incorporates SONA guidance, providing separate control over semantic and nuisance regions of ID samples. Thereby, the generated outliers achieve two crucial properties: (i) they present explicit semantic-discrepant information, while (ii) maintaining various levels of nuisance resemblance with ID. Furthermore, the improved OOD detector training with SONA outliers facilitates learning with a focus on semantic distinctions. Extensive experiments demonstrate the effectiveness of our framework, achieving an impressive AUROC of 88% on near-OOD datasets, which surpasses the performance of baseline methods by a significant margin of approximately 6%.
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。
