基于哈密顿蒙特卡洛的离群点合成用于分布外检测
Outlier Synthesis via Hamiltonian Monte Carlo for Out-of-Distribution Detection
AI总结：
本文提出HamOS框架，将离群点合成建模为基于哈密顿蒙特卡洛的马尔可夫链采样过程，仅利用分布内数据高效生成多样且具代表性的虚拟离群点，在标准与大规模基准上验证了其OOD检测的有效性与高效性。
摘要：
分布外（OOD）检测对于开发可信且可靠的机器学习系统至关重要。近年来，利用辅助OOD数据进行训练的方法在提升检测能力方面展现出显著效果。然而，这些方法严重依赖获取大量高质量的自然离群点。一些先前的方法试图通过合成虚拟离群点来缓解这一问题，但由于采样策略单调以及生成模型参数规模庞大，导致合成质量差或成本高昂。在本文中，我们提出了哈密顿蒙特卡洛离群点合成（HamOS）框架以克服上述所有问题，该框架将合成过程视为从马尔可夫链中进行采样。仅基于分布内数据，马尔可夫链即可广泛遍历特征空间并生成多样且具有代表性的离群点，从而使模型暴露于各种潜在的OOD场景中。采样接受率几乎接近1的哈密顿蒙特卡洛方法还使我们的框架具备极高的效率。通过在标准基准和大规模基准上与SOTA基线方法进行实证对比，我们验证了所提出的HamOS框架的有效性和高效性。
英文摘要：
Out-of-distribution (OOD) detection is crucial for developing trustworthy and reliable machine learning systems. Recent advances in training with auxiliary OOD data demonstrate efficacy in enhancing detection capabilities. Nonetheless, these methods heavily rely on acquiring a large pool of high-quality natural outliers. Some prior methods try to alleviate this problem by synthesizing virtual outliers but suffer from either poor quality or high cost due to the monotonous sampling strategy and the heavy-parameterized generative models. In this paper, we overcome all these problems by proposing the Hamiltonian Monte Carlo Outlier Synthesis (HamOS) framework, which views the synthesis process as sampling from Markov chains. Based solely on the in-distribution data, the Markov chains can extensively traverse the feature space and generate diverse and representative outliers, hence exposing the model to miscellaneous potential OOD scenarios. The Hamiltonian Monte Carlo with sampling acceptance rate almost close to 1 also makes our framework enjoy great efficiency. By empirically competing with SOTA baselines on both standard and large-scale benchmarks, we verify the efficacy and efficiency of our proposed HamOS.
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。
