arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2003.02977cs.LGcs.CVstat.ML
收藏

Likelihood Regret:一种变分自动编码器的分布外检测分数

Likelihood Regret: An Out-of-Distribution Detection Score For Variational Auto-encoder

University of Chicago(芝加哥大学)

Zhisheng Xiao, Qing Yan, Yali Amit

摘要:

深度概率生成模型能够对非常高维数据的可能性进行建模。生成建模的一个重要应用应该是通过设置可能性阈值来检测分布外(OOD)样本的能力。然而,最近的一些研究表明,概率生成模型可以,在某些情况下,分配较高的似然对某些类型的OOD样本,使OOD检测规则的基础上的似然阈值的问题。为了解决这个问题,已经针对深度生成模型提出了几种OOD检测方法。在本文中,我们观察到,这些方法中的许多失败时,应用到基于变分自动编码器(VAE)的生成模型。作为一种替代方案,我们提出了一个有效的OOD评分VAE的Likestival遗憾。我们基准我们提出的方法在现有的方法,和实证结果表明,我们的方法获得最佳的整体OOD检测性能时,应用于VAE。

英文摘要:

Deep probabilistic generative models enable modeling the likelihoods of very high dimensional data. An important application of generative modeling should be the ability to detect out-of-distribution (OOD) samples by setting a threshold on the likelihood. However, some recent studies show that probabilistic generative models can, in some cases, assign higher likelihoods on certain types of OOD samples, making the OOD detection rules based on likelihood threshold problematic. To address this issue, several OOD detection methods have been proposed for deep generative models. In this paper, we make the observation that many of these methods fail when applied to generative models based on Variational Auto-encoders (VAE). As an alternative, we propose Likelihood Regret, an efficient OOD score for VAEs. We benchmark our proposed method over existing approaches, and empirical results suggest that our method obtains the best overall OOD detection performances when applied to VAEs.

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。

↑