Density of States Estimation for Out-of-Distribution Detection

被引用0|浏览61
24小时获取PDF
引用

摘要

Perhaps surprisingly, recent studies have shown probabilistic model likelihoods have poor specificity for out-of-distribution (OOD) detection and often assign higher likelihoods to OOD data than in-distribution data. To ameliorate this issue we propose DoSE, the density of states estimator. Drawing on the statistical physics notion of `...更多

代码

数据

作者
Morningstar Warren R.
Morningstar Warren R.
Ham Cusuh
Ham Cusuh
Gallagher Andrew G.
Gallagher Andrew G.
Dillon Joshua V.
Dillon Joshua V.
您的评分 :
0

 

标签
评论
数据免责声明
页面数据均来自互联网公开来源、合作出版商和通过AI技术自动分析结果,我们不对页面数据的有效性、准确性、正确性、可靠性、完整性和及时性做出任何承诺和保证。若有疑问,可以通过电子邮件方式联系我们:report@aminer.cn
小科