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 2007.05566cs.LGstat.ML
收藏

改进的分布外检测的对比训练

Contrastive Training for Improved Out-of-Distribution Detection

Google Health(谷歌健康);DeepMind
Jim Winkens, Rudy Bunel, Abhijit Guha Roy, Robert Stanforth, Vivek Natarajan, Joseph R. Ledsam, Patricia MacWilliams, Pushmeet Kohli, Alan Karthikesalingam, Sim… 展开作者

Jim Winkens, Rudy Bunel, Abhijit Guha Roy, Robert Stanforth, Vivek Natarajan, Joseph R. Ledsam, Patricia MacWilliams, Pushmeet Kohli, Alan Karthikesalingam, Simon Kohl, Taylan Cemgil, S. M. Ali Eslami, Olaf Ronneberger

摘要:

可靠地检测分布外(OOD)输入越来越被理解为部署机器学习系统的先决条件。本文提出并研究了使用对比训练来提高OOD检测性能。与领先的OOD检测方法不同,我们的方法不需要访问明确标记为OOD的示例,这在实践中可能很难收集。我们在大量的实验中表明,对比训练显着有助于OOD检测性能的一些常见的基准。通过引入和采用混淆对数概率(CLP)得分,通过捕获内点和离群点数据集的相似性来量化OOD检测任务的难度,我们表明我们的方法特别提高了“近OOD”类的性能-这是以前方法的一个特别具有挑战性的设置。

英文摘要:

Reliable detection of out-of-distribution (OOD) inputs is increasingly understood to be a precondition for deployment of machine learning systems. This paper proposes and investigates the use of contrastive training to boost OOD detection performance. Unlike leading methods for OOD detection, our approach does not require access to examples labeled explicitly as OOD, which can be difficult to collect in practice. We show in extensive experiments that contrastive training significantly helps OOD detection performance on a number of common benchmarks. By introducing and employing the Confusion Log Probability (CLP) score, which quantifies the difficulty of the OOD detection task by capturing the similarity of inlier and outlier datasets, we show that our method especially improves performance in the `near OOD' classes -- a particularly challenging setting for previous methods.

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。

↑