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 1802.04865stat.MLcs.LG
收藏

神经网络分布外检测的学习置信度

Learning Confidence for Out-of-Distribution Detection in Neural Networks

University of Guelph(圭尔夫大学);Vector Institute(向量研究所)

Terrance DeVries, Graham W. Taylor

摘要:

现代神经网络是非常强大的预测模型,但它们通常无法识别它们的预测何时可能是错误的。与此密切相关的是分布外检测的任务,其中网络必须确定输入是否在预期安全执行的集合之外。为了共同解决这些问题,我们提出了一种学习神经网络的置信度估计的方法,该方法易于实现并产生直观可解释的输出。我们证明,在任务的分布检测,我们的技术优于最近提出的技术,构建信心的基础上,网络的输出分布,而不需要任何额外的标签或访问的分布外的例子。此外,我们解决的问题,校准的分布检测器,在那里我们证明,错误分类的分布的例子可以用作代理的分布的例子。

英文摘要:

Modern neural networks are very powerful predictive models, but they are often incapable of recognizing when their predictions may be wrong. Closely related to this is the task of out-of-distribution detection, where a network must determine whether or not an input is outside of the set on which it is expected to safely perform. To jointly address these issues, we propose a method of learning confidence estimates for neural networks that is simple to implement and produces intuitively interpretable outputs. We demonstrate that on the task of out-of-distribution detection, our technique surpasses recently proposed techniques which construct confidence based on the network's output distribution, without requiring any additional labels or access to out-of-distribution examples. Additionally, we address the problem of calibrating out-of-distribution detectors, where we demonstrate that misclassified in-distribution examples can be used as a proxy for out-of-distribution examples.

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。

↑