arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2107.02845cs.LG
收藏

基于Logit的分类不确定性度量

Logit-based Uncertainty Measure in Classification

Northwestern University(西北大学)

Huiyu Wu, Diego Klabjan

摘要:

我们为分类任务引入了一种新的、可靠的、不可知的不确定性度量,称为logit不确定性。它基于神经网络的logit输出。我们特别表明,这种新的不确定性度量在不同的任务,包括样本检测和发现错误的预测,产生了优于现有的不确定性度量的性能。我们分析了测量的理论基础,并探讨了与高密度区域的关系。我们还演示了如何在生成对抗网络的训练中使用中间输出来测试不确定性。我们提出了两种潜在的方法来利用logit为基础的不确定性在现实世界中的应用,并表明不确定性措施优于。

英文摘要:

We introduce a new, reliable, and agnostic uncertainty measure for classification tasks called logit uncertainty. It is based on logit outputs of neural networks. We in particular show that this new uncertainty measure yields a superior performance compared to existing uncertainty measures on different tasks, including out of sample detection and finding erroneous predictions. We analyze theoretical foundations of the measure and explore a relationship with high density regions. We also demonstrate how to test uncertainty using intermediate outputs in training of generative adversarial networks. We propose two potential ways to utilize logit-based uncertainty in real world applications, and show that the uncertainty measure outperforms.

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。

↑