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 1610.02136cs.NEcs.CVcs.LG
收藏

一种检测神经网络中误分类和分布外样本的基线

A Baseline for Detecting Misclassified and Out-of-Distribution Examples in Neural Networks

University of California, Berkeley(加州大学伯克利分校);Toyota Technological Institute at Chicago(芝加哥丰田理工学院)

Dan Hendrycks, Kevin Gimpel

摘要:

我们考虑两个相关的问题,检测一个例子是错误分类或分布。我们提出了一个简单的基线,利用softmax分布的概率。正确分类的示例往往比错误分类和分布外的示例具有更大的最大softmax概率,从而允许它们的检测。我们通过定义计算机视觉、自然语言处理和自动语音识别中的几个任务来评估性能,显示了该基线在所有方面的有效性。然后,我们表明基线有时可以被超越,展示了这些未充分探索的检测任务的未来研究的空间。

英文摘要:

We consider the two related problems of detecting if an example is misclassified or out-of-distribution. We present a simple baseline that utilizes probabilities from softmax distributions. Correctly classified examples tend to have greater maximum softmax probabilities than erroneously classified and out-of-distribution examples, allowing for their detection. We assess performance by defining several tasks in computer vision, natural language processing, and automatic speech recognition, showing the effectiveness of this baseline across all. We then show the baseline can sometimes be surpassed, demonstrating the room for future research on these underexplored detection tasks.

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。

↑