arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1702.04595cs.CVcs.AI
收藏

可视化深度神经网络决策:预测差异分析

Visualizing Deep Neural Network Decisions: Prediction Difference Analysis

University of Amsterdam(阿姆斯特丹大学);Vrije Universiteit Brussel(布鲁塞尔自由大学);Canadian Institute of Advanced Research(加拿大高级研究院)

Luisa M Zintgraf, Taco S Cohen, Tameem Adel, Max Welling

摘要:

本文提出了预测差异分析方法,用于可视化深度神经网络对特定输入的响应。当对图像进行分类时,该方法突出显示给定输入图像中提供支持或反对某个类别的证据的区域。它克服了以前的方法的几个缺点,并提供了很大的额外的洞察分类器的决策过程。通过可视化使神经网络决策可解释对于改进模型和加速黑盒分类器在医学等应用领域的采用都很重要。我们在自然图像(ImageNet数据)以及医学图像(MRI脑部扫描)上的实验中说明了该方法。

英文摘要:

This article presents the prediction difference analysis method for visualizing the response of a deep neural network to a specific input. When classifying images, the method highlights areas in a given input image that provide evidence for or against a certain class. It overcomes several shortcoming of previous methods and provides great additional insight into the decision making process of classifiers. Making neural network decisions interpretable through visualization is important both to improve models and to accelerate the adoption of black-box classifiers in application areas such as medicine. We illustrate the method in experiments on natural images (ImageNet data), as well as medical images (MRI brain scans).

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。

↑