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 2002.00772cs.HC
收藏

评价卷积神经网络的显着性映射:用户研究

Evaluating Saliency Map Explanations for Convolutional Neural Networks: A User Study

Ahmed Alqaraawi, Martin Schuessler, Philipp Weiß, Enrico Costanza, Nadia Berthouze

摘要:

卷积神经网络(CNN)在一系列应用中提供了出色的机器学习性能,但即使是专家也很难解释它们的操作。已经提出了各种解释算法来解决这个问题,但有限的研究工作已经报告了关于他们的用户评价。在本文中,我们报告了一个在线的组间用户研究,旨在评估“显着图”的性能-一个流行的解释算法的CNN的图像分类应用。我们的研究结果表明,显着性图产生的LRP算法帮助参与者了解一些特定的图像功能的系统是敏感的。然而,这些地图似乎对参与者预测网络输出新图像的帮助非常有限。根据我们的研究结果,我们强调了设计和进一步研究可解释人工智能的意义。特别是,我们认为HCI和AI社区应该超越实例级别的解释。

英文摘要:

Convolutional neural networks (CNNs) offer great machine learning performance over a range of applications, but their operation is hard to interpret, even for experts. Various explanation algorithms have been proposed to address this issue, yet limited research effort has been reported concerning their user evaluation. In this paper, we report on an online between-group user study designed to evaluate the performance of "saliency maps" - a popular explanation algorithm for image classification applications of CNNs. Our results indicate that saliency maps produced by the LRP algorithm helped participants to learn about some specific image features the system is sensitive to. However, the maps seem to provide very limited help for participants to anticipate the network's output for new images. Drawing on our findings, we highlight implications for design and further research on explainable AI. In particular, we argue the HCI and AI communities should look beyond instance-level explanations.

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。

↑