More Persuasive Explanation Method for End-to-End Driving Models
More Persuasive Explanation Method for End-to-End Driving Models
复制标题
端到端驾驶模型更有说服力的解释方法
DOI：
10.1109/access.2023.3235739
复制
发表时间：
2023
期刊：
影响因子：
3.9
通讯作者：
Murase Hiroshi
中科院分区：
文献类型：
--
作者：
Zhang Chenkai;Deguchi Daisuke;Okafuji Yuki;Murase Hiroshi
随着自动驾驶技术的快速发展，各种高性能的端到端驾驶模型（e2edm）被提出。为了理解e2edm的计算方法，采用像素级解释方法获得e2edm的解释。然而，很少有人关注e2edm解释的卓越性。因此，为了构建可信的e2edm，我们着重于提高e2edm解释的可信度。提出了一种E2EDM的对象级解释方法（主要方法），该方法先对图像中的目标进行掩盖，然后将预测结果的变化视为目标的重要性，然后通过每个目标的重要性来解释E2EDM。为了进一步验证对象级解释的有效性，我们提出了另一种方法（验证方法），该方法以对象信息作为输入训练e2edm，并使用一般解释方法生成对象的重要性。这两种方法都产生了对象级解释，为了将这些对象级解释与传统的像素级解释进行比较，我们提出了实验方法，通过主观和客观的方法来衡量e2edm解释的可信度。主观方法根据参与者认为解释所表明的特征的重要性是正确的程度来评估可信度。客观方法是基于仅提供图像的重要部分与提供完整图像之间的人类注释相似性来评估可信度。实验结果表明，对象级解释比传统的像素级解释更有说服力。
With the rapid development of autonomous driving technology, a variety of high-performance end-to-end driving models (E2EDMs) are being proposed. In order to understand the computational methods of E2EDMs, pixel-level explanations methods are used to obtain the explanations of the E2EDMs. However, little attention has been paid to the excellence of the explanations of E2EDMs. Therefore, in order to build trustworthy E2EDMs, we focus on improving the persuasibility of the explanations of E2EDMs. We propose an object-level explanation method (main approach) for E2EDMs, which masks the objects in the image and then treats the change in the prediction result as the importance of the objects, then we explain the E2EDM by the importance of each object. To further validate the effectiveness of object-level explanations, we propose another approach (validation approach), which trains E2EDMs with object information as input and generates the importance of objects using general explanation methods. Both approaches generate object-level explanations, in order to compare these object-level explanations with traditional pixel-level explanations, we propose experimental methods to measure the persuasibility of explanations of E2EDMs through a subjective and objective method. The subjective method evaluates persuasibility based on the extent to which participants think the importance of features indicated by the explanations is correct. The objective method evaluates the persuasibility based on the human annotation similarity between provided with only the important part of images and provided with the complete images. The experimental results show that the object-level explanations are more persuasive than the traditional pixel-level explanations.
登录
查看更多内容
DOI：
--
发表时间：
2019-01
期刊：
ArXiv
影响因子：
--
作者：
Isaac Lage;Emily Chen;Jeffrey He;Menaka Narayanan;Been Kim;Sam Gershman;F. Doshi-Velez
通讯作者：
Isaac Lage;Emily Chen;Jeffrey He;Menaka Narayanan;Been Kim;Sam Gershman;F. Doshi-Velez
影响因子：
--
作者：
Jun Li;Daoyu Lin;Yang Wang;Guangluan Xu;C. Ding
通讯作者：
C. Ding
在可解释的机器学习中评估没有基本事实的解释
DOI：
--
发表时间：
2019
期刊：
arXiv.org
影响因子：
--
作者：
Fan Yang;Mengnan Du;Xia Hu
通讯作者：
Xia Hu
影响因子：
2.9
作者：
Montavon, Gregoire;Samek, Wojciech;Mueller, Klaus-Robert
通讯作者：
Mueller, Klaus-Robert
影响因子：
3.4
作者：
Mohseni, Sina;Zarei, Niloofar;Ragan, Eric D.
通讯作者：
Ragan, Eric D.