Interpretable Basis Decomposition for Visual Explanation

被引:160
作者
Zhou, Bolei [1 ]
Sun, Yiyou [2 ]
Bau, David [1 ]
Torralba, Antonio [1 ]
机构
[1] MIT, CSAIL, Cambridge, MA 02139 USA
[2] Harvard, Cambridge, MA USA
来源
COMPUTER VISION - ECCV 2018, PT VIII | 2018年 / 11212卷
基金
美国国家科学基金会;
关键词
D O I
10.1007/978-3-030-01237-3_8
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Explanations of the decisions made by a deep neural network are important for human end-users to be able to understand and diagnose the trustworthiness of the system. Current neural networks used for visual recognition are generally used as black boxes that do not provide any human interpretable justification for a prediction. In this work we propose a new framework called Interpretable Basis Decomposition for providing visual explanations for classification networks. By decomposing the neural activations of the input image into semantically interpretable components pre-trained from a large concept corpus, the proposed framework is able to disentangle the evidence encoded in the activation feature vector, and quantify the contribution of each piece of evidence to the final prediction. We apply our framework for providing explanations to several popular networks for visual recognition, and show it is able to explain the predictions given by the networks in a human-interpretable way. The human interpretability of the visual explanations provided by our framework and other recent explanation methods is evaluated through Amazon Mechanical Turk, showing that our framework generates more faithful and interpretable explanations (The code and data are available at https://github.com/CSAILVision/IBD).
引用
收藏
页码:122 / 138
页数:17
相关论文
共 30 条
[1]  
[Anonymous], 2016, arXiv preprint arXiv:1611.07450
[2]  
[Anonymous], 2014, ADV NEURAL INFORM PR
[3]  
[Anonymous], 2017, P IEEE C COMP VIS PA
[4]  
Antol S., 2015, P CVPR
[5]   On Pixel-Wise Explanations for Non-Linear Classifier Decisions by Layer-Wise Relevance Propagation [J].
Bach, Sebastian ;
Binder, Alexander ;
Montavon, Gregoire ;
Klauschen, Frederick ;
Mueller, Klaus-Robert ;
Samek, Wojciech .
PLOS ONE, 2015, 10 (07)
[6]  
Bau D., 2017, P CVPR
[7]  
Deng J., 2009, CVPR 2009
[8]  
Dosovitskiy Alexey, 2016, ADV NEURAL INFORM PR, V29, DOI DOI 10.48550/ARXIV.1602.02644
[9]   The PASCAL Visual Object Classes Challenge: A Retrospective [J].
Everingham, Mark ;
Eslami, S. M. Ali ;
Van Gool, Luc ;
Williams, Christopher K. I. ;
Winn, John ;
Zisserman, Andrew .
INTERNATIONAL JOURNAL OF COMPUTER VISION, 2015, 111 (01) :98-136
[10]  
Gonzalez-Garcia A., 2017, INT J COMPUT VIS, P1