Interpreting cnns via decision trees

Zhang, Quanshi1; Yang, Yu2; Ma, Haotian3; Wu, Ying Nian3

10.1109/CVPR.2019.00642

2019

1063-6919

32nd IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2019

2019-June

6254-6263

Long Beach, CA, United states

IEEE Computer Society

This paper aims to quantitatively explain the rationales of each prediction that is made by a pre-trained convolutional neural network (CNN). We propose to learn a decision tree, which clarifies the specific reason for each prediction made by the CNN at the semantic level. I.e., the decision tree decomposes feature representations in high conv-layers of the CNN into elementary concepts of object parts. In this way, the decision tree tells people which object parts activate which filters for the prediction and how much each object part contributes to the prediction score. Such semantic and quantitative explanations for CNN predictions have specific values beyond the traditional pixel-level analysis of CNNs. More specifically, our method mines all potential decision modes of the CNN, where each mode represents a typical case of how the CNN uses object parts for prediction. The decision tree organizes all potential decision modes in a coarse-to-fine manner to explain CNN predictions at different fine-grained levels. Experiments have demonstrated the effectiveness of the proposed method.
© 2019 IEEE.

其他

EI ; CPCI-S

Army Research Office[W911NF1810296] ; National Science Foundation[IIS 1423305] ; Defense Advanced Research Projects Agency[N66001-17-2-4029] ; Shanghai Jiao Tong University[]

20200508113545

Computer vision ; Forecasting ; Neural networks ; Semantic Segmentation ; Deep learning ; Semantics

Ergonomics and Human Factors Engineering:461.4 ; Artificial Intelligence:723.4 ; Computer Applications:723.5 ; Vision:741.2 ; Combinatorial Mathematics, Includes Graph Theory, Set Theory:921.4 ; Systems Science:961

EV Compendex

1.Shanghai Jiao Tong University, China
2.University of California, Los Angeles, United States
3.Southern University of Science and Technology, China

Zhang, Quanshi,Yang, Yu,Ma, Haotian,et al. Interpreting cnns via decision trees[C]:IEEE Computer Society,2019:6254-6263.