Next Article in Journal
Rising Temperature Is a More Important Driver Than Increasing Carbon Dioxide Concentrations in the Trait Responses of Enhalus acoroides Seedlings
Previous Article in Journal
A Novel Multi-Criteria Sorting Model Based on AHP-Entropy Grey Clustering for Dealing with Uncertain Incoming Core Quality in Remanufacturing Systems
Article

Towards a Reliable Evaluation of Local Interpretation Methods

by 1,2,3,4, 1,2, 1,2, 1,2 and 1,3,4,*
1
Aerospace Information Research Institute, Chinese Academy of Sciences, Beijing 100094, China
2
Key Laboratory of Network Information System Technology (NIST), Institute of Electronics, Chinese Academy of Sciences, Beijing 100190, China
3
University of Chinese Academy of Sciences, Beijing 100094, China
4
School of Electronic, Electrical and Communication Engineering, University of Chinese Academy of Sciences, Beijing 100190, China
*
Author to whom correspondence should be addressed.
Academic Editor: Ángel González-Prieto
Appl. Sci. 2021, 11(6), 2732; https://doi.org/10.3390/app11062732
Received: 25 January 2021 / Revised: 8 March 2021 / Accepted: 16 March 2021 / Published: 18 March 2021
The growing use of deep neural networks in critical applications is making interpretability urgently to be solved. Local interpretation methods are the most prevalent and accepted approach for understanding and interpreting deep neural networks. How to effectively evaluate the local interpretation methods is challenging. To address this question, a unified evaluation framework is proposed, which assesses local interpretation methods from three dimensions: accuracy, persuasibility and class discriminativeness. Specifically, in order to assess correctness, we designed an interactive user feature annotation tool to provide ground truth for local interpretation methods. To verify the usefulness of the interpretation method, we iteratively display part of the interpretation results, and then ask users whether they agree with the category information. At the same time, we designed and built a set of evaluation data sets with a rich hierarchical structure. Surprisingly, one finding is that the existing visual interpretation methods cannot satisfy all evaluation dimensions at the same time, and each has its own shortcomings. View Full-Text
Keywords: deep learning interpretability evaluation; prediction explanation; saliency map deep learning interpretability evaluation; prediction explanation; saliency map
Show Figures

Figure 1

MDPI and ACS Style

Li, J.; Lin, D.; Wang, Y.; Xu, G.; Ding, C. Towards a Reliable Evaluation of Local Interpretation Methods. Appl. Sci. 2021, 11, 2732. https://doi.org/10.3390/app11062732

AMA Style

Li J, Lin D, Wang Y, Xu G, Ding C. Towards a Reliable Evaluation of Local Interpretation Methods. Applied Sciences. 2021; 11(6):2732. https://doi.org/10.3390/app11062732

Chicago/Turabian Style

Li, Jun, Daoyu Lin, Yang Wang, Guangluan Xu, and Chibiao Ding. 2021. "Towards a Reliable Evaluation of Local Interpretation Methods" Applied Sciences 11, no. 6: 2732. https://doi.org/10.3390/app11062732

Find Other Styles
Note that from the first issue of 2016, MDPI journals use article numbers instead of page numbers. See further details here.

Article Access Map by Country/Region

1
Back to TopTop