Explaining Image Classifiers using Statistical Fault Localization

Youcheng Sun, Hana Chockler, Xiaowei Huang, Daniel Kroening

Research output: Chapter in Book/Report/Conference proceedingConference contribution

41 Downloads (Pure)

Abstract

The black-box nature of deep neural networks (DNNs) makes it impossible to understand why a particular output is produced, creating demand for “Explainable AI”. In this paper, we show that statistical fault localization (SFL) techniques from software engineering deliver high quality explanations of the outputs of DNNs, where we define an explanation as a minimal subset of features sufficient for making the same decision as for the original input. We present an algorithm and a tool called DeepCover, which synthesizes a ranking of the features of the inputs using SFL and constructs explanations for the decisions of the DNN based on this ranking. We compare explanations produced by DeepCover with those of the state-of-the-art tools gradcam, lime, shap, rise and extremal and show that explanations generated by DeepCover are consistently better across a broad set of experiments. On a benchmark set with known ground truth, DeepCover achieves 76.7% accuracy, which is 6% better than the second best extremal.
Original languageEnglish
Title of host publicationEuropean Conference on Computer Vision: 23-28 August 2020: Proceedings
PublisherSpringer
Pages391-406
ISBN (Print)978-3-030-58536-5
DOIs
Publication statusPublished - 03 Nov 2020

Publication series

NameLecture Notes in Computer Science
PublisherSpringer
ISSN (Print)0302-9743

Fingerprint Dive into the research topics of 'Explaining Image Classifiers using Statistical Fault Localization'. Together they form a unique fingerprint.

Cite this