Skip to main content

Explaining Image Classifiers Using Statistical Fault Localization

  • Conference paper
  • First Online:
Computer Vision – ECCV 2020 (ECCV 2020)


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.

This is a preview of subscription content, log in via an institution to check access.

Access this chapter

Subscribe and save

Springer+ Basic
EUR 32.99 /Month
  • Get 10 units per month
  • Download Article/Chapter or Ebook
  • 1 Unit = 1 Article or 1 Chapter
  • Cancel anytime
Subscribe now

Buy Now

USD 29.95
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
USD 84.99
Price excludes VAT (USA)
  • Available as EPUB and PDF
  • Read on any device
  • Instant download
  • Own it forever
Softcover Book
USD 109.99
Price excludes VAT (USA)
  • Compact, lightweight edition
  • Dispatched in 3 to 5 business days
  • Free shipping worldwide - see info

Tax calculation will be finalised at checkout

Purchases are for personal use only

Institutional subscriptions

Similar content being viewed by others


  1. 1.

  2. 2.

    lime version 0.1.33; shap version 0.29.1; gradcam, rise and extremal are from (commit 6a198ee61d229360a3def590410378d2ed6f1f06).

  3. 3.

    The benchmark images are publicly available at


  1. Adebayo, J., Gilmer, J., Muelly, M., Goodfellow, I., Hardt, M., Kim, B.: Sanity checks for saliency maps. In: Advances in Neural Information Processing Systems, pp. 9505–9515 (2018)

    Google Scholar 

  2. Chajewska, U., Halpern, J.Y.: Defining explanation in probabilistic systems. In: Uncertainty in Artificial Intelligence (UAI), pp. 62–71. Morgan Kaufmann (1997)

    Google Scholar 

  3. Chen, J., Song, L., Wainwright, M., Jordan, M.: Learning to explain: an information-theoretic perspective on model interpretation. In: International Conference on Machine Learning (ICML), vol. 80, pp. 882–891. PMLR (2018)

    Google Scholar 

  4. Datta, A., Sen, S., Zick, Y.: Algorithmic transparency via quantitative input influence: theory and experiments with learning systems. In: Security and Privacy (S&P), pp. 598–617. IEEE (2016)

    Google Scholar 

  5. Eiter, T., Lukasiewicz, T.: Complexity results for explanations in the structural-model approach. Artif. Intell. 154(1–2), 145–198 (2004)

    Article  MathSciNet  Google Scholar 

  6. Fong, R., Patrick, M., Vedaldi, A.: Understanding deep networks via extremal perturbations and smooth masks. In: International Conference on Computer Vision (ICCV), pp. 2950–2958. IEEE (2019)

    Google Scholar 

  7. Gärdenfors, P.: Knowledge in Flux. MIT Press, Cambridge (1988)

    MATH  Google Scholar 

  8. Gonzalez-Sanchez, A.: Automatic error detection techniques based on dynamic invariants. M.S. thesis, Delft University of Technology, The Netherlands (2007)

    Google Scholar 

  9. Gunning, D.: Explainable artificial intelligence (XAI) - program information. Defense Advanced Research Projects Agency (2017).

  10. Halpern, J.Y., Pearl, J.: Causes and explanations: a structural-model approach. Part I: causes. Br. J. Philos. Sci. 56(4), 843–887 (2005)

    Article  Google Scholar 

  11. Halpern, J.Y., Pearl, J.: Causes and explanations: a structural-model approach. Part II: explanations. Br. J. Philos. Sci. 56(4), 889–911 (2005)

    Article  Google Scholar 

  12. Hempel, C.G.: Aspects of Scientific Explanation. Free Press, New York (1965)

    Google Scholar 

  13. Huang, X., et al.: A survey of safety and trustworthiness of deep neural networks: verification, testing, adversarial attack and defence, and interpretability. Comput. Sci. Rev. 37, 100270 (2020)

    Article  MathSciNet  Google Scholar 

  14. Jones, J.A., Harrold, M.J.: Empirical evaluation of the Tarantula automatic fault-localization technique. In: Proceedings of ASE, pp. 273–282. ACM (2005)

    Google Scholar 

  15. Landsberg, D., Chockler, H., Kroening, D., Lewis, M.: Evaluation of measures for statistical fault localisation and an optimising scheme. In: Egyed, A., Schaefer, I. (eds.) FASE 2015. LNCS, vol. 9033, pp. 115–129. Springer, Heidelberg (2015).

    Chapter  Google Scholar 

  16. Landsberg, D., Sun, Y., Kroening, D.: Optimising spectrum based fault localisation for single fault programs using specifications. In: Russo, A., Schürr, A. (eds.) FASE 2018. LNCS, vol. 10802, pp. 246–263. Springer, Cham (2018).

    Chapter  Google Scholar 

  17. Liu, Y., et al.: Trojaning attack on neural networks. In: Network and Distributed System Security Symposium (NDSS). The Internet Society (2018)

    Google Scholar 

  18. Lundberg, S.M., Lee, S.I.: A unified approach to interpreting model predictions. In: Advances in Neural Information Processing Systems, pp. 4765–4774 (2017)

    Google Scholar 

  19. Naish, L., Lee, H.J., Ramamohanarao, K.: A model for spectra-based software diagnosis. ACM TOSEM 20(3), 11 (2011)

    Article  Google Scholar 

  20. Noller, Y., Păsăreanu, C.S., Böhme, M., Sun, Y., Nguyen, H.L., Grunske, L.: HyDiff: hybrid differential software analysis. In: Proceedings of the International Conference on Software Engineering (ICSE) (2020)

    Google Scholar 

  21. Ochiai, A.: Zoogeographic studies on the soleoid fishes found in Japan and its neighbouring regions. Bull. Jpn. Soc. Sci. Fish. 22, 526–530 (1957)

    Article  Google Scholar 

  22. Odena, A., Olsson, C., Andersen, D., Goodfellow, I.: TensorFuzz: debugging neural networks with coverage-guided fuzzing. In: International Conference on Machine Learning, pp. 4901–4911 (2019)

    Google Scholar 

  23. Olah, C., et al.: The building blocks of interpretability. Distill 3, e10 (2018)

    Article  Google Scholar 

  24. Pearl, J.: Probabilistic Reasoning in Intelligent Systems. Morgan Kaufmann, Burlington (1988)

    MATH  Google Scholar 

  25. Petsiuk, V., Das, A., Saenko, K.: RISE: randomized input sampling for explanation of black-box models. In: British Machine Vision Conference (BMVC). BMVA Press (2018)

    Google Scholar 

  26. Rahwan, I., et al.: Machine behaviour. Nature 568(7753), 477 (2019)

    Article  Google Scholar 

  27. Ribeiro, M.T., Singh, S., Guestrin, C.: Why should I trust you? Explaining the predictions of any classifier. In: Knowledge Discovery and Data Mining (KDD), pp. 1135–1144. ACM (2016)

    Google Scholar 

  28. Salmon, W.C.: Four Decades of Scientific Explanation. University of Minnesota Press, Minneapolis (1989)

    Google Scholar 

  29. Selvaraju, R.R., Cogswell, M., Das, A., Vedantam, R., Parikh, D., Batra, D.: Grad-CAM: visual explanations from deep networks via gradient-based localization. In: International Conference on Computer Vision (ICCV), pp. 618–626. IEEE (2017)

    Google Scholar 

  30. Shrikumar, A., Greenside, P., Kundaje, A.: Learning important features through propagating activation differences. In: International Conference on Machine Learning (ICML), vol. 70, pp. 3145–3153. PMLR (2017)

    Google Scholar 

  31. Sun, Y., Wu, M., Ruan, W., Huang, X., Kwiatkowska, M., Kroening, D.: Concolic testing for deep neural networks. In: Proceedings of the 33rd ACM/IEEE International Conference on Automated Software Engineering, ASE, pp. 109–119 (2018)

    Google Scholar 

  32. Sun, Y., Zhou, Y., Maskell, S., Sharp, J., Huang, X.: Reliability validation of learning enabled vehicle tracking. In: International Conference on Robotics and Automation (ICRA). IEEE (2020)

    Google Scholar 

  33. Wong, W.E., Gao, R., Li, Y., Abreu, R., Wotawa, F.: A survey on software fault localization. IEEE TSE 42(8), 707–740 (2016)

    Google Scholar 

  34. Wong, W.E., Qi, Y., Zhao, L., Cai, K.: Effective fault localization using code coverage. In: Computer Software and Applications Conference (COMPSAC), pp. 449–456 (2007)

    Google Scholar 

  35. Zemla, J.C., Sloman, S., Bechlivanidis, C., Lagnado, D.A.: Evaluating everyday explanations. Psychon. Bull. Rev. 24(5), 1488–1500 (2017).

    Article  Google Scholar 

  36. Ziegler, C.: A Google self-driving car caused a crash for the first time. The Verge (2016).

Download references

Author information

Authors and Affiliations


Corresponding author

Correspondence to Youcheng Sun .

Editor information

Editors and Affiliations

Rights and permissions

Reprints and permissions

Copyright information

© 2020 Springer Nature Switzerland AG

About this paper

Check for updates. Verify currency and authenticity via CrossMark

Cite this paper

Sun, Y., Chockler, H., Huang, X., Kroening, D. (2020). Explaining Image Classifiers Using Statistical Fault Localization. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, JM. (eds) Computer Vision – ECCV 2020. ECCV 2020. Lecture Notes in Computer Science(), vol 12373. Springer, Cham.

Download citation

  • DOI:

  • Published:

  • Publisher Name: Springer, Cham

  • Print ISBN: 978-3-030-58603-4

  • Online ISBN: 978-3-030-58604-1

  • eBook Packages: Computer ScienceComputer Science (R0)

Publish with us

Policies and ethics