Skip to main content

Making Heads or Tails: Towards Semantically Consistent Visual Counterfactuals

  • Conference paper
  • First Online:
Computer Vision – ECCV 2022 (ECCV 2022)

Part of the book series: Lecture Notes in Computer Science ((LNCS,volume 13672))

Included in the following conference series:

Abstract

A visual counterfactual explanation replaces image regions in a query image with regions from a distractor image such that the system’s decision on the transformed image changes to the distractor class. In this work, we present a novel framework for computing visual counterfactual explanations based on two key ideas. First, we enforce that the replaced and replacer regions contain the same semantic part, resulting in more semantically consistent explanations. Second, we use multiple distractor images in a computationally efficient way and obtain more discriminative explanations with fewer region replacements. Our approach is \(\mathbf {27\%}\) more semantically consistent and an order of magnitude faster than a competing method on three fine-grained image recognition datasets. We highlight the utility of our counterfactuals over existing works through machine teaching experiments where we teach humans to classify different bird species. We also complement our explanations with the vocabulary of parts and attributes that contributed the most to the system’s decision. In this task as well, we obtain state-of-the-art results when using our counterfactual explanations relative to existing works, reinforcing the importance of semantically consistent explanations. Source code is available at github.com/facebookresearch/visual-counterfactuals.

F. Radenovic and D. Ghadiyaram—Equal contribution.

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

Chapter
USD 29.95
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
eBook
USD 89.00
Price excludes VAT (USA)
  • Available as EPUB and PDF
  • Read on any device
  • Instant download
  • Own it forever
Softcover Book
USD 119.99
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

References

  1. Authors: Copyright for Figure 3 images from inaturalist-2021, employed for illustration of research work. iNaturalist people: longhairedlizzy: CC BY-NC 4.0, Volker Heinrich: CC BY-NC 4.0, Lee: CC BY-NC 4.0, Jonny Chung: CC BY-NC 4.0, romanvrbicek: CC BY-NC 4.0, poloyellow23: CC BY-NC 4.0. Accessed 02 Mar 2022

  2. Adadi, A., Berrada, M.: Peeking inside the black-box: a survey on explainable artificial intelligence (XAI). IEEE Access 6, 52138–52160 (2018)

    Article  Google Scholar 

  3. Adebayo, J., Gilmer, J., Muelly, M., Goodfellow, I., Hardt, M., Kim, B.: Sanity checks for saliency maps. In: NeurIPS (2018)

    Google Scholar 

  4. Akula, A., Wang, S., Zhu, S.C.: CoCoX: generating conceptual and counterfactual explanations via fault-lines. In: AAAI (2020)

    Google Scholar 

  5. Alipour, K., et al.: Improving users’ mental model with attention-directed counterfactual edits. Appl. AI Lett. 2, e47 (2021)

    Google Scholar 

  6. Ancona, M., Ceolini, E., Öztireli, C., Gross, M.: Towards better understanding of gradient-based attribution methods for deep neural networks. In: ICLR (2018)

    Google Scholar 

  7. Asano, Y., Rupprecht, C., Vedaldi, A.: Self-labelling via simultaneous clustering and representation learning. In: ICLR (2019)

    Google Scholar 

  8. Bach, S., Binder, A., Montavon, G., Klauschen, F., Müller, K.R., Samek, W.: On pixel-wise explanations for non-linear classifier decisions by layer-wise relevance propagation. PloS One 10, e0130140 (2015)

    Google Scholar 

  9. Beck, S.R., Riggs, K.J., Gorniak, S.L.: Relating developments in children’s counterfactual thinking and executive functions. Thinking Reason. 15, 337–354 (2009)

    Article  Google Scholar 

  10. Biggs, B., Boyne, O., Charles, J., Fitzgibbon, A., Cipolla, R.: Who left the dogs out? 3D animal reconstruction with expectation maximization in the loop. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12356, pp. 195–211. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-58621-8_12

    Chapter  Google Scholar 

  11. Buchsbaum, D., Bridgers, S., Skolnick Weisberg, D., Gopnik, A.: The power of possibility: causal learning, counterfactual reasoning, and pretend play. Philos. Trans. Roy. Soc. B: Biol. Sci. 367, 2202–2212 (2012)

    Google Scholar 

  12. Caron, M., Bojanowski, P., Joulin, A., Douze, M.: Deep clustering for unsupervised learning of visual features. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) Computer Vision – ECCV 2018. LNCS, vol. 11218, pp. 139–156. Springer, Cham (2018). https://doi.org/10.1007/978-3-030-01264-9_9

    Chapter  Google Scholar 

  13. Caron, M., Misra, I., Mairal, J., Goyal, P., Bojanowski, P., Joulin, A.: Unsupervised learning of visual features by contrasting cluster assignments. In: NeurIPS (2020)

    Google Scholar 

  14. Caron, M., et al.: Emerging properties in self-supervised vision transformers. In: ICCV (2021)

    Google Scholar 

  15. Chang, C.H., Creager, E., Goldenberg, A., Duvenaud, D.: Explaining image classifiers by counterfactual generation. In: ICLR (2018)

    Google Scholar 

  16. Chen, T., Kornblith, S., Norouzi, M., Hinton, G.: A simple framework for contrastive learning of visual representations. In: ICML (2020)

    Google Scholar 

  17. Dabkowski, P., Gal, Y.: Real time image saliency for black box classifiers. In: NeurIPS (2017)

    Google Scholar 

  18. Datta, A., Sen, S., Zick, Y.: Algorithmic transparency via quantitative input influence: theory and experiments with learning systems. In: IEEE SSP (2016)

    Google Scholar 

  19. Deng, J., Dong, W., Socher, R., Li, L.J., Li, K., Fei-Fei, L.: ImageNet: a large-scale hierarchical image database. In: CVPR (2009)

    Google Scholar 

  20. Dhurandhar, A., et al.: Explanations based on the missing: towards contrastive explanations with pertinent negatives. In: NeurIPS (2018)

    Google Scholar 

  21. Fong, R.C., Vedaldi, A.: Interpretable explanations of black boxes by meaningful perturbation. In: ICCV (2017)

    Google Scholar 

  22. Goyal, Y., Wu, Z., Ernst, J., Batra, D., Parikh, D., Lee, S.: Counterfactual visual explanations. In: ICML (2019)

    Google Scholar 

  23. He, K., Fan, H., Wu, Y., Xie, S., Girshick, R.: Momentum contrast for unsupervised visual representation learning. In: CVPR (2020)

    Google Scholar 

  24. He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: CVPR (2016)

    Google Scholar 

  25. Hvilshøj, F., Iosifidis, A., Assent, I.: ECINN: efficient counterfactuals from invertible neural networks. In: BMVC (2021)

    Google Scholar 

  26. Jacob, P., Zablocki, É., Ben-Younes, H., Chen, M., Pérez, P., Cord, M.: STEEX: steering counterfactual explanations with semantics. arXiv:2111.09094 (2021)

  27. Karras, T., Laine, S., Aittala, M., Hellsten, J., Lehtinen, J., Aila, T.: Analyzing and improving the image quality of stylegan. In: CVPR (2020)

    Google Scholar 

  28. Khosla, A., Jayadevaprakash, N., Yao, B., Fei-Fei, L.: Novel dataset for fine-grained image categorization. In: CVPR Workshop (2011)

    Google Scholar 

  29. Kim, B., et al.: Interpretability beyond feature attribution: quantitative testing with concept activation vectors (tcav). In: ICML (2018)

    Google Scholar 

  30. Koh, P.W., et al.: Concept bottleneck models. In: ICML (2020)

    Google Scholar 

  31. Lang, O., et al.: Explaining in style: training a GAN to explain a classifier in stylespace. In: ICCV (2021)

    Google Scholar 

  32. Liu, S., Kailkhura, B., Loveland, D., Han, Y.: Generative counterfactual introspection for explainable deep learning. In: GlobalSIP (2019)

    Google Scholar 

  33. Lundberg, S.M., Lee, S.I.: A unified approach to interpreting model predictions. In: NeurIPS (2017)

    Google Scholar 

  34. Markus, A.F., Kors, J.A., Rijnbeek, P.R.: The role of explainability in creating trustworthy artificial intelligence for health care: a comprehensive survey of the terminology, design choices, and evaluation strategies. JBI 113, 103655 (2021)

    Google Scholar 

  35. Miller, T.: Explanation in artificial intelligence: insights from the social sciences. Artif. Intell. 267, 1–38 (2019)

    Article  MathSciNet  Google Scholar 

  36. Mothilal, R.K., Sharma, A., Tan, C.: Explaining machine learning classifiers through diverse counterfactual explanations. In: ACM FAccT (2020)

    Google Scholar 

  37. Paszke, A., et al.: PyTorch: an imperative style, high-performance deep learning library. In: NeurIPS (2019)

    Google Scholar 

  38. Petsiuk, V., Das, A., Saenko, K.: RISE: randomized input sampling for explanation of black-box models. In: BMVC (2018)

    Google Scholar 

  39. Poyiadzi, R., Sokol, K., Santos-Rodriguez, R., De Bie, T., Flach, P.: FACE: feasible and actionable counterfactual explanations. In: AAAI/ACM AIES (2020)

    Google Scholar 

  40. Rebuffi, S.A., Fong, R., Ji, X., Vedaldi, A.: There and back again: revisiting backpropagation saliency methods. In: CVPR (2020)

    Google Scholar 

  41. Ribeiro, M.T., Singh, S., Guestrin, C.: “Why should i trust you?” explaining the predictions of any classifier. In: SIGKDD (2016)

    Google Scholar 

  42. Ribeiro, M.T., Singh, S., Guestrin, C.: Anchors: High-precision model-agnostic explanations. In: AAAI (2018)

    Google Scholar 

  43. Rodriguez, P., et al.: Beyond trivial counterfactual explanations with diverse valuable explanations. In: ICCV (2021)

    Google Scholar 

  44. 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: ICCV (2017)

    Google Scholar 

  45. Shrikumar, A., Greenside, P., Shcherbina, A., Kundaje, A.: Not just a black box: learning important features through propagating activation differences. arXiv:1605.01713 (2016)

  46. Simonyan, K., Vedaldi, A., Zisserman, A.: Deep inside convolutional networks: visualising image classification models and saliency maps. arXiv:1312.6034 (2013)

  47. Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. arXiv:1409.1556 (2014)

  48. Singla, S., Pollack, B., Chen, J., Batmanghelich, K.: Explanation by progressive exaggeration. In: ICLR (2019)

    Google Scholar 

  49. Singla, S., Pollack, B., Wallace, S., Batmanghelich, K.: Explaining the black-box smoothly-a counterfactual approach. arXiv:2101.04230 (2021)

  50. Slack, D., Hilgard, S., Jia, E., Singh, S., Lakkaraju, H.: Fooling lime and shap: adversarial attacks on post hoc explanation methods. In: AAAI (2020)

    Google Scholar 

  51. Sundararajan, M., Taly, A., Yan, Q.: Axiomatic attribution for deep networks. In: ICML (2017)

    Google Scholar 

  52. Van Gansbeke, W., Vandenhende, S., Georgoulis, S., Gool, L.V.: Revisiting contrastive methods for unsupervised learning of visual representations. In: NeurIPS (2021)

    Google Scholar 

  53. Van Gansbeke, W., Vandenhende, S., Georgoulis, S., Proesmans, M., Van Gool, L.: SCAN: learning to classify images without labels. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12355, pp. 268–285. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-58607-2_16

    Chapter  Google Scholar 

  54. Van Gansbeke, W., Vandenhende, S., Georgoulis, S., Van Gool, L.: Unsupervised semantic segmentation by contrasting object mask proposals. In: ICCV (2021)

    Google Scholar 

  55. Van Horn, G., Cole, E., Beery, S., Wilber, K., Belongie, S., Mac Aodha, O.: Benchmarking representation learning for natural world image collections. In: CVPR (2021)

    Google Scholar 

  56. Verma, S., Dickerson, J., Hines, K.: Counterfactual explanations for machine learning: a review. arXiv:2010.10596 (2020)

  57. Wachter, S., Mittelstadt, B., Russell, C.: Counterfactual explanations without opening the black box: automated decisions and the GDPR. Harv. J. Law Technol. 31, 841 (2018)

    Google Scholar 

  58. Wah, C., Branson, S., Welinder, P., Perona, P., Belongie, S.: The caltech-UCSD birds-200-2011 dataset. Technical report, California Institute of Technology (2011)

    Google Scholar 

  59. Wang, P., Vasconcelos, N.: SCOUT: self-aware discriminant counterfactual explanations. In: CVPR (2020)

    Google Scholar 

  60. Wu, Z., Xiong, Y., Yu, S.X., Lin, D.: Unsupervised feature learning via non-parametric instance discrimination. In: CVPR (2018)

    Google Scholar 

  61. Zablocki, É., Ben-Younes, H., Pérez, P., Cord, M.: Explainability of vision-based autonomous driving systems: review and challenges. arXiv:2101.05307 (2021)

  62. Zeiler, M.D., Fergus, R.: Visualizing and understanding convolutional networks. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8689, pp. 818–833. Springer, Cham (2014). https://doi.org/10.1007/978-3-319-10590-1_53

    Chapter  Google Scholar 

  63. Zhou, B., Khosla, A., Lapedriza, A., Oliva, A., Torralba, A.: Learning deep features for discriminative localization. In: CVPR (2016)

    Google Scholar 

  64. Zhou, B., Sun, Y., Bau, D., Torralba, A.: Interpretable basis decomposition for visual explanation. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11212, pp. 122–138. Springer, Cham (2018). https://doi.org/10.1007/978-3-030-01237-3_8

    Chapter  Google Scholar 

  65. Zintgraf, L.M., Cohen, T.S., Adel, T., Welling, M.: Visualizing deep neural network decisions: prediction difference analysis. In: ICLR (2017)

    Google Scholar 

Download references

Author information

Authors and Affiliations

Authors

Corresponding author

Correspondence to Simon Vandenhende .

Editor information

Editors and Affiliations

1 Electronic supplementary material

Below is the link to the electronic supplementary material.

Supplementary material 1 (pdf 3365 KB)

Rights and permissions

Reprints and permissions

Copyright information

© 2022 The Author(s), under exclusive license to Springer Nature Switzerland AG

About this paper

Check for updates. Verify currency and authenticity via CrossMark

Cite this paper

Vandenhende, S., Mahajan, D., Radenovic, F., Ghadiyaram, D. (2022). Making Heads or Tails: Towards Semantically Consistent Visual Counterfactuals. In: Avidan, S., Brostow, G., Cissé, M., Farinella, G.M., Hassner, T. (eds) Computer Vision – ECCV 2022. ECCV 2022. Lecture Notes in Computer Science, vol 13672. Springer, Cham. https://doi.org/10.1007/978-3-031-19775-8_16

Download citation

  • DOI: https://doi.org/10.1007/978-3-031-19775-8_16

  • Published:

  • Publisher Name: Springer, Cham

  • Print ISBN: 978-3-031-19774-1

  • Online ISBN: 978-3-031-19775-8

  • eBook Packages: Computer ScienceComputer Science (R0)

Publish with us

Policies and ethics