Counterfactual Visual Explanations

Yash Goyal, Ziyan Wu, Jan Ernst, Dhruv Batra, Devi Parikh, Stefan Lee
Proceedings of the 36th International Conference on Machine Learning, PMLR 97:2376-2384, 2019.

Abstract

In this work, we develop a technique to produce counterfactual visual explanations. Given a ‘query’ image $I$ for which a vision system predicts class $c$, a counterfactual visual explanation identifies how $I$ could change such that the system would output a different specified class $c’$. To do this, we select a ‘distractor’ image $I’$ that the system predicts as class $c’$ and identify spatial regions in $I$ and $I’$ such that replacing the identified region in $I$ with the identified region in $I’$ would push the system towards classifying $I$ as $c’$. We apply our approach to multiple image classification datasets generating qualitative results showcasing the interpretability and discriminativeness of our counterfactual explanations. To explore the effectiveness of our explanations in teaching humans, we present machine teaching experiments for the task of fine-grained bird classification. We find that users trained to distinguish bird species fare better when given access to counterfactual explanations in addition to training examples.

Cite this Paper

BibTeX
@InProceedings{pmlr-v97-goyal19a, title = {Counterfactual Visual Explanations}, author = {Goyal, Yash and Wu, Ziyan and Ernst, Jan and Batra, Dhruv and Parikh, Devi and Lee, Stefan}, booktitle = {Proceedings of the 36th International Conference on Machine Learning}, pages = {2376--2384}, year = {2019}, editor = {Chaudhuri, Kamalika and Salakhutdinov, Ruslan}, volume = {97}, series = {Proceedings of Machine Learning Research}, month = {09--15 Jun}, publisher = {PMLR}, pdf = {http://proceedings.mlr.press/v97/goyal19a/goyal19a.pdf}, url = {https://proceedings.mlr.press/v97/goyal19a.html}, abstract = {In this work, we develop a technique to produce counterfactual visual explanations. Given a ‘query’ image $I$ for which a vision system predicts class $c$, a counterfactual visual explanation identifies how $I$ could change such that the system would output a different specified class $c’$. To do this, we select a ‘distractor’ image $I’$ that the system predicts as class $c’$ and identify spatial regions in $I$ and $I’$ such that replacing the identified region in $I$ with the identified region in $I’$ would push the system towards classifying $I$ as $c’$. We apply our approach to multiple image classification datasets generating qualitative results showcasing the interpretability and discriminativeness of our counterfactual explanations. To explore the effectiveness of our explanations in teaching humans, we present machine teaching experiments for the task of fine-grained bird classification. We find that users trained to distinguish bird species fare better when given access to counterfactual explanations in addition to training examples.} }
Endnote
%0 Conference Paper %T Counterfactual Visual Explanations %A Yash Goyal %A Ziyan Wu %A Jan Ernst %A Dhruv Batra %A Devi Parikh %A Stefan Lee %B Proceedings of the 36th International Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2019 %E Kamalika Chaudhuri %E Ruslan Salakhutdinov %F pmlr-v97-goyal19a %I PMLR %P 2376--2384 %U https://proceedings.mlr.press/v97/goyal19a.html %V 97 %X In this work, we develop a technique to produce counterfactual visual explanations. Given a ‘query’ image $I$ for which a vision system predicts class $c$, a counterfactual visual explanation identifies how $I$ could change such that the system would output a different specified class $c’$. To do this, we select a ‘distractor’ image $I’$ that the system predicts as class $c’$ and identify spatial regions in $I$ and $I’$ such that replacing the identified region in $I$ with the identified region in $I’$ would push the system towards classifying $I$ as $c’$. We apply our approach to multiple image classification datasets generating qualitative results showcasing the interpretability and discriminativeness of our counterfactual explanations. To explore the effectiveness of our explanations in teaching humans, we present machine teaching experiments for the task of fine-grained bird classification. We find that users trained to distinguish bird species fare better when given access to counterfactual explanations in addition to training examples.
APA
Goyal, Y., Wu, Z., Ernst, J., Batra, D., Parikh, D. & Lee, S.. (2019). Counterfactual Visual Explanations. Proceedings of the 36th International Conference on Machine Learning, in Proceedings of Machine Learning Research 97:2376-2384 Available from https://proceedings.mlr.press/v97/goyal19a.html.

Related Material