查看文章

In this work, we develop a technique to produce counterfactual visual explanations. Given a ‘query’image for which a vision system predicts class , a counterfactual visual explanation identifies how could change such that the system would output a different specified class . To do this, we select a ‘distractor’image that the system predicts as class and identify spatial regions in and such that replacing the identified region in with the identified region in would push the system towards classifying as . 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.