@article{MertesHuberWeitzetal.2022, author = {Mertes, Silvan and Huber, Tobias and Weitz, Katharina and Heimerl, Alexander and Andr{\´e}, Elisabeth}, title = {GANterfactual—Counterfactual Explanations for Medical Non-experts Using Generative Adversarial Learning}, volume = {5}, pages = {825565}, journal = {Frontiers in Artificial Intelligence}, publisher = {Frontiers Media}, address = {Lausanne}, issn = {2624-8212}, doi = {https://doi.org/10.3389/frai.2022.825565}, year = {2022}, abstract = {With the ongoing rise of machine learning, the need for methods for explaining decisions made by artificial intelligence systems is becoming a more and more important topic. Especially for image classification tasks, many state-of-the-art tools to explain such classifiers rely on visual highlighting of important areas of the input data. Contrary, counterfactual explanation systems try to enable a counterfactual reasoning by modifying the input image in a way such that the classifier would have made a different prediction. By doing so, the users of counterfactual explanation systems are equipped with a completely different kind of explanatory information. However, methods for generating realistic counterfactual explanations for image classifiers are still rare. Especially in medical contexts, where relevant information often consists of textural and structural information, high-quality counterfactual images have the potential to give meaningful insights into decision processes. In this work, we present GANterfactual, an approach to generate such counterfactual image explanations based on adversarial image-to-image translation techniques. Additionally, we conduct a user study to evaluate our approach in an exemplary medical use case. Our results show that, in the chosen medical use-case, counterfactual explanations lead to significantly better results regarding mental models, explanation satisfaction, trust, emotions, and self-efficacy than two state-of-the art systems that work with saliency maps, namely LIME and LRP.}, language = {en} } @unpublished{MertesKarleHuberetal.2022, author = {Mertes, Silvan and Karle, Christina and Huber, Tobias and Weitz, Katharina and Schlagowski, Ruben and Andr{\´e}, Elisabeth}, title = {Alterfactual Explanations - The Relevance of Irrelevance for Explaining AI Systems}, publisher = {arXiv}, address = {Ithaca}, doi = {https://doi.org/10.48550/arXiv.2207.09374}, year = {2022}, abstract = {Explanation mechanisms from the field of Counterfactual Thinking are a widely-used paradigm for Explainable Artificial Intelligence (XAI), as they follow a natural way of reasoning that humans are familiar with. However, all common approaches from this field are based on communicating information about features or characteristics that are especially important for an AI's decision. We argue that in order to fully understand a decision, not only knowledge about relevant features is needed, but that the awareness of irrelevant information also highly contributes to the creation of a user's mental model of an AI system. Therefore, we introduce a new way of explaining AI systems. Our approach, which we call Alterfactual Explanations, is based on showing an alternative reality where irrelevant features of an AI's input are altered. By doing so, the user directly sees which characteristics of the input data can change arbitrarily without influencing the AI's decision. We evaluate our approach in an extensive user study, revealing that it is able to significantly contribute to the participants' understanding of an AI. We show that alterfactual explanations are suited to convey an understanding of different aspects of the AI's reasoning than established counterfactual explanation methods.}, language = {en} }