Explainable Image Classification with Evidence Counterfactual

The complexity of state-of-the-art modeling techniques for image classification impedes the ability to explain model predictions in an interpretable way. Existing explanation methods generally create importance rankings in terms of pixels or pixel groups. However, the resulting explanations lack an optimal size, do not consider feature dependence and are only related to one class. Counterfactual explanation methods are considered promising to explain complex model decisions, since they are associated with a high degree of human interpretability. In this paper, SEDC is introduced as a model-agnostic instance-level explanation method for image classification to obtain visual counterfactual explanations. For a given image, SEDC searches a small set of segments that, in case of removal, alters the classification. As image classification tasks are typically multiclass problems, SEDC-T is proposed as an alternative method that allows specifying a target counterfactual class. We compare SEDC(-T) with popular feature importance methods such as LRP, LIME and SHAP, and we describe how the mentioned importance ranking issues are addressed. Moreover, concrete examples and experiments illustrate the potential of our approach (1) to obtain trust and insight, and (2) to obtain input for model improvement by explaining misclassifications.

[1]  Jun Wang,et al.  Working with Beliefs: AI Transparency in the Enterprise , 2018, IUI Workshops.

[2]  Foster J. Provost,et al.  Explaining Data-Driven Document Classifications , 2013, MIS Q..

[3]  Lee Lacy,et al.  Defense Advanced Research Projects Agency (DARPA) Agent Markup Language Computer Aided Knowledge Acquisition , 2005 .

[4]  Francisco Herrera,et al.  Explainable Artificial Intelligence (XAI): Concepts, Taxonomies, Opportunities and Challenges toward Responsible AI , 2020, Inf. Fusion.

[5]  Applying Image Recognition to Insurance June 2018 , 2018 .

[6]  Max Welling,et al.  Visualizing Deep Neural Network Decisions: Prediction Difference Analysis , 2017, ICLR.

[7]  Ziyan Wu,et al.  Counterfactual Visual Explanations , 2019, ICML.

[8]  Sebastian Thrun,et al.  Dermatologist-level classification of skin cancer with deep neural networks , 2017, Nature.

[9]  Ali N. Akansu,et al.  A class of fast Gaussian binomial filters for speech and image processing , 1991, IEEE Trans. Signal Process..

[10]  Rob Fergus,et al.  Visualizing and Understanding Convolutional Networks , 2013, ECCV.

[11]  David Martens,et al.  A Framework and Benchmarking Study for Counterfactual Generating Methods on Tabular Data , 2021, Applied Sciences.

[12]  Carlos Guestrin,et al.  Anchors: High-Precision Model-Agnostic Explanations , 2018, AAAI.

[13]  Theodoros Evgeniou,et al.  A comparison of instance-level counterfactual explanation algorithms for behavioral and textual data: SEDC, LIME-C and SHAP-C , 2019, Advances in Data Analysis and Classification.

[14]  Kouichi Sakurai,et al.  One Pixel Attack for Fooling Deep Neural Networks , 2017, IEEE Transactions on Evolutionary Computation.

[15]  Geoffrey E. Hinton,et al.  Deep Learning , 2015, Nature.

[16]  Amina Adadi,et al.  Peeking Inside the Black-Box: A Survey on Explainable Artificial Intelligence (XAI) , 2018, IEEE Access.

[17]  Scott Lundberg,et al.  A Unified Approach to Interpreting Model Predictions , 2017, NIPS.

[18]  Song-Chun Zhu,et al.  CoCoX: Generating Conceptual and Counterfactual Explanations via Fault-Lines , 2020, AAAI.

[19]  Pascal Fua,et al.  SLIC Superpixels Compared to State-of-the-Art Superpixel Methods , 2012, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[20]  Amit Dhurandhar,et al.  Explanations based on the Missing: Towards Contrastive Explanations with Pertinent Negatives , 2018, NeurIPS.

[21]  Carlos Guestrin,et al.  "Why Should I Trust You?": Explaining the Predictions of Any Classifier , 2016, ArXiv.

[22]  Stefano Soatto,et al.  Quick Shift and Kernel Methods for Mode Seeking , 2008, ECCV.

[23]  Lalana Kagal,et al.  J un 2 01 8 Explaining Explanations : An Approach to Evaluating Interpretability of Machine Learning , 2018 .

[24]  Zachary Chase Lipton The mythos of model interpretability , 2016, ACM Queue.

[25]  Alexander Binder,et al.  On Pixel-Wise Explanations for Non-Linear Classifier Decisions by Layer-Wise Relevance Propagation , 2015, PloS one.

[26]  David Weinberger,et al.  Accountability of AI Under the Law: The Role of Explanation , 2017, ArXiv.

[27]  Tommi S. Jaakkola,et al.  On the Robustness of Interpretability Methods , 2018, ArXiv.

[28]  Bolei Zhou,et al.  Object Detectors Emerge in Deep Scene CNNs , 2014, ICLR.

[29]  Md Zahidul Islam,et al.  Comparing sets of patterns with the Jaccard index , 2018, Australas. J. Inf. Syst..

[30]  Klaus-Robert Müller,et al.  Towards Explainable Artificial Intelligence , 2019, Explainable AI.

[31]  Jonathon Shlens,et al.  Explaining and Harnessing Adversarial Examples , 2014, ICLR.

[32]  D. Hilton,et al.  The Psychology of Counterfactual Thinking , 2005 .

[33]  Chris Russell,et al.  Counterfactual Explanations Without Opening the Black Box: Automated Decisions and the GDPR , 2017, ArXiv.

[34]  Freddy Lécué,et al.  Explainable AI: The New 42? , 2018, CD-MAKE.

[35]  Carlos Guestrin,et al.  Model-Agnostic Interpretability of Machine Learning , 2016, ArXiv.

[36]  Foster Provost,et al.  Explaining Data-Driven Decisions made by AI Systems: The Counterfactual Approach , 2020, MIS Quarterly.

[37]  Alexander Binder,et al.  Unmasking Clever Hans predictors and assessing what machines really learn , 2019, Nature Communications.

[38]  Mark Sandler,et al.  MobileNetV2: Inverted Residuals and Linear Bottlenecks , 2018, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

[39]  Lalana Kagal,et al.  Explaining Explanations: An Overview of Interpretability of Machine Learning , 2018, 2018 IEEE 5th International Conference on Data Science and Advanced Analytics (DSAA).

[40]  Ruth M. J. Byrne,et al.  Counterfactuals in Explainable Artificial Intelligence (XAI): Evidence from Human Reasoning , 2019, IJCAI.

[41]  EU guidelines on ethics in artificial intelligence : Context and implementation , 2019 .

[42]  Tim Miller,et al.  Explanation in Artificial Intelligence: Insights from the Social Sciences , 2017, Artif. Intell..

[43]  Solon Barocas,et al.  The hidden assumptions behind counterfactual explanations and principal reasons , 2019, FAT*.

[44]  Joan Bruna,et al.  Intriguing properties of neural networks , 2013, ICLR.

[45]  Bernhard Schölkopf,et al.  Algorithmic Recourse: from Counterfactual Explanations to Interventions , 2020, FAccT.

[46]  Luciano Floridi,et al.  Why a Right to Explanation of Automated Decision-Making Does Not Exist in the General Data Protection Regulation , 2017 .

[47]  Foster J. Provost,et al.  Enhancing Transparency and Control When Drawing Data-Driven Inferences About Individuals , 2016, Big Data.

[48]  Trevor Darrell,et al.  Generating Counterfactual Explanations with Natural Language , 2018, ICML 2018.

[49]  Seth Flaxman,et al.  European Union Regulations on Algorithmic Decision-Making and a "Right to Explanation" , 2016, AI Mag..

[50]  Yoshua Bengio,et al.  Gradient-based learning applied to document recognition , 1998, Proc. IEEE.