paper-with-me

Papers

Be Careful When Evaluating Explanations Regarding Ground Truth

2023-11-08 · Hubert Baniecki, Maciej Chrabaszcz, Andreas Holzinger, Bastian Pfeifer, Anna Saranti, Przemyslaw Biecek

Evaluating explanations of image classifiers regarding ground truth, e.g. segmentation masks defined by human perception, primarily evaluates the quality of the models under consideration rather than the explanation methods themselves. Driven by this observation, we propose a framework for $\textit{jointly}$ evaluating the robustness of safety-critical systems that $\textit{combine}$ a deep neural network with an explanation method. These are increasingly used in real-world applications like medical image analysis or robotics. We introduce a fine-tuning procedure to (mis)align model$\unicode{x2013}$explanation pipelines with ground truth and use it to quantify the potential discrepancy between worst and best-case scenarios of human alignment. Experiments across various model architectures and post-hoc local interpretation methods provide insights into the robustness of vision transformers and the overall vulnerability of such AI systems to potential adversarial attacks.

📄 PDF Abstract BibTeX arXiv:2311.04813

Code (1)

mi2datalab/be-careful-evaluating-explanations 공식 구현 pytorch

Tasks

Medical Image Analysis

Similar Papers 제목 키워드 기반

Evaluating the Utility of Model Explanations for Model Development

2023-12-10 · Shawn Im, Jacob Andreas, Yilun Zhou

One of the motivations for explainable AI is to allow humans to make better and more informed decisions regarding the use and deployment of AI models. But careful evaluations are needed to assess whether this expectation…

counterfactualDecision MakingmodelModel Selection

Guiding the generation of counterfactual explanations through temporal background knowledge for Predictive Process Monitoring

2024-03-18 · Andrei Buliga, Chiara Di Francescomarino, Chiara Ghidini, Ivan Donadello 외

Counterfactual explanations suggest what should be different in the input instance to change the outcome of an AI system. When dealing with counterfactual explanations in the field of Predictive Process Monitoring, howev…

counterfactualPredictive Process Monitoring

(When) Are Contrastive Explanations of Reinforcement Learning Helpful?

2022-11-14 · Sanjana Narayanan, Isaac Lage, Finale Doshi-Velez

Global explanations of a reinforcement learning (RL) agent's expected behavior can make it safer to deploy. However, such explanations are often difficult to understand because of the complicated nature of many RL polici…

reinforcement-learningReinforcement LearningReinforcement Learning (RL)

Evaluating Model Explanations without Ground Truth

2025-05-15 · Kaivalya Rawal, Zihao Fu, Eoin Delaney, Chris Russell

There can be many competing and contradictory explanations for a single model prediction, making it difficult to select which one to use. Current explanation evaluation frameworks measure quality by comparing against ide…

Feature ImportancemodelSensitivity

Evaluating the Ability of Explanations to Disambiguate Models in a Rashomon Set

2026-01-13 · Kaivalya Rawal, Eoin Delaney, Zihao Fu, Sandra Wachter 외 arxiv

Explainable artificial intelligence (XAI) is concerned with producing explanations indicating the inner workings of models. For a Rashomon set of similarly performing models, explanations provide a way of disambiguating …