paper-with-me

Papers

SAFE: Saliency-Aware Counterfactual Explanations for DNN-based Automated Driving Systems

2023-07-28 · Amir Samadi, Amir Shirian, Konstantinos Koufos, Kurt Debattista, Mehrdad Dianati

A CF explainer identifies the minimum modifications in the input that would alter the model's output to its complement. In other words, a CF explainer computes the minimum modifications required to cross the model's decision boundary. Current deep generative CF models often work with user-selected features rather than focusing on the discriminative features of the black-box model. Consequently, such CF examples may not necessarily lie near the decision boundary, thereby contradicting the definition of CFs. To address this issue, we propose in this paper a novel approach that leverages saliency maps to generate more informative CF explanations. Source codes are available at: https://github.com/Amir-Samadi//Saliency_Aware_CF.

📄 PDF Abstract BibTeX arXiv:2307.15786

Code (0)

등록된 구현이 없습니다.

Tasks

counterfactual

Similar Papers 제목 키워드 기반

SAFE-RL: Saliency-Aware Counterfactual Explainer for Deep Reinforcement Learning Policies

2024-04-28 · Amir Samadi, Konstantinos Koufos, Kurt Debattista, Mehrdad Dianati

While Deep Reinforcement Learning (DRL) has emerged as a promising solution for intricate control tasks, the lack of explainability of the learned policies impedes its uptake in safety-critical applications, such as auto…

counterfactualDeep Reinforcement Learning

Info-CELS: Informative Saliency Map Guided Counterfactual Explanation

2024-10-27 · Peiyu Li, Omar Bahri, Pouya Hosseinzadeh, Soukaïna Filali Boubrahimi 외

As the demand for interpretable machine learning approaches continues to grow, there is an increasing necessity for human involvement in providing informative explanations for model decisions. This is necessary for build…

counterfactualCounterfactual ExplanationExplainable artificial intelligenceExplainable Artificial Intelligence (XAI)+1

Exploratory Not Explanatory: Counterfactual Analysis of Saliency Maps for Deep Reinforcement Learning

2019-12-09 · ICLR 2020 1 · Akanksha Atrey, Kaleigh Clary, David Jensen

Saliency maps are frequently used to support explanations of the behavior of deep reinforcement learning (RL) agents. However, a review of how saliency maps are used in practice indicates that the derived explanations ar…

Atari GamescounterfactualCounterfactual ReasoningDeep Reinforcement Learning+3

Provably Robust Bayesian Counterfactual Explanations under Model Changes

2026-01-23 · Jamie Duell, Xiuyi Fan arxiv

Counterfactual explanations (CEs) offer interpretable insights into machine learning predictions by answering ``what if?" questions. However, in real-world settings where models are frequently updated, existing counterfa…

Counterfactual-based Saliency Map: Towards Visual Contrastive Explanations for Neural Networks

2023-01-01 · ICCV 2023 1 · Xue Wang, Zhibo Wang, Haiqin Weng, Hengchang Guo 외

Explaining deep models in a human-understandable way has been explored by many works that mostly explain why an input causes a corresponding prediction (ie., Why P?). However, seldom they could handle those more comp…

counterfactual