[HTML][HTML] Beyond explaining: Opportunities and challenges of XAI-based model improvement

L Weber, S Lapuschkin, A Binder, W Samek - Information Fusion, 2023 - Elsevier
Abstract Explainable Artificial Intelligence (XAI) is an emerging research field bringing
transparency to highly complex and opaque machine learning (ML) models. Despite the …

Utilizing explainable ai for improving the performance of neural networks

H Sun, L Servadei, H Feng, M Stephan… - 2022 21st IEEE …, 2022 - ieeexplore.ieee.org
Nowadays, deep neural networks are widely used in a variety of fields that have a direct
impact on society. Although those models typically show outstanding performance, they …

XAI-Enhanced Semantic Segmentation Models for Visual Quality Inspection

T Clement, TTH Nguyen, M Abdelaal… - 2024 IEEE International …, 2024 - ieeexplore.ieee.org
Visual quality inspection systems, crucial in sectors like manufacturing and logistics, employ
computer vision and machine learning for precise, rapid defect detection. However, their …

[PDF][PDF] Distillation for High-Quality Knowledge Extraction via Explainable Oracle Approach

MH Lee, W Cho, S Kim, J Kim, J Lee - 2023 - papers.bmvc2023.org
Recent successes suggest that knowledge distillation techniques can usefully transfer
knowledge between deep neural networks as compression and acceleration techniques, eg …

[PDF][PDF] SHAP-based explanations to improve classification systems

A Apicella, S Giugliano, F Isgrò, R Prevete - 2023 - ceur-ws.org
Abstract Explainable Artificial Intelligence (XAI) is a field usually dedicated to offering
insights into the decisionmaking mechanisms of AI models. Its purpose is to enable users to …

[PDF][PDF] ASurvey ON EXPLAINABLE ARTIFICIAL INTELLI-GENCE: TECHNIQUES, XAI-BASED MODEL IMPROVE-MENT METHODS, APPLICATIONS

TTH Nguyen - researchgate.net
This review serves as our note encapsulating our insights from the latest advancements and
research in the domain of Explainable Artificial Intelligence (XAI), focusing on the methods …