MetaCAM as an ensemble-based class activation mapping framework improves model explainability

Abstract The need for clear, trustworthy explanations of deep learning model predictions is essential for high-criticality fields, such as medicine and biometric identification. Class Activation Maps (CAMs) are an increasingly popular category of visual explanation methods for Convolutional Neural N...

ver descrição completa

Detalhes bibliográficos

Principais autores:	Kevin Dick, Emily Kaczmarek, Olivier X. Miguel, Alexa C. Bowie, Robin Ducharme, Alysha L. J. Dingwall-Harvey, Steven Hawken, Christine M. Armour, Mark C. Walker
Formato:	Artigo
Idioma:	Inglês
Publicado em:	Nature Portfolio 2026-03-01
Colecção:	Scientific Reports
Assuntos:	Class activation map Convolutional neural network Explainable artificial intelligence Ensemble machine learning
Acesso em linha:	https://doi.org/10.1038/s41598-026-42879-0
Tags:	Adicionar Tag Sem tags, seja o primeiro a adicionar uma tag!