Generation of Rule-Based Explanations of CNN Classifiers Using Regional Features


Por: Philipp, W, Yashwanthika, R, Sikha, OK and Benítez R

Publicada: 5 sep 2024
Resumen:
Although Deep Learning networks generally outperform traditional machine learning approaches based on tailored features, they often lack explainability. To address this issue, numerous methods have been proposed, particularly for image-related tasks such as image classification or object segmentation. These methods generate a heatmap that visually explains the classification problem by identifying the most important regions for the classifier. However, these explanations remain purely visual. To overcome this limitation, we introduce a novel CNN explainability method that identifies the most relevant regions in an image and generates a decision tree based on meaningful regional features, providing a rule-based explanation of the classification model. We evaluated the proposed method on a synthetic blob's dataset and subsequently applied it to two cell image classification datasets with healthy and pathological patterns.

Filiaciones:
Philipp, W:
 Univ Politecn Catalunya UPC BarcelonaTECH, Automat Control Dept, Barcelona 08034, Spain

Yashwanthika, R:
 Amrita Vishwa Vidyapeetham, Dept Comp Sci & Engn, Amrita Sch Comp, Coimbatore, India

Sikha, OK:
 Univ Politecn Catalunya UPC BarcelonaTECH, Automat Control Dept, Barcelona 08034, Spain

 Amrita Vishwa Vidyapeetham, Dept Comp Sci & Engn, Amrita Sch Comp, Coimbatore, India

Benítez R:
 Univ Politecn Catalunya UPC BarcelonaTECH, Automat Control Dept, Barcelona 08034, Spain

 Inst Recerca Sant Joan de Deu IRSJD, Barcelona, Spain
ISSN: 13704621





NEURAL PROCESSING LETTERS
Editorial
SPRINGER, VAN GODEWIJCKSTRAAT 30, 3311 GZ DORDRECHT, NETHERLANDS, Bélgica
Tipo de documento: Article
Volumen: 56 Número: 5
Páginas:
WOS Id: 001306409200001
imagen hybrid

MÉTRICAS