Evaluating the Performance of Explanation Methods on Ordinal Regression CNN Models
Hits: 2182
- Áreas de investigación:
- Sin categoría
- Año:
- 2023
- Tipo de publicación:
- Artículo en conferencia
- Palabras clave:
- Convolutional Neural Networks, Interpretability, Ordinal Regression
- Autores:
-
- Barbero-Gómez, Javier
- Cruz, Ricardo
- Cardoso, Jaime S.
- Gutiérrez, Pedro Antonio
- Hervás-Martínez, César
- Volumen:
- 14135
- Título del libro:
- IWANN 2023: Advances in Computational Intelligence
- Serie:
- Lecture Notes in Computer Science (LNCS)
- Páginas:
- 529-540
- Organización:
- Ponta Delgada, Portugal
- Mes:
- 19th-21th June, 2023
- Abstract:
- This paper introduces an evaluation procedure to validate the efficacy of explanation methods for Convolutional Neural Network (CNN) models in ordinal regression tasks. Two ordinal methods are contrasted against a baseline using cross-entropy, across four datasets. A statistical analysis demonstrates that attribution methods, such as Grad-CAM and IBA, perform significantly better when used with ordinal regression CNN models compared to a baseline approach in most ordinal and nominal metrics. The study suggests that incorporating ordinal information into the attribution map construction process may improve the explanations further.
