Go to:
Logótipo
Você está em: Start > Publications > View > CNN explanation methods for ordinal regression tasks
Map of Premises
Principal
Publication

CNN explanation methods for ordinal regression tasks

Title
CNN explanation methods for ordinal regression tasks
Type
Article in International Scientific Journal
Year
2025
Authors
Barbero-Gómez, J
(Author)
Other
The person does not belong to the institution. The person does not belong to the institution. The person does not belong to the institution. Without AUTHENTICUS Without ORCID
Cruz, RPM
(Author)
FEUP
View Personal Page You do not have permissions to view the institutional email. Search for Participant Publications View Authenticus page View ORCID page
Jaime S Cardoso
(Author)
FEUP
View Personal Page You do not have permissions to view the institutional email. Search for Participant Publications View Authenticus page View ORCID page
Gutiérrez, PA
(Author)
Other
The person does not belong to the institution. The person does not belong to the institution. The person does not belong to the institution. Without AUTHENTICUS Without ORCID
Hervás-Martínez, C
(Author)
Other
The person does not belong to the institution. The person does not belong to the institution. The person does not belong to the institution. Without AUTHENTICUS Without ORCID
Journal
Title: NeurocomputingImported from Authenticus Search for Journal Publications
Vol. 615
ISSN: 0925-2312
Publisher: Elsevier
Indexing
Publicação em ISI Web of Knowledge ISI Web of Knowledge - 0 Citations
Publicação em Scopus Scopus - 0 Citations
Other information
Authenticus ID: P-017-CCM
Abstract (EN): The use of Convolutional Neural Network (CNN) models for image classification tasks has gained significant popularity. However, the lack of interpretability in CNN models poses challenges for debugging and validation. To address this issue, various explanation methods have been developed to provide insights into CNN models. This paper focuses on the validity of these explanation methods for ordinal regression tasks, where the classes have a predefined order relationship. Different modifications are proposed for two explanation methods to exploit the ordinal relationships between classes: Grad-CAM based on Ordinal Binary Decomposition (GradOBDCAM) and Ordinal Information Bottleneck Analysis (OIBA). The performance of these modified methods is compared to existing popular alternatives. Experimental results demonstrate that GradOBD-CAM outperforms other methods in terms of interpretability for three out of four datasets, while OIBA achieves superior performance compared to IBA.
Language: English
Type (Professor's evaluation): Scientific
No. of pages: 9
Documents
We could not find any documents associated to the publication.
Related Publications

Of the same authors

Evaluating the Performance of Explanation Methods on Ordinal Regression CNN Models (2023)
Article in International Conference Proceedings Book
Barbero-Gómez, J; Cruz, R; Jaime S Cardoso; Gutiérrez, PA; Hervás-Martínez, C

Of the same journal

The vitality of pattern recognition and image analysis (2015)
Another Publication in an International Scientific Journal
Luisa Mico; Joao M Sanches; Jaime S Cardoso
ydata-profiling: Accelerating data-centric AI with high-quality data (2023)
Article in International Scientific Journal
Clemente, F; Ribeiro, GM; Quemy, A; Santos, MS; Pereira, RC; Barros, A
The vitality of pattern recognition and image analysis (2015)
Article in International Scientific Journal
Micó, L; Sanches, JM; Jaime S Cardoso
Pre-processing approaches for imbalanced distributions in regression (2019)
Article in International Scientific Journal
Branco, P; Torgo, L; Rita Ribeiro
Predicting satisfaction: perceived decision quality by decision-makers in Web-based group decision support systems (2019)
Article in International Scientific Journal
João Carneiro; Pedro Saraiva; Luís Conceição; Ricardo Santos; Goreti Marreiros; Paulo Novais

See all (22)

Recommend this page Top
Copyright 1996-2025 © Faculdade de Medicina Dentária da Universidade do Porto  I Terms and Conditions  I Acessibility  I Index A-Z
Page created on: 2025-08-07 at 12:45:28 | Privacy Policy | Personal Data Protection Policy | Whistleblowing | Electronic Yellow Book