Amedeo Napoli
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Amedeo Napoli has a total of 111 co-authors. Here are the top co-authors by number of shared publications:
- Sergei O. Kuznetsov
School of Data Analysis and Artificial Intelligence, National Research University Higher School of Economics, Moscow, Russia
12 shared publications - Miguel Couceiro
INESC-ID, Instituto Superior Técnico, Universidade de Lisboa, Lisbon, Portugal
11 shared publications - Adrien Coulet
Inria, Inserm, Université Paris Cité, U1346 HeKA, Paris, France
7 shared publications - Jean Lieber
LORIA, Université de Lorraine, CNRS, INRIA
6 shared publications - Pierre Monnin
Université Côte d’Azur, Inria, CNRS, I3S, Sophia-Antipolis, France
6 shared publications - Jaume Baixeries
Universitat Politecnica de Catalunya
5 shared publications
Latest Publications
- 11 August 2026
- Published by Springer Nature
- p. 210-225
Themes and Variations in Integrating Clustering in FCA
- 11 August 2026
- Published by Springer Nature
- p. 210-225
Themes and Variations in Integrating Clustering in FCA
- 6 September 2025
- Published by Springer Nature
- p. 161-177
A Proposal for Building a Compact and Tunable Representation of a Concept Lattice Based on Clustering
- 6 September 2025
- Published by Springer Nature
- p. 161-177
A Proposal for Building a Compact and Tunable Representation of a Concept Lattice Based on Clustering
- 6 September 2025
- Published by Springer Nature
- p. 178-194
Atomic Patterns for Efficient Computation with Pattern Structures
- 6 September 2025
- Published by Springer Nature
- p. 178-194
Atomic Patterns for Efficient Computation with Pattern Structures
- 20 November 2024
- Published by Springer Nature
- p. 53-68
Discovering a Representative Set of Link Keys in RDF Datasets
- 20 November 2024
- Published by Springer Nature
- p. 53-68
Discovering a Representative Set of Link Keys in RDF Datasets
- 1 August 2024
- Published by Springer Nature
- p. 286-301
Document Classification via Stable Graph Patterns and Conceptual AMR Graphs
- 1 August 2024
- Published by Springer Nature
- p. 286-301
Document Classification via Stable Graph Patterns and Conceptual AMR Graphs
- 6 July 2023
- Published by Springer Nature
- p. 127-142
Description Quivers for Compact Representation of Concept Lattices and Ensembles of Decision Trees
- 6 July 2023
- Published by Springer Nature
- p. 127-142
Description Quivers for Compact Representation of Concept Lattices and Ensembles of Decision Trees
- 6 July 2023
- Published by Springer Nature
- p. 78-94
Three Views on Dependency Covers from an FCA Perspective
- 6 July 2023
- Published by Springer Nature
- p. 78-94
Three Views on Dependency Covers from an FCA Perspective
- Open Access
Clarity: an improved gradient method for producing quality visual counterfactual explanations
Visual counterfactual explanations identify modifications to an image that would change the prediction of a classifier. We propose a set of techniques based on generative models (VAE) and a classifier ensemble directly trained in the latent space, which all together, improve the quality of the gradient required to compute visual counterfactuals. These improvements lead to a novel classification model, Clarity, which produces realistic counterfactual explanations over all images. We also present several experiments that give insights on why these techniques lead to better quality results than those in the literature. The explanations produced are competitive with the state-of-the-art and emphasize the importance of selecting a meaningful input space for training.
Open AccessClarity: an improved gradient method for producing quality visual counterfactual explanations
Visual counterfactual explanations identify modifications to an image that would change the prediction of a classifier. We propose a set of techniques based on generative models (VAE) and a classifier ensemble directly trained in the latent space, which all together, improve the quality of the gradient required to compute visual counterfactuals. These improvements lead to a novel classification model, Clarity, which produces realistic counterfactual explanations over all images. We also present several experiments that give insights on why these techniques lead to better quality results than those in the literature. The explanations produced are competitive with the state-of-the-art and emphasize the importance of selecting a meaningful input space for training.
- 8 December 2021
- Published by Springer Nature
- p. 225-237
Towards Distributivity in FCA for Phylogenetic Data
- 8 December 2021
- Published by Springer Nature
- p. 225-237
Towards Distributivity in FCA for Phylogenetic Data