Hervé Luga
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
Hervé Luga has a total of 83 co-authors. Here are the top co-authors by number of shared publications:
Yves Duthen
University of Toulouse, Toulouse, France
22 shared publicationsSylvain Cussat-Blanc
IRIT, UMR5505 CNRS, Université de Toulouse, Toulouse, France
12 shared publications- Sylvain Cussat-Blanc
Institut de Recherche en Informatique de Toulouse (IRIT) , Toulouse 31400
11 shared publications - Camilo De La Torre
Université Toulouse Capitole, IRIT - CNRS UMR5505
8 shared publications - Dennis G. Wilson
ISAE-SUPAERO, University of Toulouse
8 shared publications - Noureddine Djedi
LESIA Laboratory Department of computer Science Biskra University, Algeria
7 shared publications
Latest Publications
- 3 June 2026
- Published by Springer Nature
- p. 79-101
On Interpretability in Multimodal Biomedical Image Analysis
- 3 June 2026
- Published by Springer Nature
- p. 79-101
On Interpretability in Multimodal Biomedical Image Analysis
- 28 April 2026
- Published by Springer Nature
- p. 34-50
A Comparative Study on Robustness in Evolved Image Classifiers
- 28 April 2026
- Published by Springer Nature
- p. 34-50
A Comparative Study on Robustness in Evolved Image Classifiers
- Open Access
- 11 April 2026
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Evolutionary Learning and Optimization
Analyzing Interpretable Visual Control Policy Search and Synthesis
Vision-based decision-making is relevant to many domains, including safety-critical ones where transparency matters as much as performance. Therefore, automating sequential decision making in such settings requires approaches that balance effectiveness with interpretability. While deep reinforcement learning techniques based on artificial neural networks have achieved strong performance, their black-box nature typically necessitates post hoc explainability analyses. To address this limitation, we propose an approach based on Graph-based Genetic Programming (GGP) that generates policies in the form of computer code, which is fully observable and inherently interpretable. To improve both performance and robustness, we expose GGP-based visual control policies to multiple representative conditions during optimization, mitigating convergence to strong local optima and fragility under changing conditions. Finally, to gain insights into the evolutionary search dynamics, we employ Search Trajectory Networks, an analytical and visualization tool for studying optimization behavior. Our results demonstrate that the resulting policies approach human-level performance and empirically confirm the presence of strong local optima acting as attractors during evolution, providing new insights into the behavior and potential limitations of interpretable evolutionary policy search approaches.
- 11 April 2026
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Evolutionary Learning and Optimization
Open AccessAnalyzing Interpretable Visual Control Policy Search and Synthesis
Vision-based decision-making is relevant to many domains, including safety-critical ones where transparency matters as much as performance. Therefore, automating sequential decision making in such settings requires approaches that balance effectiveness with interpretability. While deep reinforcement learning techniques based on artificial neural networks have achieved strong performance, their black-box nature typically necessitates post hoc explainability analyses. To address this limitation, we propose an approach based on Graph-based Genetic Programming (GGP) that generates policies in the form of computer code, which is fully observable and inherently interpretable. To improve both performance and robustness, we expose GGP-based visual control policies to multiple representative conditions during optimization, mitigating convergence to strong local optima and fragility under changing conditions. Finally, to gain insights into the evolutionary search dynamics, we employ Search Trajectory Networks, an analytical and visualization tool for studying optimization behavior. Our results demonstrate that the resulting policies approach human-level performance and empirically confirm the presence of strong local optima acting as attractors during evolution, providing new insights into the behavior and potential limitations of interpretable evolutionary policy search approaches.
- 1 February 2026
- Published by Springer Nature
- p. 311-332
Extending Cartesian Genetic Programming via Iterative Subgraph Assessment
- 1 February 2026
- Published by Springer Nature
- p. 311-332
Extending Cartesian Genetic Programming via Iterative Subgraph Assessment
- Open Access
- 14 July 2025
- Published by Association for Computing Machinery (ACM)
- p. 2162-2166
On Chromosome Crossover in Multimodal Adaptive Graph Evolution
- 14 July 2025
- Published by Association for Computing Machinery (ACM)
- p. 2162-2166
Open AccessOn Chromosome Crossover in Multimodal Adaptive Graph Evolution
- Open Access
- 13 July 2025
- Published by Association for Computing Machinery (ACM)
- p. 358-367
Evolution of Inherently Interpretable Visual Control Policies
- 13 July 2025
- Published by Association for Computing Machinery (ACM)
- p. 358-367
Open AccessEvolution of Inherently Interpretable Visual Control Policies
- 18 April 2025
- Published by Springer Nature
- p. 173-189
Evolved and Transparent Pipelines for Biomedical Image Classification
- 18 April 2025
- Published by Springer Nature
- p. 173-189
Evolved and Transparent Pipelines for Biomedical Image Classification
- 7 September 2024
- Published by Springer Nature
- p. 306-321
Multimodal Adaptive Graph Evolution for Program Synthesis
- 7 September 2024
- Published by Springer Nature
- p. 306-321
Multimodal Adaptive Graph Evolution for Program Synthesis
- 21 March 2024
- Published by Springer Nature
- p. 19-34
Improving Image Filter Efficiency: A Multi-objective Genetic Algorithm Approach to Optimize Computing Efficiency
- 21 March 2024
- Published by Springer Nature
- p. 19-34
Improving Image Filter Efficiency: A Multi-objective Genetic Algorithm Approach to Optimize Computing Efficiency
- 20 April 2022
- Published by Springer Nature in Journal of Digital Imaging
- Vol. 35 (5) , 1326-1349
Finding a Suitable Class Distribution for Building Histological Images Datasets Used in Deep Model Training—The Case of Cancer Detection
The class distribution of a training dataset is an important factor which influences the performance of a deep learning-based system. Understanding the optimal class distribution is therefore crucial when building a new training set which may be costly to annotate. This is the case for histological images used in cancer diagnosis where image annotation requires domain experts. In this paper, we tackle the problem of finding the optimal class distribution of a training set to be able to train an optimal model that detects cancer in histological images. We formulate several hypotheses which are then tested in scores of experiments with hundreds of trials. The experiments have been designed to account for both segmentation and classification frameworks with various class distributions in the training set, such as natural, balanced, over-represented cancer, and over-represented non-cancer. In the case of cancer detection, the experiments show several important results: (a) the natural class distribution produces more accurate results than the artificially generated balanced distribution; (b) the over-representation of non-cancer/negative classes (healthy tissue and/or background classes) compared to cancer/positive classes reduces the number of samples which are falsely predicted as cancer (false positive); (c) the least expensive to annotate non-ROI (non-region-of-interest) data can be useful in compensating for the performance loss in the system due to a shortage of expensive to annotate ROI data; (d) the multi-label examples are more useful than the single-label ones to train a segmentation model; and (e) when the classification model is tuned with a balanced validation set, it is less affected than the segmentation model by the class distribution of the training set.
- 20 April 2022
- Published by Springer Nature in Journal of Digital Imaging
- Vol. 35 (5) , 1326-1349
Finding a Suitable Class Distribution for Building Histological Images Datasets Used in Deep Model Training—The Case of Cancer Detection
The class distribution of a training dataset is an important factor which influences the performance of a deep learning-based system. Understanding the optimal class distribution is therefore crucial when building a new training set which may be costly to annotate. This is the case for histological images used in cancer diagnosis where image annotation requires domain experts. In this paper, we tackle the problem of finding the optimal class distribution of a training set to be able to train an optimal model that detects cancer in histological images. We formulate several hypotheses which are then tested in scores of experiments with hundreds of trials. The experiments have been designed to account for both segmentation and classification frameworks with various class distributions in the training set, such as natural, balanced, over-represented cancer, and over-represented non-cancer. In the case of cancer detection, the experiments show several important results: (a) the natural class distribution produces more accurate results than the artificially generated balanced distribution; (b) the over-representation of non-cancer/negative classes (healthy tissue and/or background classes) compared to cancer/positive classes reduces the number of samples which are falsely predicted as cancer (false positive); (c) the least expensive to annotate non-ROI (non-region-of-interest) data can be useful in compensating for the performance loss in the system due to a shortage of expensive to annotate ROI data; (d) the multi-label examples are more useful than the single-label ones to train a segmentation model; and (e) when the classification model is tuned with a balanced validation set, it is less affected than the segmentation model by the class distribution of the training set.