Eleonora Poeta
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Eleonora Poeta has a total of 13 co-authors. Here are the top co-authors by number of shared publications:
- Eliana Pastor
Politecnico di Torino
7 shared publications - Elena Baralis
Politecnico di Torino
6 shared publications - Tania Cerquitelli
Politecnico di Torino, Turin, Italy
6 shared publications - Daniele Rege Cambrin
Politecnico di Torino
3 shared publications - Gabriele Ciravegna
Politecnico di Torino
3 shared publications - Paolo Garza
Politecnico di Torino
3 shared publications
Latest Publications
- Top Cited PapersOpen Access
- 8 November 2025
- Published by Association for Computing Machinery (ACM) in ACM Computing Surveys
- Vol. 58 (16) , 1-36
Concept-based Explainable Artificial Intelligence: A Survey
The field of explainable artificial intelligence emerged in response to the growing need for more transparent and reliable models. However, using raw features to provide explanations has been discussed in several works lately, advocating for more user-understandable explanations. To address this issue, a wide range of papers proposing Concept-based eXplainable Artificial Intelligence (C-XAI) methods have been published in recent years. Nevertheless, a unified categorization and precise field definition are still missing. This paper fills the gap by offering a thorough review of C-XAI approaches. We identify and define different concepts and explanation types. We propose a taxonomy comprising nine categories and guidelines for selecting a suitable category based on the application context. Additionally, we discuss common evaluation strategies including metrics, human evaluations, and datasets employed, aiming to assist the development of future methods. Overall, we believe this survey will assist researchers, practitioners, and domain experts in enhancing their understanding and contributing to the progress of this innovative field.
- 8 November 2025
- Published by Association for Computing Machinery (ACM) in ACM Computing Surveys
- Vol. 58 (16) , 1-36
Top Cited PapersOpen AccessConcept-based Explainable Artificial Intelligence: A Survey
The field of explainable artificial intelligence emerged in response to the growing need for more transparent and reliable models. However, using raw features to provide explanations has been discussed in several works lately, advocating for more user-understandable explanations. To address this issue, a wide range of papers proposing Concept-based eXplainable Artificial Intelligence (C-XAI) methods have been published in recent years. Nevertheless, a unified categorization and precise field definition are still missing. This paper fills the gap by offering a thorough review of C-XAI approaches. We identify and define different concepts and explanation types. We propose a taxonomy comprising nine categories and guidelines for selecting a suitable category based on the application context. Additionally, we discuss common evaluation strategies including metrics, human evaluations, and datasets employed, aiming to assist the development of future methods. Overall, we believe this survey will assist researchers, practitioners, and domain experts in enhancing their understanding and contributing to the progress of this innovative field.
- Open Access
- 3 November 2025
- Published by Association for Computing Machinery (ACM)
- p. 265-276
HydroChronos: Forecasting Decades of Surface Water Change
- 3 November 2025
- Published by Association for Computing Machinery (ACM)
- p. 265-276
Open AccessHydroChronos: Forecasting Decades of Surface Water Change
- 21 September 2025
- Published by Springer Nature
- p. 52-62
Divergence-Aware Training with Automatic Subgroup Mitigation for Breast Tumor Segmentation
- 21 September 2025
- Published by Springer Nature
- p. 52-62
Divergence-Aware Training with Automatic Subgroup Mitigation for Breast Tumor Segmentation
- Open Access
- 3 August 2025
- Published by Association for Computing Machinery (ACM)
- p. 6247-6248
Beyond Input Attribution: A Hands-On Tutorial to Concept-Based Explainable AI and Mechanistic Interpretability
- 3 August 2025
- Published by Association for Computing Machinery (ACM)
- p. 6247-6248
Open AccessBeyond Input Attribution: A Hands-On Tutorial to Concept-Based Explainable AI and Mechanistic Interpretability
- 12 May 2025
- Published by Springer Nature
- p. 115-131
KAN You See It? KANs and Sentinel for Effective and Explainable Crop Field Segmentation
- 12 May 2025
- Published by Springer Nature
- p. 115-131
KAN You See It? KANs and Sentinel for Effective and Explainable Crop Field Segmentation
- Open Access
KAN You See It? KANs and Sentinel for Effective and Explainable Crop Field Segmentation
Segmentation of crop fields is essential for enhancing agricultural productivity, monitoring crop health, and promoting sustainable practices. Deep learning models adopted for this task must ensure accurate and reliable predictions to avoid economic losses and environmental impact. The newly proposed Kolmogorov-Arnold networks (KANs) offer promising advancements in the performance of neural networks. This paper analyzes the integration of KAN layers into the U-Net architecture (U-KAN) to segment crop fields using Sentinel-2 and Sentinel-1 satellite images and provides an analysis of the performance and explainability of these networks. Our findings indicate a 2\% improvement in IoU compared to the traditional full-convolutional U-Net model in fewer GFLOPs. Furthermore, gradient-based explanation techniques show that U-KAN predictions are highly plausible and that the network has a very high ability to focus on the boundaries of cultivated areas rather than on the areas themselves. The per-channel relevance analysis also reveals that some channels are irrelevant to this task.
Open AccessKAN You See It? KANs and Sentinel for Effective and Explainable Crop Field Segmentation
Segmentation of crop fields is essential for enhancing agricultural productivity, monitoring crop health, and promoting sustainable practices. Deep learning models adopted for this task must ensure accurate and reliable predictions to avoid economic losses and environmental impact. The newly proposed Kolmogorov-Arnold networks (KANs) offer promising advancements in the performance of neural networks. This paper analyzes the integration of KAN layers into the U-Net architecture (U-KAN) to segment crop fields using Sentinel-2 and Sentinel-1 satellite images and provides an analysis of the performance and explainability of these networks. Our findings indicate a 2\% improvement in IoU compared to the traditional full-convolutional U-Net model in fewer GFLOPs. Furthermore, gradient-based explanation techniques show that U-KAN predictions are highly plausible and that the network has a very high ability to focus on the boundaries of cultivated areas rather than on the areas themselves. The per-channel relevance analysis also reveals that some channels are irrelevant to this task.
- Open Access
Concept-based Explainable Artificial Intelligence: A Survey
The field of explainable artificial intelligence emerged in response to the growing need for more transparent and reliable models. However, using raw features to provide explanations has been disputed in several works lately, advocating for more user-understandable explanations. To address this issue, a wide range of papers proposing Concept-based eXplainable Artificial Intelligence (C-XAI) methods have arisen in recent years. Nevertheless, a unified categorization and precise field definition are still missing. This paper fills the gap by offering a thorough review of C-XAI approaches. We define and identify different concepts and explanation types. We provide a taxonomy identifying nine categories and propose guidelines for selecting a suitable category based on the development context. Additionally, we report common evaluation strategies including metrics, human evaluations and dataset employed, aiming to assist the development of future methods. We believe this survey will serve researchers, practitioners, and domain experts in comprehending and advancing this innovative field.
Open AccessConcept-based Explainable Artificial Intelligence: A Survey
The field of explainable artificial intelligence emerged in response to the growing need for more transparent and reliable models. However, using raw features to provide explanations has been disputed in several works lately, advocating for more user-understandable explanations. To address this issue, a wide range of papers proposing Concept-based eXplainable Artificial Intelligence (C-XAI) methods have arisen in recent years. Nevertheless, a unified categorization and precise field definition are still missing. This paper fills the gap by offering a thorough review of C-XAI approaches. We define and identify different concepts and explanation types. We provide a taxonomy identifying nine categories and propose guidelines for selecting a suitable category based on the development context. Additionally, we report common evaluation strategies including metrics, human evaluations and dataset employed, aiming to assist the development of future methods. We believe this survey will serve researchers, practitioners, and domain experts in comprehending and advancing this innovative field.