| Title: | Enhancing trust in automated 3D point cloud data interpretation through explainable counterfactuals |
|---|
| Authors: | ID Holzinger, Andreas (Author)
ID Lukač, Niko (Author)
ID Rozajac, Dzemail (Author)
ID Johnston, Emil (Author)
ID Kočić, Veljka (Author)
ID Hoerl, Bernhard (Author)
ID Gollob, Christoph (Author)
ID Nothdurft, Arne (Author)
ID Stampfer, Karl (Author)
ID Schweng, Stefan (Author)
ID Del Ser, Javier (Author) |
|---|
| Files: |  1-s2.0-S1566253525001058-main.pdf (3,74 MB)
MD5: 285223F94FB5F290B890C8E5585DBEA5
 https://www.sciencedirect.com/science/article/pii/S1566253525001058?via%3Dihub
|
|---|
| Language: | English |
|---|
| Work type: | Article |
|---|
| Typology: | 1.01 - Original Scientific Article |
|---|
| Organization: | FERI - Faculty of Electrical Engineering and Computer Science
|
|---|
| Abstract: | This paper introduces a novel framework for augmenting explainability in the interpretation of point cloud data by fusing expert knowledge with counterfactual reasoning. Given the complexity and voluminous nature of point cloud datasets, derived predominantly from LiDAR and 3D scanning technologies, achieving interpretability remains a significant challenge, particularly in smart cities, smart agriculture, and smart forestry. This research posits that integrating expert knowledge with counterfactual explanations – speculative scenarios illustrating how altering input data points could lead to different outcomes – can significantly reduce the opacity of deep learning models processing point cloud data. The proposed optimization-driven framework utilizes expert-informed ad-hoc perturbation techniques to generate meaningful counterfactual scenarios when employing state-of-the-art deep learning architectures. The optimization process minimizes a multi-criteria objective comprising counterfactual metrics such as similarity, validity, and sparsity, which are specifically tailored for point cloud datasets. These metrics provide a quantitative lens for evaluating the interpretability of the counterfactuals. Furthermore, the proposed framework allows for the definition of explicit interpretable counterfactual perturbations at its core, thereby involving the audience of the model in the counterfactual generation pipeline and ultimately, improving their overall trust in the process. Results demonstrate a notable improvement in both the interpretability of the model’s decisions and the actionable insights delivered to end-users. Additionally, the study explores the role of counterfactual reasoning, coupled with expert input, in enhancing trustworthiness and enabling human-in-the-loop decision-making processes. By bridging the gap between complex data interpretations and user comprehension, this research advances the field of explainable AI, contributing to the development of transparent, accountable, and human-centered artificial intelligence systems. |
|---|
| Keywords: | explainable AI, point cloud data, counterfactual reasoning, information fusion, interpretability, human-centered AI |
|---|
| Publication status: | Published |
|---|
| Publication version: | Version of Record |
|---|
| Submitted for review: | 03.12.2024 |
|---|
| Article acceptance date: | 13.02.2025 |
|---|
| Publication date: | 25.02.2025 |
|---|
| Publisher: | Elsevier BV |
|---|
| Year of publishing: | 2025 |
|---|
| Number of pages: | 15 str. |
|---|
| Numbering: | Vol. 119, [article no.] 103032 |
|---|
| PID: | 20.500.12556/DKUM-91959  |
|---|
| UDC: | 004.8 |
|---|
| ISSN on article: | 1872-6305 |
|---|
| COBISS.SI-ID: | 228135939 |
|---|
| DOI: | 10.1016/j.inffus.2025.103032 |
|---|
| Copyright: | © 2025 The Authors |
|---|
| Publication date in DKUM: | 06.03.2025 |
|---|
| Views: | 164 |
|---|
| Downloads: | 8 |
|---|
| Metadata: |    |
|---|
| Categories: | Misc.
|
|---|
|
:
|
Copy citation |
|---|
| | | | Average score: | (0 votes) |
|---|
| Your score: | Voting is allowed only for logged in users. |
|---|
| Share: |  |
|---|
Hover the mouse pointer over a document title to show the abstract or click
on the title to get all document metadata. |
