XAI for Point Cloud Data Using Perturbations Based on Meaningful Segmentation
In this work, we propose a novel segmentation-based explainable artificial intelligence (XAI) method for neural networks working on point cloud classification. As one building block of this method, we also propose a novel point-shifting mechanism to introduce perturbations in point cloud data. In th...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2025-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/11121187/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849390401127972864 |
|---|---|
| author | Raju Ningappa Mulawade Christoph Garth Alexander Wiebel |
| author_facet | Raju Ningappa Mulawade Christoph Garth Alexander Wiebel |
| author_sort | Raju Ningappa Mulawade |
| collection | DOAJ |
| description | In this work, we propose a novel segmentation-based explainable artificial intelligence (XAI) method for neural networks working on point cloud classification. As one building block of this method, we also propose a novel point-shifting mechanism to introduce perturbations in point cloud data. In the last decade, Artificial intelligence (AI) has seen an exponential growth. However, due to the “black-box” nature of many of these AI algorithms, it is important to understand their decision-making process when it comes to their application in critical areas. Our work focuses on explaining AI algorithms that classify point cloud data. An important aspect of the methods used for explaining AI algorithms is their ability to produce explanations that are easy for humans to understand. This allows the users to analyze the performance of AI algorithms better and make appropriate decisions based on that analysis. Therefore, in this work, we intend to generate meaningful explanations that can be easily interpreted by humans. The point cloud data considered in this work represents 3D objects such as cars, guitars, and laptops. We make use of point cloud segmentation models to generate explanations for the working of classification models. The segments are used to introduce perturbations into the input point cloud data and generate saliency maps. The perturbations are introduced using the novel point-shifting mechanism proposed in this work which ensures that the shifted points no longer influence the output of the classification algorithm. In contrast to any previous methods, the segments used by our method are meaningful, i.e. humans can easily interpret the meaning of these segments. Thus, the benefit of our method over other methods is its ability to produce more meaningful saliency maps. We compare our method with the use of classical clustering algorithms to generate explanations. We also analyze the saliency maps generated for some example inputs using our method to demonstrate the usefulness of our proposed method in generating meaningful explanations. |
| format | Article |
| id | doaj-art-0b91a0b03bbb4cc9a3092bab0c85733a |
| institution | Kabale University |
| issn | 2169-3536 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj-art-0b91a0b03bbb4cc9a3092bab0c85733a2025-08-20T03:41:40ZengIEEEIEEE Access2169-35362025-01-011314017514018610.1109/ACCESS.2025.359709411121187XAI for Point Cloud Data Using Perturbations Based on Meaningful SegmentationRaju Ningappa Mulawade0https://orcid.org/0000-0002-0180-8517Christoph Garth1https://orcid.org/0000-0003-1669-8549Alexander Wiebel2https://orcid.org/0000-0002-6583-3092ZFT and UX-Vis, Hochschule Worms University of Applied Sciences, Worms, GermanyScientific Visualization Laboratory, Rheinland-Pfälzische Technische Universität (RPTU) Kaiserslautern–Landau, Kaiserslautern, GermanyZFT and UX-Vis, Hochschule Worms University of Applied Sciences, Worms, GermanyIn this work, we propose a novel segmentation-based explainable artificial intelligence (XAI) method for neural networks working on point cloud classification. As one building block of this method, we also propose a novel point-shifting mechanism to introduce perturbations in point cloud data. In the last decade, Artificial intelligence (AI) has seen an exponential growth. However, due to the “black-box” nature of many of these AI algorithms, it is important to understand their decision-making process when it comes to their application in critical areas. Our work focuses on explaining AI algorithms that classify point cloud data. An important aspect of the methods used for explaining AI algorithms is their ability to produce explanations that are easy for humans to understand. This allows the users to analyze the performance of AI algorithms better and make appropriate decisions based on that analysis. Therefore, in this work, we intend to generate meaningful explanations that can be easily interpreted by humans. The point cloud data considered in this work represents 3D objects such as cars, guitars, and laptops. We make use of point cloud segmentation models to generate explanations for the working of classification models. The segments are used to introduce perturbations into the input point cloud data and generate saliency maps. The perturbations are introduced using the novel point-shifting mechanism proposed in this work which ensures that the shifted points no longer influence the output of the classification algorithm. In contrast to any previous methods, the segments used by our method are meaningful, i.e. humans can easily interpret the meaning of these segments. Thus, the benefit of our method over other methods is its ability to produce more meaningful saliency maps. We compare our method with the use of classical clustering algorithms to generate explanations. We also analyze the saliency maps generated for some example inputs using our method to demonstrate the usefulness of our proposed method in generating meaningful explanations.https://ieeexplore.ieee.org/document/11121187/Artificial intelligenceexplainable AIpoint cloud datasegmentation |
| spellingShingle | Raju Ningappa Mulawade Christoph Garth Alexander Wiebel XAI for Point Cloud Data Using Perturbations Based on Meaningful Segmentation IEEE Access Artificial intelligence explainable AI point cloud data segmentation |
| title | XAI for Point Cloud Data Using Perturbations Based on Meaningful Segmentation |
| title_full | XAI for Point Cloud Data Using Perturbations Based on Meaningful Segmentation |
| title_fullStr | XAI for Point Cloud Data Using Perturbations Based on Meaningful Segmentation |
| title_full_unstemmed | XAI for Point Cloud Data Using Perturbations Based on Meaningful Segmentation |
| title_short | XAI for Point Cloud Data Using Perturbations Based on Meaningful Segmentation |
| title_sort | xai for point cloud data using perturbations based on meaningful segmentation |
| topic | Artificial intelligence explainable AI point cloud data segmentation |
| url | https://ieeexplore.ieee.org/document/11121187/ |
| work_keys_str_mv | AT rajuningappamulawade xaiforpointclouddatausingperturbationsbasedonmeaningfulsegmentation AT christophgarth xaiforpointclouddatausingperturbationsbasedonmeaningfulsegmentation AT alexanderwiebel xaiforpointclouddatausingperturbationsbasedonmeaningfulsegmentation |