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: | Raju Ningappa Mulawade, Christoph Garth, Alexander Wiebel |
|---|---|
| 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!
|
Similar Items
-
LLM in the Loop: A Framework for Contextualizing Counterfactual Segment Perturbations in Point Clouds
by: Veljka Kocic, et al.
Published: (2025-01-01) -
Partial contrastive point cloud self-supervised representation learning
by: Zijun Cheng, et al.
Published: (2025-05-01) -
TFNet: point cloud Semantic Segmentation Network based on Triple feature extraction
by: Yong Li, et al.
Published: (2025-12-01) -
Reconstruction, Segmentation and Phenotypic Feature Extraction of Oilseed Rape Point Cloud Combining 3D Gaussian Splatting and CKG-PointNet++
by: Yourui Huang, et al.
Published: (2025-06-01) -
Deep Point Cloud Facet Segmentation and Applications in Downsampling and Crop Organ Extraction
by: Yixuan Wang, et al.
Published: (2025-08-01)