Towards Explainable LiDAR Point Cloud Semantic Segmentation via Gradient Based Target Localization
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2024
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866910335963758592 |
|---|---|
| author | Kuriyal, Abhishek Kumar, Vaibhav |
| author_facet | Kuriyal, Abhishek Kumar, Vaibhav |
| contents | Semantic Segmentation (SS) of LiDAR point clouds is essential for many applications, such as urban planning and autonomous driving. While much progress has been made in interpreting SS predictions for images, interpreting point cloud SS predictions remains a challenge. This paper introduces pGS-CAM, a novel gradient-based method for generating saliency maps in neural network activation layers. Inspired by Grad-CAM, which uses gradients to highlight local importance, pGS-CAM is robust and effective on a variety of datasets (SemanticKITTI, Paris-Lille3D, DALES) and 3D deep learning architectures (KPConv, RandLANet). Our experiments show that pGS-CAM effectively accentuates the feature learning in intermediate activations of SS architectures by highlighting the contribution of each point. This allows us to better understand how SS models make their predictions and identify potential areas for improvement. Relevant codes are available at https://github.com/geoai4cities/pGS-CAM. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2402_12098 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Towards Explainable LiDAR Point Cloud Semantic Segmentation via Gradient Based Target Localization Kuriyal, Abhishek Kumar, Vaibhav Computer Vision and Pattern Recognition Artificial Intelligence Semantic Segmentation (SS) of LiDAR point clouds is essential for many applications, such as urban planning and autonomous driving. While much progress has been made in interpreting SS predictions for images, interpreting point cloud SS predictions remains a challenge. This paper introduces pGS-CAM, a novel gradient-based method for generating saliency maps in neural network activation layers. Inspired by Grad-CAM, which uses gradients to highlight local importance, pGS-CAM is robust and effective on a variety of datasets (SemanticKITTI, Paris-Lille3D, DALES) and 3D deep learning architectures (KPConv, RandLANet). Our experiments show that pGS-CAM effectively accentuates the feature learning in intermediate activations of SS architectures by highlighting the contribution of each point. This allows us to better understand how SS models make their predictions and identify potential areas for improvement. Relevant codes are available at https://github.com/geoai4cities/pGS-CAM. |
| title | Towards Explainable LiDAR Point Cloud Semantic Segmentation via Gradient Based Target Localization |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence |
| url | https://arxiv.org/abs/2402.12098 |