Classification method for imbalanced LiDAR point cloud based on stack autoencoder

Peng, Ren; Xia, Qunli

doi:10.3934/era.2023175

Cited by 2 publications

(1 citation statement)

References 43 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For instance, in a street scene, the majority of points may belong to the road surface, while the number of points belonging to other classes, such as pedestrians or cars, may be much smaller. To address this challenge, various methods have been proposed in the literature, including data augmentation [10,11], class weighting [12,13], and oversampling/undersampling techniques [14,15]. However, it remains an open research problem to find an effective and efficient method that can handle unbalanced classes in the context of point cloud semantic segmentation.…”

Section: Introductionmentioning

confidence: 99%

Knowledge Enhanced Neural Networks for Point Cloud Semantic Segmentation

et al. 2023

View full text Add to dashboard Cite

Deep learning approaches have sparked much interest in the AI community during the last decade, becoming state-of-the-art in domains such as pattern recognition, computer vision, and data analysis. However, these methods are highly demanding in terms of training data, which is often a major issue in the geospatial and remote sensing fields. One possible solution to this problem comes from the Neuro-Symbolic Integration field (NeSy), where multiple methods have been defined to incorporate background knowledge into the neural network’s learning pipeline. One such method is KENN (Knowledge Enhanced Neural Networks), which injects logical knowledge into the neural network’s structure through additional final layers. Empirically, KENN showed comparable or better results than other NeSy frameworks in various tasks while being more scalable. Therefore, we propose the usage of KENN for point cloud semantic segmentation tasks, where it has immense potential to resolve issues with small sample sizes and unbalanced classes. While other works enforce the knowledge constraints in post-processing, to the best of our knowledge, no previous methods have injected inject such knowledge into the learning pipeline through the use of a NeSy framework. The experiment results over different datasets demonstrate that the introduction of knowledge rules enhances the performance of the original network and achieves state-of-the-art levels of accuracy, even with subideal training data.

show abstract