Unsupervised Feedforward Feature (UFF) Learning for Point Cloud Classification and Segmentation
This addresses the problem of reducing reliance on labeled data for point cloud analysis in fields like robotics and autonomous driving, though it is incremental as it builds on existing unsupervised and feedforward approaches.
The paper tackles unsupervised feature learning for 3D point cloud classification and segmentation by proposing a feedforward method that exploits statistical correlations, achieving performance on par with state-of-the-art deep neural networks for classification and slightly worse for segmentation.
In contrast to supervised backpropagation-based feature learning in deep neural networks (DNNs), an unsupervised feedforward feature (UFF) learning scheme for joint classification and segmentation of 3D point clouds is proposed in this work. The UFF method exploits statistical correlations of points in a point cloud set to learn shape and point features in a one-pass feedforward manner through a cascaded encoder-decoder architecture. It learns global shape features through the encoder and local point features through the concatenated encoder-decoder architecture. The extracted features of an input point cloud are fed to classifiers for shape classification and part segmentation. Experiments are conducted to evaluate the performance of the UFF method. For shape classification, the UFF is superior to existing unsupervised methods and on par with state-of-the-art DNNs. For part segmentation, the UFF outperforms semi-supervised methods and performs slightly worse than DNNs.