Unsupervised Feedforward Feature (UFF) Learning for Point Cloud Classification and Segmentation

TL;DR

This paper introduces an unsupervised feedforward feature learning scheme for 3D point cloud classification and segmentation, leveraging statistical correlations in a single pass, achieving competitive results without backpropagation.

Contribution

The work presents a novel unsupervised feedforward learning method for point clouds that eliminates the need for backpropagation, using a cascaded encoder-decoder architecture to learn shape and point features.

Findings

UFF outperforms existing unsupervised methods in shape classification.

UFF is comparable to state-of-the-art DNNs in shape classification.

UFF surpasses semi-supervised methods in part segmentation.

Abstract

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.