Addressing Overfitting on Pointcloud Classification using Atrous XCRF

TL;DR

This paper introduces Atrous XCRF, a novel method that reduces overfitting in pointcloud classification by leveraging similarity penalties from unlabeled data, leading to improved generalization.

Contribution

The paper proposes Atrous XCRF, a new approach that incorporates conditional random field penalties to enhance pointcloud classification accuracy and robustness.

Findings

Achieves 84.97% overall accuracy on ISPRS dataset

Attains 71.05% F1 score, highest among compared methods

Performs on par with the best existing models

Abstract

Advances in techniques for automated classification of pointcloud data introduce great opportunities for many new and existing applications. However, with a limited number of labeled points, automated classification by a machine learning model is prone to overfitting and poor generalization. The present paper addresses this problem by inducing controlled noise (on a trained model) generated by invoking conditional random field similarity penalties using nearby features. The method is called Atrous XCRF and works by forcing a trained model to respect the similarity penalties provided by unlabeled data. In a benchmark study carried out using the ISPRS 3D labeling dataset, our technique achieves 84.97% in term of overall accuracy, and 71.05% in term of F1 score. The result is on par with the current best model for the benchmark dataset and has the highest value in term of F1 score.