Risk-optimized Outlier Removal for Robust 3D Point Cloud Classification

TL;DR

This paper introduces a risk-based outlier removal method for 3D point cloud classification that improves robustness against noise and malicious attacks by leveraging gradient attribution and tail risk minimization.

Contribution

It presents a novel outlier cleansing approach called PointCVaR, which optimizes point removal using downstream model feedback and tail risk concepts.

Findings

Significantly improves robustness of point cloud classification.

Effectively filters diverse outliers including malicious noise.

Enhances existing robust classification methods.

Abstract

With the growth of 3D sensing technology, deep learning system for 3D point clouds has become increasingly important, especially in applications like autonomous vehicles where safety is a primary concern. However, there are also growing concerns about the reliability of these systems when they encounter noisy point clouds, whether occurring naturally or introduced with malicious intent. This paper highlights the challenges of point cloud classification posed by various forms of noise, from simple background noise to malicious backdoor attacks that can intentionally skew model predictions. While there's an urgent need for optimized point cloud denoising, current point outlier removal approaches, an essential step for denoising, rely heavily on handcrafted strategies and are not adapted for higher-level tasks, such as classification. To address this issue, we introduce an innovative point outlier cleansing method that harnesses the power of downstream classification models. By employing gradient-based attribution analysis, we define a novel concept: point risk. Drawing inspiration from tail risk minimization in finance, we recast the outlier removal process as an optimization problem, named PointCVaR. Extensive experiments show that our proposed technique not only robustly filters diverse point cloud outliers but also consistently and significantly enhances existing robust methods for point cloud classification.