XAI for Point Cloud Data using Perturbations based on Meaningful Segmentation

TL;DR

This paper introduces a segmentation-based XAI method for point cloud classification that uses a novel point-shifting perturbation technique to produce human-interpretable explanations and saliency maps.

Contribution

It presents a new point-shifting mechanism for perturbations and leverages meaningful segmentation to generate more interpretable explanations for 3D object classification.

Findings

The proposed method produces more meaningful and interpretable saliency maps.

It outperforms classical clustering algorithms in generating explanations.

Saliency maps effectively highlight important segments influencing classification.

Abstract

We propose a novel segmentation-based explainable artificial intelligence (XAI) method for neural networks working on point cloud classification. As one building block of this method, we propose a novel point-shifting mechanism to introduce perturbations in point cloud data. Recently, AI has seen an exponential growth. Hence, it is important to understand the decision-making process of AI algorithms when they are applied in critical areas. Our work focuses on explaining AI algorithms that classify point cloud data. An important aspect of the methods used for explaining AI algorithms is their ability to produce explanations that are easy for humans to understand. This allows them to analyze the AI algorithms better and make appropriate decisions based on that analysis. Therefore, in this work, we intend to generate meaningful explanations that can be easily interpreted by humans. The point cloud data we consider represents 3D objects such as cars, guitars, and laptops. We make use of point cloud segmentation models to generate explanations for the working of classification models. The segments are used to introduce perturbations into the input point cloud data and generate saliency maps. The perturbations are introduced using the novel point-shifting mechanism proposed in this work which ensures that the shifted points no longer influence the output of the classification algorithm. In contrast to previous methods, the segments used by our method are meaningful, i.e. humans can easily interpret the meaning of the segments. Thus, the benefit of our method over other methods is its ability to produce more meaningful saliency maps. We compare our method with the use of classical clustering algorithms to generate explanations. We also analyze the saliency maps generated for example inputs using our method to demonstrate the usefulness of the method in generating meaningful explanations.