XAI for Point Cloud Data using Perturbations based on Meaningful Segmentation

In this work, 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 also propose a novel point-shifting mechanism to introduce perturbations in point cloud data. In the last decade, Artificial intelligence (AI) has seen an exponential growth. However, due to the "black-box" nature of many of these AI algorithms, it is important to understand their decision-making process when it comes to their application in critical areas. Ourwork 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 the users to analyze the performance of 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 considered in this work 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 any previous methods, the segments used by our method are meaningful, i.e. humans can easily interpret the meaning of these 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 some example inputs using our method to demonstrate the usefulness of our proposed method in generating meaningful explanations.