PointCaM: Cut-and-Mix for Open-Set Point Cloud Learning
This addresses the problem of handling unknown objects in point cloud data for applications like robotics and autonomous driving, representing an incremental advance in open-set learning methods.
The paper tackles open-set point cloud learning, where models must identify unknown objects not seen during training, by proposing a Point Cut-and-Mix mechanism with Unknown-Point Simulator and Estimator modules to simulate and discriminate unknown data, achieving effectiveness in experiments.
Point cloud learning is receiving increasing attention, however, most existing point cloud models lack the practical ability to deal with the unavoidable presence of unknown objects. This paper mainly discusses point cloud learning under open-set settings, where we train the model without data from unknown classes and identify them in the inference stage. Basically, we propose to solve open-set point cloud learning using a novel Point Cut-and-Mix mechanism consisting of Unknown-Point Simulator and Unknown-Point Estimator modules. Specifically, we use the Unknown-Point Simulator to simulate out-of-distribution data in the training stage by manipulating the geometric context of partial known data. Based on this, the Unknown-Point Estimator module learns to exploit the point cloud's feature context for discriminating the known and unknown data. Extensive experiments show the plausibility of open-set point cloud learning and the effectiveness of our proposed solutions. Our code is available at \url{https://github.com/ShiQiu0419/pointcam}.