Push-and-Pull: A General Training Framework With Differential Augmentor for Domain Generalized Point Cloud Classification

作者：Jiahao Xu, Xinzhu Ma, Lin Zhang, Bo Zhang, Tao Chen · 发表于：IEEE Transactions on Circuits and Systems for Video Technology · 年份：2024 · DOI：10.1109/tcsvt.2024.3371089 · 被引用次数：8 · 研究领域：3D Shape Modeling and Analysis、3D Surveying and Cultural Heritage、Remote Sensing and LiDAR Applications

As a fundamental task of 3D perception, point cloud recognition has shown significant progress in recent years. However, existing methods still face challenges when dealing with geometry differences, resulting in performance degradation when a distribution gap exists between the training and testing data, also known as domain generalization. In this work, we focus on this problem and propose a general training framework, named Push-and-Pull, aimed at effectively improving the generalization ability of models on unseen target domains. Specifically, our framework first introduces a learnable 3D data augmentor to generate new training point clouds, which helps to reduce the domain bias and enrich the source training set. Also, an adversarial training strategy is proposed topushthe augmented samples away from the original ones in the latent space and meanwhile keep the geometric structure. Second, based on the original and augmented samples, a dual-level consistency regularization strategy on logits and feature spaces is designed topullthe deviated representations back to their original space as close as possible, and promote discriminative and domain-agnostic representations. These two steps are iteratively optimized to enhance the overall performance. Extensive experiments on the PointDA-10 and Sim2Real benchmarks consistently demonstrate the effectiveness of our proposed framework.