论文标题
3D点云中姿势不合时式对象识别的持续学习
Continual Learning for Pose-Agnostic Object Recognition in 3D Point Clouds
论文作者
论文摘要
持续的学习旨在不断学习多个传入的新任务，并将学习任务的绩效保持一致。但是，现有的关于持续学习的研究假设对象的姿势是预先定义和良好的。对于实际应用，这项工作着重于姿势不合时宜的持续学习任务，其中对象的姿势动态和不可预测地变化。从过去的方法中采用的点云增加将随着持续学习过程的任务增加而急剧上升。为了解决这个问题，我们将均值作为额外的先验知识注入网络。我们提出了一个新颖的持续学习模型，该模型有效地提炼了先前任务的几何肩rive缩合信息。该实验表明，我们的方法克服了几个主流点云数据集中姿势无关方案的挑战。我们进一步进行消融研究，以评估方法的每个组成部分的验证。
Continual Learning aims to learn multiple incoming new tasks continually, and to keep the performance of learned tasks at a consistent level. However, existing research on continual learning assumes the pose of the object is pre-defined and well-aligned. For practical application, this work focuses on pose-agnostic continual learning tasks, where the object's pose changes dynamically and unpredictably. The point cloud augmentation adopted from past approaches would sharply rise with the task increment in the continual learning process. To address this problem, we inject the equivariance as the additional prior knowledge into the networks. We proposed a novel continual learning model that effectively distillates previous tasks' geometric equivariance information. The experiments show that our method overcomes the challenge of pose-agnostic scenarios in several mainstream point cloud datasets. We further conduct ablation studies to evaluate the validation of each component of our approach.
