3D object classification has been widely applied in both academic and industrial scenarios. However, most state-of-the-art algorithms rely on a fixed object classification task set, which cannot tackle the scenario when a new 3D object classification task is coming. Meanwhile, the existing lifelong learning models can easily destroy the learned tasks performance, due to the unordered, large-scale, and irregular 3D geometry data. To address these challenges, we propose a L ifelong 3D O bject C lassification ( i.e., L3DOC) model, which can consecutively learn new 3D object classification tasks via imitating “human learning”. More specifically, the core idea of our model is to capture and store the cross-task common knowledge of 3D geometry data in a 3D neural network, named as point-knowledge , through employing layer-wise point-knowledge factorization architecture. Afterwards, a task-relevant knowledge distillation mechanism is employed to connect the current task to previous relevant tasks and effectively prevent catastrophic forgetting . It consists of a point-knowledge distillation module and a transforming-space distillation module, which transfers the accumulated point-knowledge from previous tasks and soft-transfers the compact factorized representations of the transforming-space, respectively. To our best knowledge, the proposed L3DOC algorithm is the first attempt to perform deep learning on 3D object classification tasks in a lifelong learning way. Extensive experiments on several point cloud benchmarks illustrate the superiority of our L3DOC model over the state-of-the-art lifelong learning methods.

中文翻译：

---

L3DOC：终身 3D 对象分类

3D 对象分类已广泛应用于学术和工业场景。然而，大多数最先进的算法都依赖于固定的对象分类任务集，当新的 3D 对象分类任务即将到来时，它无法解决这种情况。同时，由于无序、大规模和不规则的 3D 几何数据，现有的终身学习模型很容易破坏学习任务的性能。为了应对这些挑战，我们提出了一个终身 3D 目的 分类 （ 即，L3DOC）模型，它可以通过模仿“人类学习”来连续学习新的 3D 对象分类任务。更具体地说，我们模型的核心思想是在 3D 神经网络中捕获和存储 3D 几何数据的跨任务常识，命名为点知识，通过采用分层 点知识分解架构。之后，采用与任务相关的知识蒸馏机制，将当前任务与之前的相关任务连接起来，有效防止灾难性的遗忘。它由一个点知识蒸馏模块和转换空间蒸馏模块，将累积的 来自先前任务的点知识和软转移变换空间的紧凑分解表示，分别。据我们所知，所提出的 L3DOC 算法是首次尝试以终身学习的方式对 3D 对象分类任务进行深度学习。对几个点云基准的大量实验表明，我们的 L3DOC 模型优于最先进的终身学习方法。