Deep learning-based approaches have shown remarkable performance in the 3D object detection task. However, they suffer from a catastrophic performance drop on the originally trained classes when incrementally learning new classes without revisiting the old data. This "catastrophic forgetting" phenomenon impedes the deployment of 3D object detection approaches in real-world scenarios, where continuous learning systems are needed. In this paper, we study the unexplored yet important class-incremental 3D object detection problem and present the first solution - SDCoT, a novel static-dynamic co-teaching method. Our SDCoT alleviates the catastrophic forgetting of old classes via a static teacher, which provides pseudo annotations for old classes in the new samples and regularizes the current model by extracting previous knowledge with a distillation loss. At the same time, SDCoT consistently learns the underlying knowledge from new data via a dynamic teacher. We conduct extensive experiments on two benchmark datasets and demonstrate the superior performance of our SDCoT over baseline approaches in several incremental learning scenarios.
翻译:深层次的学习方法在 3D 对象探测任务中表现出了显著的绩效。 但是,当在不重复旧数据的情况下逐步学习新课程时,它们在最初培训的班级上遭受灾难性的性能下降。 这种“灾难性的遗忘”现象阻碍了在现实世界情景中部署3D对象探测方法,在现实情景中需要不断学习系统。 在本文中,我们研究了尚未探索但重要的3D级级对象探测问题,并提出了第一个解决方案 — SDCot, 这是一种新颖的静态动力联合教学方法。 我们的SDCot通过静态教师缓解了旧班的灾难性遗忘,这为新样本中的旧班级提供了假的注释,并通过提取以前的知识以蒸馏损失来规范当前模型。 与此同时,SDCot 持续通过动态教师从新数据中学习基本知识。 我们在两个基准数据集上进行了广泛的实验,并展示了我们SDCot在几个递增学习情景中的基线方法上的优异性表现。