论文标题
SL3D：自我监督标记的3D识别
SL3D: Self-supervised-Self-labeled 3D Recognition
论文作者
论文摘要
深度学习在许多3D视觉识别任务中取得了巨大的成功，包括形状分类，对象检测和语义分割。但是，其中许多结果依赖于手动收集密集注释的现实世界3D数据，这是非常耗时且昂贵的，从而限制了3D识别任务的可扩展性。因此，我们研究了无监督的3D识别，并提出了一个自我监督标记的3D识别（SL3D）框架。 SL3D同时求解了两个耦合目标，即聚类和学习功能表示形式，以生成伪标记的数据以进行无监督的3D识别。 SL3D是一个通用框架，可以应用于解决不同的3D识别任务，包括分类，对象检测和语义分割。广泛的实验证明了其有效性。代码可在https://github.com/fcendra/sl3d上找到。
Deep learning has attained remarkable success in many 3D visual recognition tasks, including shape classification, object detection, and semantic segmentation. However, many of these results rely on manually collecting densely annotated real-world 3D data, which is highly time-consuming and expensive to obtain, limiting the scalability of 3D recognition tasks. Thus, we study unsupervised 3D recognition and propose a Self-supervised-Self-Labeled 3D Recognition (SL3D) framework. SL3D simultaneously solves two coupled objectives, i.e., clustering and learning feature representation to generate pseudo-labeled data for unsupervised 3D recognition. SL3D is a generic framework and can be applied to solve different 3D recognition tasks, including classification, object detection, and semantic segmentation. Extensive experiments demonstrate its effectiveness. Code is available at https://github.com/fcendra/sl3d.
