Timezone: »

Self-Supervised Pretraining for Large-Scale Point Clouds
Zaiwei Zhang · Min Bai · Li Erran Li

Wed Nov 30 02:00 PM -- 04:00 PM (PST) @ Hall J #901

Pretraining on large unlabeled datasets has been proven to improve the down-stream task performance on many computer vision tasks, such as 2D object detection and video classification. However, for large-scale 3D scenes, such as outdoor LiDAR point clouds, pretraining is not widely used. Due to the special data characteristics of large 3D point clouds, 2D pretraining frameworks tend to not generalize well. In this paper, we propose a new self-supervised pretraining method that targets large-scale 3D scenes. We pretrain commonly used point-based and voxel-based model architectures and show the transfer learning performance on 3D object detection and also semantic segmentation. We demonstrate the effectiveness of our approach on both dense 3D indoor point clouds and also sparse outdoor lidar point clouds.

Author Information

Zaiwei Zhang (Amazon)
Zaiwei Zhang

Zaiwei is a 3D vision researcher, currently working on self-supervised learning in 3D and 3D point clouds auto labeling in AWS AI. He graduated from the University of Texas at Austin in August 2021, and his advisor was Prof.Qixing Huang. Previously, he graduated with a distinguished degree in B.S. of Computer Engineering from Purdue University in May 2015. His research interests lie in the intersection of 3D Vision, Deep Learning and Computer Graphics. He is particularly interested in applying machine learning, especially deep learning, to 3D scene understanding tasks, such as indoor scene generation, scene segmentation, and object detection, and he has publications in top conferences, such as CVPR, ECCV, ICCV and Siggraph.

Min Bai (Amazon)
Li Erran Li (AWS AI, Amazon)

Li Erran Li is the head of machine learning at Scale and an adjunct professor at Columbia University. Previously, he was chief scientist at Pony.ai. Before that, he was with the perception team at Uber ATG and machine learning platform team at Uber where he worked on deep learning for autonomous driving, led the machine learning platform team technically, and drove strategy for company-wide artificial intelligence initiatives. He started his career at Bell Labs. Li’s current research interests are machine learning, computer vision, learning-based robotics, and their application to autonomous driving. He has a PhD from the computer science department at Cornell University. He’s an ACM Fellow and IEEE Fellow.

More from the Same Authors