SESS: Self-Ensembling Semi-Supervised 3D Object Detection

CVPR(2020)

引用 117|浏览245
暂无评分
摘要
The performance of existing point cloud-based 3D object detection methods heavily relies on large-scale high-quality 3D annotations. However, such annotations are often tedious and expensive to collect. Semi-supervised learning is a good alternative to mitigate the data annotation issue, but has remained largely unexplored in 3D object detection. Inspired by the recent success of self-ensembling technique in semi-supervised image classification task, we propose SESS, a self-ensembling semi-supervised 3D object detection framework. Specifically, we design a thorough perturbation scheme to enhance generalization of the network on unlabeled and new unseen data. Furthermore, we propose three consistency losses to enforce the consistency between two sets of predicted 3D object proposals, to facilitate the learning of structure and semantic invariances of objects. Extensive experiments conducted on SUN RGB-D and ScanNet datasets demonstrate the effectiveness of SESS in both inductive and transductive semi-supervised 3D object detection. Our SESS achieves competitive performance compared to the state-of-the-art fully-supervised method by using only 50% labeled data. Our code is available at https://github.com/Na-Z/sess.
更多
查看译文
关键词
SESS,self-ensembling semisupervised 3D object detection,semisupervised learning,data annotation,self-ensembling technique,semisupervised image classification,3D object proposals,point cloud-based 3D object detection,large-scale high-quality 3D annotations,SUN RGB-D
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要