Shi, X., Xu, X., Zhang, W., Zhu, X., Foo, C. S., & Jia, K. (2022). Open-Set Semi-Supervised Learning for 3D Point Cloud Understanding. 2022 26th International Conference on Pattern Recognition (ICPR). https://doi.org/10.1109/icpr56361.2022.9956506
Semantic understanding of 3D point cloud relies on learning models with massively annotated data, which, in many cases, are expensive or difficult to collect. This has led to an emerging research interest in semi-supervised learning (SSL) for 3D point cloud. It is commonly assumed in SSL that the unlabeled data are drawn from the same distribution as that of the labeled ones; This assumption, however, rarely holds
true in realistic environments. Blindly using out-of-distribution (OOD) unlabeled data could harm SSL performance. In this work, we propose to selectively utilize unlabeled data through sample weighting, so that only conducive unlabeled data would be prioritized. To estimate the weights, we adopt a bi-level optimization framework which iteratively optimizes a meta-objective on a held-out validation set and a task-objective on a training set. Faced with the instability of efficient bi-level optimizers, we further propose three regularization techniques to enhance the training stability. Extensive experiments on 3D point cloud classification and segmentation tasks verify the effectiveness of our proposed method. We also demonstrate the feasibility of
a more efficient training strategy.
This research / project is supported by the A*STAR - Career Development Award
Grant Reference no. : C210112059
This work was in part supported by the Guangdong R&D key project of China (No. 2019B010155001), the Program for Guangdong Introducing Innovative and Entrepreneurial Teams (No. 2017ZT07X183), and the National Natural Science Foundation of China (NSFC) under Grant 62106078.