Label-Efficient Point Cloud Semantic Segmentation: An Active Learning Approach
This addresses the time-consuming and expensive annotation problem for researchers and practitioners in 3D computer vision, though it is an incremental improvement on existing active learning methods.
The paper tackles the problem of high annotation costs for semantic point cloud segmentation by proposing an active learning approach that uses super-point based selection with local consistency constraints, achieving more efficient budget usage compared to point-level and instance-level methods on ShapeNet and S3DIS datasets.
Deep learning models are the state-of-the-art methods for semantic point cloud segmentation, the success of which relies on the availability of large-scale annotated datasets. However, it can be extremely time-consuming and prohibitively expensive to compile such datasets. In this work, we propose an active learning approach to maximize model performance given limited annotation budgets. We investigate the appropriate sample granularity for active selection under realistic annotation cost measurement (clicks), and demonstrate that super-point based selection allows for more efficient usage of the limited budget compared to point-level and instance-level selection. We further exploit local consistency constraints to boost the performance of the super-point based approach. We evaluate our methods on two benchmarking datasets (ShapeNet and S3DIS) and the results demonstrate that active learning is an effective strategy to address the high annotation costs in semantic point cloud segmentation.