Reliability-Adaptive Consistency Regularization for Weakly-Supervised Point Cloud Segmentation
This addresses the problem of reducing annotation costs for 3D point cloud segmentation, but it is incremental as it builds on existing consistency regularization methods.
The paper tackles weakly-supervised point cloud segmentation with limited labels by proposing a reliability-adaptive consistency network that uses both confidence and uncertainty to improve pseudo-label quality, achieving superior performance on S3DIS and ScanNet-v2 benchmarks.
Weakly-supervised point cloud segmentation with extremely limited labels is highly desirable to alleviate the expensive costs of collecting densely annotated 3D points. This paper explores applying the consistency regularization that is commonly used in weakly-supervised learning, for its point cloud counterpart with multiple data-specific augmentations, which has not been well studied. We observe that the straightforward way of applying consistency constraints to weakly-supervised point cloud segmentation has two major limitations: noisy pseudo labels due to the conventional confidence-based selection and insufficient consistency constraints due to discarding unreliable pseudo labels. Therefore, we propose a novel Reliability-Adaptive Consistency Network (RAC-Net) to use both prediction confidence and model uncertainty to measure the reliability of pseudo labels and apply consistency training on all unlabeled points while with different consistency constraints for different points based on the reliability of corresponding pseudo labels. Experimental results on the S3DIS and ScanNet-v2 benchmark datasets show that our model achieves superior performance in weakly-supervised point cloud segmentation. The code will be released publicly at https://github.com/wu-zhonghua/RAC-Net.