Weakly Supervised 3D Segmentation via Receptive-Driven Pseudo Label Consistency and Structural Consistency
DOI:
https://doi.org/10.1609/aaai.v37i1.25205Keywords:
CV: 3D Computer Vision, CV: SegmentationAbstract
As manual point-wise label is time and labor-intensive for fully supervised large-scale point cloud semantic segmentation, weakly supervised method is increasingly active. However, existing methods fail to generate high-quality pseudo labels effectively, leading to unsatisfactory results. In this paper, we propose a weakly supervised point cloud semantic segmentation framework via receptive-driven pseudo label consistency and structural consistency to mine potential knowledge. Specifically, we propose three consistency contrains: pseudo label consistency among different scales, semantic structure consistency between intra-class features and class-level relation structure consistency between pair-wise categories. Three consistency constraints are jointly used to effectively prepares and utilizes pseudo labels simultaneously for stable training. Finally, extensive experimental results on three challenging datasets demonstrate that our method significantly outperforms state-of-the-art weakly supervised methods and even achieves comparable performance to the fully supervised methods.Downloads
Published
2023-06-26
How to Cite
Lan, Y., Zhang, Y., Qu, Y., Wang, C., Li, C., Cai, J., Xie, Y., & Wu, Z. (2023). Weakly Supervised 3D Segmentation via Receptive-Driven Pseudo Label Consistency and Structural Consistency. Proceedings of the AAAI Conference on Artificial Intelligence, 37(1), 1222-1230. https://doi.org/10.1609/aaai.v37i1.25205
Issue
Section
AAAI Technical Track on Computer Vision I