Conclusion
To address the UDA problem for point clouds, we propose a novel learnable self-supervised task that helps the adapted neural network extract transferable features. Specifically, we propose a learnable point cloud transformation and use it in a point cloud destruction-reconstruction self-supervised auxiliary task. We train the main task network and the auxiliary task network, which share an encoder, so that the encoder extracts features that are highly transferable to the target domain. We further propose a multi-region transformation strategy to make the network focus on local features, which are more transferable. New state-of-the-art performance is achieved on the point cloud classification and segmentation UDA benchmarks.
This is a preview of subscription content, log in via an institution to check access.
References
Landrieu L, Simonovsky M. Large-scale point cloud semantic segmentation with superpoint graphs. In: Proceedings of 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition. 2018, 4558–4567
Aoki Y, Goforth H, Srivatsan R A, Lucey S. PointNetLK: Robust & efficient point cloud registration using pointNet. In: Proceedings of 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition. 2019, 7156–7165
Alliegro A, Boscaini D, Tommasi T. Joint supervised and self-supervised learning for 3D real world challenges. In: Proceedings of the 25th International Conference on Pattern Recognition. 2021, 6718–6725
Achituve I, Maron H, Chechik G. Self-supervised learning for domain adaptation on point clouds. In: Proceedings of the IEEE Winter Conference on Applications of Computer Vision. 2021, 123–133
Qin C, You H, Wang L, Kuo C C J, Fu Y. PointDAN: a multi-scale 3D domain adaption network for point cloud representation. In: Proceedings of the 33rd International Conference on Neural Information Processing Systems. 2019, 646
Zou L, Tang H, Chen K, Jia K. Geometry-aware self-training for unsupervised domain adaptation on object point clouds. In: Proceedings of 2021 IEEE/CVF International Conference on Computer Vision. 2021, 6383–6392
Sauder J, Sievers B. Self-supervised deep learning on point clouds by reconstructing space. In: Proceedings of the 33rd International Conference on Neural Information Processing Systems. 2019, 1161
Acknowledgements
This work was supported by the National Natural Science Foundation of China (Grant No. 62076070).
Author information
Authors and Affiliations
Corresponding authors
Additional information
Supporting information
The supporting information is available online at journal.hep.com.cn and link.springer.com.
Rights and permissions
About this article
Cite this article
Liu, S., Luo, X., Fu, K. et al. A learnable self-supervised task for unsupervised domain adaptation on point cloud classification and segmentation. Front. Comput. Sci. 17, 176708 (2023). https://doi.org/10.1007/s11704-022-2435-4
Received:
Accepted:
Published:
DOI: https://doi.org/10.1007/s11704-022-2435-4