Are you sure you want to delete this task? Once this task is deleted, it cannot be recovered.
Happiness22 8a43355178 | 1 week ago | |
---|---|---|
DefRec_and_PCM | 3 years ago | |
PointDA | 2 years ago | |
PointSegDA | 3 years ago | |
resources | 3 years ago | |
utils | 1 year ago | |
visualization | 1 year ago | |
.gitignore | 3 years ago | |
Models.py | 1 year ago | |
README.md | 3 years ago | |
__init__.py | 3 years ago | |
df_trainer.py | 1 year ago | |
my_trainer.py | 1 year ago | |
requirements.txt | 1 year ago | |
setup.py | 3 years ago | |
trainer.py | 1 year ago | |
trainer_auto.py | 1 year ago | |
trainer_test.py | 1 week ago |
Self-supervised learning (SSL) allows to learn useful representations from unlabeled data and has been applied effectively for domain adaptation (DA) on images. It is still unknown if and how it can be leveraged for domain adaptation for 3D perception. Here we describe the first study of SSL for DA on point clouds. We introduce a new family of pretext tasks, Deformation Reconstruction, motivated by the deformations encountered in sim-to-real transformations. The key idea is to deform regions of the input shape and use a neural network to reconstruct them. We design three types of shape deformation methods: (1) Volume-based: shape deformation based on proximity in the input space; (2) Feature-based: deforming regions in the shape that are semantically similar; and (3) Sampling-based: shape deformation based on three simple sampling schemes. As a separate contribution, we also develop a new method based on the Mixup training procedure for point-clouds. Evaluations on six domain adaptations across synthetic and real furniture data, demonstrate large improvement over previous work.
Clone repo and install it
git clone https://github.com/IdanAchituve/DefRec_and_PCM.git
cd DefRec_and_PCM
pip install -e .
Download data:
cd ./xxx/data
python download.py
Where xxx is the dataset (either PointDA or PointSegDA)
Please cite this paper if you want to use it in your work,
@inproceedings{achituve2021self,
title={Self-Supervised Learning for Domain Adaptation on Point Clouds},
author={Achituve, Idan and Maron, Haggai and Chechik, Gal},
booktitle={Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision},
pages={123--133},
year={2021}
}
Some of the code in this repoistory was taken (and modified according to needs) from the follwing sources:
[PointNet], [PointNet++], [DGCNN], [PointDAN], [Reconstructing_space], [Mixup]
使用Deformation Reconstruction和Point Cloud Mixup的领域自适应
Python Shell Text
Dear OpenI User
Thank you for your continuous support to the Openl Qizhi Community AI Collaboration Platform. In order to protect your usage rights and ensure network security, we updated the Openl Qizhi Community AI Collaboration Platform Usage Agreement in January 2024. The updated agreement specifies that users are prohibited from using intranet penetration tools. After you click "Agree and continue", you can continue to use our services. Thank you for your cooperation and understanding.
For more agreement content, please refer to the《Openl Qizhi Community AI Collaboration Platform Usage Agreement》