Self-Supervised Learning for Domain Adaptation on Point-Clouds
Introduction
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.
Instructions
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)
Citation
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}
}
PointSegDA dataset
Shape Reconstruction
Acknowledgement
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]
259 Dec 25, 2022
43 Dec 5, 2022
29 Nov 30, 2022
20 Jun 29, 2022
80 Dec 25, 2022
84 Dec 26, 2022
238 Dec 22, 2022
569 Dec 30, 2022
1 Dec 25, 2021
149 Dec 15, 2022
92 Nov 30, 2022
84 Dec 12, 2022
26 Dec 26, 2022
11 Nov 3, 2022
243 Jan 9, 2023
35 Nov 14, 2022
42 Dec 9, 2022
1.4k Jan 8, 2023
40 Dec 30, 2022