GeoMask3D: Geometrically Informed Mask Selection for Self-Supervised Point Cloud Learning in 3D

We introduce a pioneering approach to self-supervised learning for point clouds, employing a geometrically informed mask selection strategy called GeoMask3D (GM3D) to boost the efficiency of Masked Auto Encoders (MAE). Unlike the conventional method of random masking, our technique utilizes a teache...

Full description

Saved in:
Bibliographic Details
Published in:arXiv.org 2024-05
Main Authors: Bahri, Ali, Yazdanpanah, Moslem, Noori, Mehrdad, Cheraghalikhani, Milad, Vargas Hakim, Gustavo Adolfo, Osowiechi, David, Beizaee, Farzad, Ismail Ben Ayed, Desrosiers, Christian
Format: Article
Language:English
Subjects:
Complexity
Distillation
Machine learning
Self-supervised learning
Three dimensional models
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:We introduce a pioneering approach to self-supervised learning for point clouds, employing a geometrically informed mask selection strategy called GeoMask3D (GM3D) to boost the efficiency of Masked Auto Encoders (MAE). Unlike the conventional method of random masking, our technique utilizes a teacher-student model to focus on intricate areas within the data, guiding the model's focus toward regions with higher geometric complexity. This strategy is grounded in the hypothesis that concentrating on harder patches yields a more robust feature representation, as evidenced by the improved performance on downstream tasks. Our method also presents a complete-to-partial feature-level knowledge distillation technique designed to guide the prediction of geometric complexity utilizing a comprehensive context from feature-level information. Extensive experiments confirm our method's superiority over State-Of-The-Art (SOTA) baselines, demonstrating marked improvements in classification, and few-shot tasks.
ISSN:2331-8422