GeoMask3D: Geometrically Informed Mask Selection for Self-Supervised Point Cloud Learning in 3D
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2024
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866912275587137536 |
|---|---|
| author | Bahri, Ali Yazdanpanah, Moslem Noori, Mehrdad Cheraghalikhani, Milad Hakim, Gustavo Adolfo Vargas Osowiechi, David Beizaee, Farzad Ayed, Ismail Ben Desrosiers, Christian |
| author_facet | Bahri, Ali Yazdanpanah, Moslem Noori, Mehrdad Cheraghalikhani, Milad Hakim, Gustavo Adolfo Vargas Osowiechi, David Beizaee, Farzad Ayed, Ismail Ben Desrosiers, Christian |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2405_12419 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | GeoMask3D: Geometrically Informed Mask Selection for Self-Supervised Point Cloud Learning in 3D Bahri, Ali Yazdanpanah, Moslem Noori, Mehrdad Cheraghalikhani, Milad Hakim, Gustavo Adolfo Vargas Osowiechi, David Beizaee, Farzad Ayed, Ismail Ben Desrosiers, Christian Computer Vision and Pattern Recognition Machine Learning 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. |
| title | GeoMask3D: Geometrically Informed Mask Selection for Self-Supervised Point Cloud Learning in 3D |
| topic | Computer Vision and Pattern Recognition Machine Learning |
| url | https://arxiv.org/abs/2405.12419 |