PointCaM: Cut-and-Mix for Open-Set Point Cloud Learning
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2022
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866913117447913472 |
|---|---|
| author | Hong, Jie Qiu, Shi Li, Weihao Anwar, Saeed Harandi, Mehrtash Barnes, Nick Petersson, Lars |
| author_facet | Hong, Jie Qiu, Shi Li, Weihao Anwar, Saeed Harandi, Mehrtash Barnes, Nick Petersson, Lars |
| contents | Point cloud learning is receiving increasing attention. However, most existing point cloud models lack the practical ability to deal with the unavoidable presence of unknown objects. This paper primarily discusses point cloud learning in open-set settings, where we train the model without data from unknown classes and identify them during the inference stage. In essence, we propose a novel Point Cut-and-Mix mechanism for solving open-set point cloud learning, comprising an Unknown-Point Simulator and an Unknown-Point Estimator module. Specifically, we use the Unknown-Point Simulator to simulate out-of-distribution data in the training stage by manipulating the geometric context of partially known data. Based on this, the Unknown-Point Estimator module learns to exploit the point cloud's feature context to discriminate between known and unknown data. Unlike existing methods that only consider classifier features, our proposed solution leverages multi-level feature contexts to recognize unknown point cloud objects more effectively. We test the proposed approach on several datasets, including customized S3DIS, ModelNet40, and ScanObjectNN. The improved open-set performances over comparative baselines show the effectiveness of our PointCaM method. Our code is available at https://github.com/JHome1/pointcam. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2212_02011 |
| institution | arXiv |
| publishDate | 2022 |
| record_format | arxiv |
| spellingShingle | PointCaM: Cut-and-Mix for Open-Set Point Cloud Learning Hong, Jie Qiu, Shi Li, Weihao Anwar, Saeed Harandi, Mehrtash Barnes, Nick Petersson, Lars Computer Vision and Pattern Recognition Point cloud learning is receiving increasing attention. However, most existing point cloud models lack the practical ability to deal with the unavoidable presence of unknown objects. This paper primarily discusses point cloud learning in open-set settings, where we train the model without data from unknown classes and identify them during the inference stage. In essence, we propose a novel Point Cut-and-Mix mechanism for solving open-set point cloud learning, comprising an Unknown-Point Simulator and an Unknown-Point Estimator module. Specifically, we use the Unknown-Point Simulator to simulate out-of-distribution data in the training stage by manipulating the geometric context of partially known data. Based on this, the Unknown-Point Estimator module learns to exploit the point cloud's feature context to discriminate between known and unknown data. Unlike existing methods that only consider classifier features, our proposed solution leverages multi-level feature contexts to recognize unknown point cloud objects more effectively. We test the proposed approach on several datasets, including customized S3DIS, ModelNet40, and ScanObjectNN. The improved open-set performances over comparative baselines show the effectiveness of our PointCaM method. Our code is available at https://github.com/JHome1/pointcam. |
| title | PointCaM: Cut-and-Mix for Open-Set Point Cloud Learning |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2212.02011 |