Adaptive Point Transformer
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2024
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866917575968948224 |
|---|---|
| author | Baiocchi, Alessandro Spinelli, Indro Nicolosi, Alessandro Scardapane, Simone |
| author_facet | Baiocchi, Alessandro Spinelli, Indro Nicolosi, Alessandro Scardapane, Simone |
| contents | The recent surge in 3D data acquisition has spurred the development of geometric deep learning models for point cloud processing, boosted by the remarkable success of transformers in natural language processing. While point cloud transformers (PTs) have achieved impressive results recently, their quadratic scaling with respect to the point cloud size poses a significant scalability challenge for real-world applications. To address this issue, we propose the Adaptive Point Cloud Transformer (AdaPT), a standard PT model augmented by an adaptive token selection mechanism. AdaPT dynamically reduces the number of tokens during inference, enabling efficient processing of large point clouds. Furthermore, we introduce a budget mechanism to flexibly adjust the computational cost of the model at inference time without the need for retraining or fine-tuning separate models. Our extensive experimental evaluation on point cloud classification tasks demonstrates that AdaPT significantly reduces computational complexity while maintaining competitive accuracy compared to standard PTs. The code for AdaPT is made publicly available. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2401_14845 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Adaptive Point Transformer Baiocchi, Alessandro Spinelli, Indro Nicolosi, Alessandro Scardapane, Simone Computer Vision and Pattern Recognition Machine Learning The recent surge in 3D data acquisition has spurred the development of geometric deep learning models for point cloud processing, boosted by the remarkable success of transformers in natural language processing. While point cloud transformers (PTs) have achieved impressive results recently, their quadratic scaling with respect to the point cloud size poses a significant scalability challenge for real-world applications. To address this issue, we propose the Adaptive Point Cloud Transformer (AdaPT), a standard PT model augmented by an adaptive token selection mechanism. AdaPT dynamically reduces the number of tokens during inference, enabling efficient processing of large point clouds. Furthermore, we introduce a budget mechanism to flexibly adjust the computational cost of the model at inference time without the need for retraining or fine-tuning separate models. Our extensive experimental evaluation on point cloud classification tasks demonstrates that AdaPT significantly reduces computational complexity while maintaining competitive accuracy compared to standard PTs. The code for AdaPT is made publicly available. |
| title | Adaptive Point Transformer |
| topic | Computer Vision and Pattern Recognition Machine Learning |
| url | https://arxiv.org/abs/2401.14845 |