Pseudo Label Refinery for Unsupervised Domain Adaptation on Cross-dataset 3D Object Detection
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_ | 1866916229894111232 |
|---|---|
| author | Zhang, Zhanwei Chen, Minghao Xiao, Shuai Peng, Liang Li, Hengjia Lin, Binbin Li, Ping Wang, Wenxiao Wu, Boxi Cai, Deng |
| author_facet | Zhang, Zhanwei Chen, Minghao Xiao, Shuai Peng, Liang Li, Hengjia Lin, Binbin Li, Ping Wang, Wenxiao Wu, Boxi Cai, Deng |
| contents | Recent self-training techniques have shown notable improvements in unsupervised domain adaptation for 3D object detection (3D UDA). These techniques typically select pseudo labels, i.e., 3D boxes, to supervise models for the target domain. However, this selection process inevitably introduces unreliable 3D boxes, in which 3D points cannot be definitively assigned as foreground or background. Previous techniques mitigate this by reweighting these boxes as pseudo labels, but these boxes can still poison the training process. To resolve this problem, in this paper, we propose a novel pseudo label refinery framework. Specifically, in the selection process, to improve the reliability of pseudo boxes, we propose a complementary augmentation strategy. This strategy involves either removing all points within an unreliable box or replacing it with a high-confidence box. Moreover, the point numbers of instances in high-beam datasets are considerably higher than those in low-beam datasets, also degrading the quality of pseudo labels during the training process. We alleviate this issue by generating additional proposals and aligning RoI features across different domains. Experimental results demonstrate that our method effectively enhances the quality of pseudo labels and consistently surpasses the state-of-the-art methods on six autonomous driving benchmarks. Code will be available at https://github.com/Zhanwei-Z/PERE. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2404_19384 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Pseudo Label Refinery for Unsupervised Domain Adaptation on Cross-dataset 3D Object Detection Zhang, Zhanwei Chen, Minghao Xiao, Shuai Peng, Liang Li, Hengjia Lin, Binbin Li, Ping Wang, Wenxiao Wu, Boxi Cai, Deng Computer Vision and Pattern Recognition Artificial Intelligence Recent self-training techniques have shown notable improvements in unsupervised domain adaptation for 3D object detection (3D UDA). These techniques typically select pseudo labels, i.e., 3D boxes, to supervise models for the target domain. However, this selection process inevitably introduces unreliable 3D boxes, in which 3D points cannot be definitively assigned as foreground or background. Previous techniques mitigate this by reweighting these boxes as pseudo labels, but these boxes can still poison the training process. To resolve this problem, in this paper, we propose a novel pseudo label refinery framework. Specifically, in the selection process, to improve the reliability of pseudo boxes, we propose a complementary augmentation strategy. This strategy involves either removing all points within an unreliable box or replacing it with a high-confidence box. Moreover, the point numbers of instances in high-beam datasets are considerably higher than those in low-beam datasets, also degrading the quality of pseudo labels during the training process. We alleviate this issue by generating additional proposals and aligning RoI features across different domains. Experimental results demonstrate that our method effectively enhances the quality of pseudo labels and consistently surpasses the state-of-the-art methods on six autonomous driving benchmarks. Code will be available at https://github.com/Zhanwei-Z/PERE. |
| title | Pseudo Label Refinery for Unsupervised Domain Adaptation on Cross-dataset 3D Object Detection |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence |
| url | https://arxiv.org/abs/2404.19384 |