Power of Cooperative Supervision: Multiple Teachers Framework for Enhanced 3D Semi-Supervised Object Detection
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2024
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866909213967515648 |
|---|---|
| author | Lee, Jin-Hee Lee, Jae-Keun Kim, Je-Seok Kwon, Soon |
| author_facet | Lee, Jin-Hee Lee, Jae-Keun Kim, Je-Seok Kwon, Soon |
| contents | To ensure safe urban driving for autonomous platforms, it is crucial not only to develop high-performance object detection techniques but also to establish a diverse and representative dataset that captures various urban environments and object characteristics. To address these two issues, we have constructed a multi-class 3D LiDAR dataset reflecting diverse urban environments and object characteristics, and developed a robust 3D semi-supervised object detection (SSOD) based on a multiple teachers framework. This SSOD framework categorizes similar classes and assigns specialized teachers to each category. Through collaborative supervision among these category-specialized teachers, the student network becomes increasingly proficient, leading to a highly effective object detector. We propose a simple yet effective augmentation technique, Pie-based Point Compensating Augmentation (PieAug), to enable the teacher network to generate high-quality pseudo-labels. Extensive experiments on the WOD, KITTI, and our datasets validate the effectiveness of our proposed method and the quality of our dataset. Experimental results demonstrate that our approach consistently outperforms existing state-of-the-art 3D semi-supervised object detection methods across all datasets. We plan to release our multi-class LiDAR dataset and the source code available on our Github repository in the near future. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2405_20720 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Power of Cooperative Supervision: Multiple Teachers Framework for Enhanced 3D Semi-Supervised Object Detection Lee, Jin-Hee Lee, Jae-Keun Kim, Je-Seok Kwon, Soon Computer Vision and Pattern Recognition To ensure safe urban driving for autonomous platforms, it is crucial not only to develop high-performance object detection techniques but also to establish a diverse and representative dataset that captures various urban environments and object characteristics. To address these two issues, we have constructed a multi-class 3D LiDAR dataset reflecting diverse urban environments and object characteristics, and developed a robust 3D semi-supervised object detection (SSOD) based on a multiple teachers framework. This SSOD framework categorizes similar classes and assigns specialized teachers to each category. Through collaborative supervision among these category-specialized teachers, the student network becomes increasingly proficient, leading to a highly effective object detector. We propose a simple yet effective augmentation technique, Pie-based Point Compensating Augmentation (PieAug), to enable the teacher network to generate high-quality pseudo-labels. Extensive experiments on the WOD, KITTI, and our datasets validate the effectiveness of our proposed method and the quality of our dataset. Experimental results demonstrate that our approach consistently outperforms existing state-of-the-art 3D semi-supervised object detection methods across all datasets. We plan to release our multi-class LiDAR dataset and the source code available on our Github repository in the near future. |
| title | Power of Cooperative Supervision: Multiple Teachers Framework for Enhanced 3D Semi-Supervised Object Detection |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2405.20720 |