OWL: Unsupervised 3D Object Detection by Occupancy Guided Warm-up and Large Model Priors Reasoning
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866918233932562432 |
|---|---|
| author | Guo, Xusheng Zhang, Wanfa Zhao, Shijia Xia, Qiming Xie, Xiaolong Wang, Mingming Wu, Hai Wen, Chenglu |
| author_facet | Guo, Xusheng Zhang, Wanfa Zhao, Shijia Xia, Qiming Xie, Xiaolong Wang, Mingming Wu, Hai Wen, Chenglu |
| contents | Unsupervised 3D object detection leverages heuristic algorithms to discover potential objects, offering a promising route to reduce annotation costs in autonomous driving. Existing approaches mainly generate pseudo labels and refine them through self-training iterations. However, these pseudo-labels are often incorrect at the beginning of training, resulting in misleading the optimization process. Moreover, effectively filtering and refining them remains a critical challenge. In this paper, we propose OWL for unsupervised 3D object detection by occupancy guided warm-up and large-model priors reasoning. OWL first employs an Occupancy Guided Warm-up (OGW) strategy to initialize the backbone weight with spatial perception capabilities, mitigating the interference of incorrect pseudo-labels on network convergence. Furthermore, OWL introduces an Instance-Cued Reasoning (ICR) module that leverages the prior knowledge of large models to assess pseudo-label quality, enabling precise filtering and refinement. Finally, we design a Weight-adapted Self-training (WAS) strategy to dynamically re-weight pseudo-labels, improving the performance through self-training. Extensive experiments on Waymo Open Dataset (WOD) and KITTI demonstrate that OWL outperforms state-of-the-art unsupervised methods by over 15.0% mAP, revealing the effectiveness of our method. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2512_05698 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | OWL: Unsupervised 3D Object Detection by Occupancy Guided Warm-up and Large Model Priors Reasoning Guo, Xusheng Zhang, Wanfa Zhao, Shijia Xia, Qiming Xie, Xiaolong Wang, Mingming Wu, Hai Wen, Chenglu Computer Vision and Pattern Recognition Unsupervised 3D object detection leverages heuristic algorithms to discover potential objects, offering a promising route to reduce annotation costs in autonomous driving. Existing approaches mainly generate pseudo labels and refine them through self-training iterations. However, these pseudo-labels are often incorrect at the beginning of training, resulting in misleading the optimization process. Moreover, effectively filtering and refining them remains a critical challenge. In this paper, we propose OWL for unsupervised 3D object detection by occupancy guided warm-up and large-model priors reasoning. OWL first employs an Occupancy Guided Warm-up (OGW) strategy to initialize the backbone weight with spatial perception capabilities, mitigating the interference of incorrect pseudo-labels on network convergence. Furthermore, OWL introduces an Instance-Cued Reasoning (ICR) module that leverages the prior knowledge of large models to assess pseudo-label quality, enabling precise filtering and refinement. Finally, we design a Weight-adapted Self-training (WAS) strategy to dynamically re-weight pseudo-labels, improving the performance through self-training. Extensive experiments on Waymo Open Dataset (WOD) and KITTI demonstrate that OWL outperforms state-of-the-art unsupervised methods by over 15.0% mAP, revealing the effectiveness of our method. |
| title | OWL: Unsupervised 3D Object Detection by Occupancy Guided Warm-up and Large Model Priors Reasoning |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2512.05698 |