Knowledge Commons of Institute of Automation,CAS
A-Teacher: Asymmetric Network for 3D Semi-Supervised Object Detection | |
Wang, Hanshi1,2; Zhang, Zhipeng3![]() ![]() ![]() | |
2024-06 | |
会议名称 | IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) |
会议日期 | 2024-06-17至2024-06-21 |
会议地点 | Seattle, United States |
摘要 | This work proposes the first online asymmetric semi- supervised framework, namely A-Teacher, for LiDAR-based 3D object detection. Our motivation stems from the obser- vation that 1) existing symmetric teacher-student methods for semi-supervised 3D object detection have characterized simplicity, but impede the distillation performance between teacher and student because of the demand for an identical model structure and input data format. 2) The offline asym- metric methods with a complex teacher model, constructed differently, can generate more precise pseudo labels, but is challenging to jointly optimize the teacher and student model. Consequently, in this paper, we devise a different path from the conventional paradigm, which can harness the capacity of a strong teacher while preserving the advan- tages of jointly updating the whole framework. The essence is the proposed attention-based refinement model that can be seamlessly integrated into a vanilla teacher. The refine- ment model works in the divide-and-conquer manner that respectively handles three challenging scenarios including 1) objects detected in the current timestamp but with sub- optimal box quality, 2) objects are missed in the current timestamp but are detected in supporting frames, 3) objects are neglected in all frames. It is worth noting that even while tackling these complex cases, our model retains the efficiency of the online semi-supervised framework. Exper- imental results on Waymo [38] show that our method out- performs previous state-of-the-art HSSDA [17] for 4.7 on mAP (L1) while consuming fewer training resources. |
收录类别 | EI |
七大方向——子方向分类 | 目标检测、跟踪与识别 |
国重实验室规划方向分类 | 实体人工智能系统感认知 |
是否有论文关联数据集需要存交 | 否 |
文献类型 | 会议论文 |
条目标识符 | http://ir.ia.ac.cn/handle/173211/57511 |
专题 | 多模态人工智能系统全国重点实验室_视频内容安全 |
通讯作者 | Gao, Jin |
作者单位 | 1.State Key Laboratory of Multimodal Artificial Intelligence Systems (MAIS), CASIA 2.School of Artificial Intelligence, University of Chinese Academy of Sciences 3.KargoBot 4.School of Information Science and Technology, ShanghaiTech University |
第一作者单位 | 中国科学院自动化研究所 |
通讯作者单位 | 中国科学院自动化研究所 |
推荐引用方式 GB/T 7714 | Wang, Hanshi,Zhang, Zhipeng,Gao, Jin,et al. A-Teacher: Asymmetric Network for 3D Semi-Supervised Object Detection[C],2024. |
条目包含的文件 | 下载所有文件 | |||||
文件名称/大小 | 文献类型 | 版本类型 | 开放类型 | 使用许可 | ||
Wang_A-Teacher_Asymm(2903KB) | 会议论文 | 开放获取 | CC BY-NC-SA | 浏览 下载 |
除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。
修改评论