中国科学院自动化研究所机构知识库

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.