DDS3D: Dense Pseudo-Labels with Dynamic Threshold for Semi-Supervised 3D Object Detection
This work addresses the problem of reducing annotation costs for 3D object detection in autonomous driving, representing an incremental improvement over existing semi-supervised methods.
The paper tackles semi-supervised 3D object detection by proposing DDS3D, which uses dense pseudo-labels and dynamic thresholds to improve training, achieving state-of-the-art results with mAP gains of 3.1% for pedestrians and 2.1% for cyclists using only 1% labeled data.
In this paper, we present a simple yet effective semi-supervised 3D object detector named DDS3D. Our main contributions have two-fold. On the one hand, different from previous works using Non-Maximal Suppression (NMS) or its variants for obtaining the sparse pseudo labels, we propose a dense pseudo-label generation strategy to get dense pseudo-labels, which can retain more potential supervision information for the student network. On the other hand, instead of traditional fixed thresholds, we propose a dynamic threshold manner to generate pseudo-labels, which can guarantee the quality and quantity of pseudo-labels during the whole training process. Benefiting from these two components, our DDS3D outperforms the state-of-the-art semi-supervised 3d object detection with mAP of 3.1% on the pedestrian and 2.1% on the cyclist under the same configuration of 1% samples. Extensive ablation studies on the KITTI dataset demonstrate the effectiveness of our DDS3D. The code and models will be made publicly available at https://github.com/hust-jy/DDS3D