Semi-supervised 3D Object Detection with PatchTeacher and PillarMix
This work addresses the challenge of leveraging unlabeled data for 3D object detection in autonomous driving, representing an incremental improvement over existing semi-supervised methods.
The paper tackles the problem of generating high-quality pseudo labels for semi-supervised 3D object detection by proposing PatchTeacher, which processes partial scenes with high-resolution voxelization, and PillarMix, a data augmentation strategy. It achieves new state-of-the-art results on Waymo and ONCE datasets, surpassing existing methods by a large margin.
Semi-supervised learning aims to leverage numerous unlabeled data to improve the model performance. Current semi-supervised 3D object detection methods typically use a teacher to generate pseudo labels for a student, and the quality of the pseudo labels is essential for the final performance. In this paper, we propose PatchTeacher, which focuses on partial scene 3D object detection to provide high-quality pseudo labels for the student. Specifically, we divide a complete scene into a series of patches and feed them to our PatchTeacher sequentially. PatchTeacher leverages the low memory consumption advantage of partial scene detection to process point clouds with a high-resolution voxelization, which can minimize the information loss of quantization and extract more fine-grained features. However, it is non-trivial to train a detector on fractions of the scene. Therefore, we introduce three key techniques, i.e., Patch Normalizer, Quadrant Align, and Fovea Selection, to improve the performance of PatchTeacher. Moreover, we devise PillarMix, a strong data augmentation strategy that mixes truncated pillars from different LiDAR scans to generate diverse training samples and thus help the model learn more general representation. Extensive experiments conducted on Waymo and ONCE datasets verify the effectiveness and superiority of our method and we achieve new state-of-the-art results, surpassing existing methods by a large margin. Codes are available at https://github.com/LittlePey/PTPM.