基于PatchTeacher与PillarMix的半监督3D目标检测
Semi-supervised 3D Object Detection with PatchTeacher and PillarMix
AI总结：
针对半监督3D目标检测中伪标签质量受限的问题，提出聚焦局部场景检测的PatchTeacher及配套优化技术与PillarMix数据增强策略，在Waymo和ONCE数据集上取得大幅领先的SOTA结果。
摘要：
半监督学习旨在利用大量无标注数据提升模型性能。当前半监督3D目标检测方法通常采用教师模型为学生模型生成伪标签，伪标签的质量对最终性能至关重要。本文提出PatchTeacher，聚焦于局部场景3D目标检测，为学生模型提供高质量伪标签。具体而言，我们将完整场景划分为一系列图像块（patch），并将其依次输入PatchTeacher。PatchTeacher利用局部场景检测内存占用低的优势，以高分辨率体素化处理点云，可最大程度降低量化的信息损失，提取更细粒度的特征。然而，在场景片段上训练检测器并非易事。因此，我们引入三项关键技术，即Patch Normalizer（图像块归一化器）、Quadrant Align（象限对齐）和Fovea Selection（中央凹选择），以提升PatchTeacher的性能。此外，我们设计了PillarMix，这是一种强数据增强策略，通过混合来自不同激光雷达扫描的截断柱体（pillar）生成多样化的训练样本，从而帮助模型学习更具泛化性的表征。我们在Waymo和ONCE数据集上开展了大量实验，验证了所提方法的有效性与优越性，取得了新的当前最优（SOTA）结果，大幅超越现有方法。代码可在https://github.com/LittlePey/PTPM获取。
英文摘要：
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.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
