MonoSAOD：面向稀疏标注标签的单目3D目标检测
MonoSAOD: Monocular 3D Object Detection with Sparsely Annotated Label
针对稀疏标注场景，用道路感知的图像块粘贴增强保持3D几何一致性，并用原型相似度加深度不确定性过滤伪标签，可直接迁移到其他3D/2D检测器的半监督训练流程。
原文依据 Road-Aware Patch Augmentation (RAPA), which leverages sparse annotations by augmenting segmented object patches onto road regions
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论单目3D目标检测在密集标注数据集上已取得令人瞩目的性能。然而，由于3D标注成本高昂，当仅有少量目标被标注时，其性能会显著下降。这种稀疏标注设定在现实场景中十分常见，因为标注每一个目标并不现实。为解决这一问题，我们提出了一种面向稀疏标注单目3D目标检测的新框架，包含两个关键模块。首先，我们提出道路感知图像块增强（RAPA），该方法利用稀疏标注，将分割出的目标图像块增强到道路区域上，同时保持3D几何一致性。其次，我们提出基于原型的过滤（PBF），通过原型相似度和深度不确定性对预测结果进行过滤，从而生成高质量伪标签。PBF维护全局2D RoI特征原型，并选择既与已学习原型在特征上保持一致、又具有可靠深度估计的伪标签。我们的训练策略将保持几何一致的增强与原型引导的伪标签相结合，从而在稀疏监督下实现鲁棒检测。大量实验结果验证了所提方法的有效性。源代码将公开。
英文原文摘要 1230 字符
Monocular 3D Object Detection has achieved impressive performance on densely annotated datasets. However, it struggles when only a fraction of objects are labeled due to the high cost of 3D annotation. This sparsely-annotated setting is common in real-world scenarios where annotating every object is impractical.To address this, we propose a novel framework for sparsely-annotated monocular 3D object detection with two key modules.First, we propose Road-Aware Patch Augmentation (RAPA), which leverages sparse annotations by augmenting segmented object patches onto road regions while preserving 3D geometric consistency. Second, we propose Prototype-Based Filtering (PBF), which generates high-quality pseudo-labels by filtering predictions through prototype similarity and depth uncertainty. PBF maintains global 2D RoI feature prototypes and selects pseudo-labels that are both feature-consistent with learned prototypes and have reliable depth estimates.Our training strategy combines geometry-preserving augmentation with prototype-guided pseudo-labeling to achieve robust detection under sparse supervision.Extensive results demonstrate the effectiveness of the proposed method. The source code will be publicly available.