可学习性驱动的子模优化用于主动路侧3D检测
Learnability-Driven Submodular Optimization for Active Roadside 3D Detection
针对路侧单目3D检测提出可学习性驱动的主动学习框架，通过子模优化选择信息量大且可靠可标注的场景，避免固有歧义样本，为数据标注受限下的3D感知提供可复用策略。
原文依据 we develop an active learning framework for roadside monocular 3D object detection and propose a learnability-driven framework that selects scenes which are both informative and reliably labelable
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论路侧感知数据集通常通过同步的车载与路侧帧对进行协同标注来构建，但由于硬件和隐私限制，实际部署往往仅能获得路侧数据。即使人类专家在没有车载数据的情况下也难以生成准确标注，这一观察揭示了一个根本性的可学习性问题：许多仅路侧场景包含远处、模糊或被遮挡的物体，其3D属性从单一视角看是模糊的，只有通过交叉核对配对的车载-路侧帧才能可靠标注。我们将此类情况称为固有歧义样本。在本工作中，我们开发了一个用于路侧单目3D目标检测的主动学习框架，并提出了一个可学习性驱动的框架，该框架选择既具有信息量又可靠可标注的场景，在确保覆盖的同时抑制固有歧义样本。实验表明，我们的方法显著优于基于不确定性的基线，这表明对于路侧3D感知而言，重要的是可学习性而非不确定性。
英文原文摘要 1104 字符
Roadside perception datasets are typically constructed via cooperative labeling between synchronized vehicle and roadside frame pairs, but real deployment is often limited roadside-only data due to hardware and privacy constraints. The observation that even human experts struggle to produce accurate labels without vehicle-side data reveals a fundamental learnability problem: many roadside-only scenes contain distant, blurred, or occluded objects whose 3D properties are ambiguous from a single view and can only be reliably annotated by cross-checking paired vehicle--roadside frames. We refer to such cases as inherently ambiguous samples. In this work, we develop an active learning framework for roadside monocular 3D object detection and propose a learnability-driven framework that selects scenes which are both informative and reliably labelable, suppressing inherently ambiguous samples while ensuring coverage. Experiments demonstrate that our method significantly outperforms uncertainty-based baselines, which suggests that learnability, not uncertainty, matters for roadside 3D perception.