通过学习类别原型，用极少标注实现室内外3D目标检测统一突破
Learning Class Prototypes for Unified Sparse Supervised 3D Object Detection
- 用类别原型匹配未标注特征，自动挖掘潜在目标
- 仅需每场景1个标注，室内/室外数据集上性能达全监督90%以上
- 适合标注稀缺场景的3D检测，尤其适用于智能体感知系统
室内外场景感知对具身智能至关重要，但现有稀疏监督3D目标检测方法仅关注室外场景。为此，我们提出一种统一的稀疏监督3D目标检测方法，通过学习类别原型有效利用未标注物体。首先设计基于原型的目标挖掘模块，将未标注目标挖掘转化为类别原型与未标注特征间的匹配问题，利用最优传输匹配结果为高置信度特征分配原型标签，实现未标注物体的挖掘。随后提出多标签协同优化模块，通过伪标签质量控制和原型标签协作，有效恢复漏检目标。实验表明，该方法在室内外数据集上均达到当前最优性能，在每场景仅1个标注的稀疏监督设定下，分别在ScanNet V2、SUN RGB-D和KITTI上达到全监督检测器78%、90%和96%的性能，验证了方法的可扩展性。代码已开源。
原文摘要 · Abstract (English)
Both indoor and outdoor scene perceptions are essential for embodied intelligence. However, current sparse supervised 3D object detection methods focus solely on outdoor scenes without considering indoor settings. To this end, we propose a unified sparse supervised 3D object detection method for both indoor and outdoor scenes through learning class prototypes to effectively utilize unlabeled objects. Specifically, we first propose a prototype-based object mining module that converts the unlabeled object mining into a matching problem between class prototypes and unlabeled features. By using optimal transport matching results, we assign prototype labels to high-confidence features, thereby achieving the mining of unlabeled objects. We then present a multi-label cooperative refinement module to effectively recover missed detections through pseudo label quality control and prototype label cooperation. Experiments show that our method achieves state-of-the-art performance under the one object per scene sparse supervised setting across indoor and outdoor datasets. With only one labeled object per scene, our method achieves about 78%, 90%, and 96% performance compared to the fully supervised detector on ScanNet V2, SUN RGB-D, and KITTI, respectively, highlighting the scalability of our method. Code is available at https://github.com/zyrant/CPDet3D.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。