CA-W3D：利用上下文感知知识进行弱监督单目3D检测
CA-W3D: Leveraging Context-Aware Knowledge for Weakly Supervised Monocular 3D Detection
AI总结：
本文提出CA-W3D，通过两阶段训练（ROCM预训练和D2OD蒸馏）增强弱监督单目3D检测的上下文感知能力，在KITTI基准上全面超越现有方法。
摘要：
弱监督单目3D检测虽然减少了标注需求，但往往难以捕捉可靠3D推理所需的全局上下文。传统的标签高效方法侧重于以对象为中心的特征，忽略了在复杂场景中至关重要的上下文语义关系。在这项工作中，我们提出了一种用于单目3D目标检测的上下文感知弱监督方法，即CA-W3D，以两阶段训练范式解决这一局限性。具体来说，我们首先引入一个预训练阶段，采用区域级对象对比匹配（ROCM），该匹配将对齐来自可训练单目3D编码器和冻结的开词汇2D视觉基础模型导出的区域对象嵌入。这种对齐鼓励单目编码器区分场景特定属性并获取更丰富的上下文知识。在第二阶段，我们结合了带有双到一蒸馏（D2OD）机制的伪标签训练过程，该机制有效地将上下文先验转移到单目编码器中，同时保持空间保真度并在推理期间维持计算效率。在公开的KITTI基准上进行的大量实验证明了我们方法的有效性，在所有指标上超越了最先进的方法，突出了上下文感知知识在弱监督单目3D检测中的重要性。
英文摘要：
Weakly supervised monocular 3D detection, while less annotation-intensive, often struggles to capture the global context required for reliable 3D reasoning. Conventional label-efficient methods focus on object-centric features, neglecting contextual semantic relationships that are critical in complex scenes. In this work, we propose a Context-Aware Weak Supervision for Monocular 3D object detection, namely CA-W3D, to address this limitation in a two-stage training paradigm. Specifically, we first introduce a pre-training stage employing Region-wise Object Contrastive Matching (ROCM), which aligns regional object embeddings derived from a trainable monocular 3D encoder and a frozen open-vocabulary 2D visual grounding model. This alignment encourages the monocular encoder to discriminate scene-specific attributes and acquire richer contextual knowledge. In the second stage, we incorporate a pseudo-label training process with a Dual-to-One Distillation (D2OD) mechanism, which effectively transfers contextual priors into the monocular encoder while preserving spatial fidelity and maintaining computational efficiency during inference. Extensive experiments conducted on the public KITTI benchmark demonstrate the effectiveness of our approach, surpassing the SoTA method over all metrics, highlighting the importance of contextual-aware knowledge in weakly-supervised monocular 3D detection.
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。
