Transformer-based methods have demonstrated superior performance for monocular 3D object detection recently, which aims at predicting 3D attributes from a single 2D image. Most existing transformer-based methods leverage both visual and depth representations to explore valuable query points on objects, and the quality of the learned query points has a great impact on detection accuracy. Unfortunately, existing unsupervised attention mechanisms in transformers are prone to generate low-quality query features due to inaccurate receptive fields, especially on hard objects. To tackle this problem, this paper proposes a novel "Supervised Scale-aware Deformable Attention" (SSDA) for monocular 3D object detection. Specifically, SSDA presets several masks with different scales and utilizes depth and visual features to adaptively learn a scale-aware filter for object query augmentation. Imposing the scale awareness, SSDA could well predict the accurate receptive field of an object query to support robust query feature generation. Aside from this, SSDA is assigned with a Weighted Scale Matching (WSM) loss to supervise scale prediction, which presents more confident results as compared to the unsupervised attention mechanisms. Extensive experiments on the KITTI and Waymo Open datasets demonstrate that SSDA significantly improves the detection accuracy, especially on moderate and hard objects, yielding state-of-the-art performance as compared to the existing approaches. Our code will be made publicly available at https://github.com/mikasa3lili/SSD-MonoDETR.

翻译：基于Transformer的方法近年来在单目3D目标检测任务中展现出优越性能，该任务旨在从单张2D图像预测3D属性。现有基于Transformer的方法大多利用视觉特征与深度表征来探索物体上的有效查询点，而学习所得查询点的质量对检测精度影响显著。然而，现有Transformer中的无监督注意力机制会因不准确的感受野（尤其在困难物体上）而产生低质量查询特征。为解决此问题，本文提出一种新颖的"监督尺度感知可变形注意力"（SSDA）方法用于单目3D目标检测。具体而言，SSDA预置多个不同尺度的掩膜，并利用深度特征与视觉特征自适应学习尺度感知滤波器以增强物体查询。通过引入尺度感知能力，SSDA能够准确预测物体查询的有效感受野，从而支持鲁棒的查询特征生成。此外，SSDA采用加权尺度匹配（WSM）损失进行尺度预测监督，相较于无监督注意力机制可得到更可靠的结果。在KITTI与Waymo Open数据集上的大量实验表明，SSDA显著提升了检测精度（尤其在中等难度与困难物体上），相较现有方法达到了最先进性能。相关代码将在https://github.com/mikasa3lili/SSD-MonoDETR公开。