Abstract
Detecting small and distant objects remains challenging for object detectors due to scale variation, low resolution, and background clutter. Safety-critical applications require reliable detection of these objects for safe planning. Depth information can improve detection, but existing approaches require complex, model-specific architectural modifications. We provide a theoretical analysis followed by an empirical investigation of the depth-detection relationship. Together, they explain how depth causes systematic performance degradation and why depth-informed supervision mitigates it. We introduce DepthPrior, a framework that uses depth as prior knowledge rather than as a fused feature, providing comparable benefits without modifying detector architectures. DepthPrior consists of Depth-Based Loss Weighting (DLW) and Depth-Based Loss Stratification (DLS) during training, and Depth-Aware Confidence Thresholding (DCT) during inference. The only overhead is the initial cost of depth estimation. Experiments across four benchmarks (KITTI, MS COCO, VisDrone, SUN RGB-D) and two detectors (YOLOv11, EfficientDet) demonstrate the effectiveness of DepthPrior, achieving up to +9% mAP$_S$ and +7% mAR$_S$ for small objects, with inference recovery rates as high as 95:1 (true vs. false detections). DepthPrior offers these benefits without additional sensors, architectural changes, or performance costs. Code is available at this https URL.
Abstract (translated)
检测小而远的物体对于目标检测器来说仍然是一个挑战，原因在于尺度变化、低分辨率和背景杂乱。安全关键应用需要可靠地检测这些对象以进行安全规划。深度信息可以提高检测效果，但现有的方法通常需要复杂的、模型特定的架构修改。我们提供了关于深度与检测关系的理论分析和实证研究。两者共同解释了深度如何导致系统性性能下降以及为什么基于深度的信息监督可以缓解这一问题。 为此，我们提出了DepthPrior框架，它将深度信息作为先验知识使用，而不是将其融合为特征表示，从而在无需修改检测器架构的情况下提供可比的益处。DepthPrior由三个部分组成：训练时的基于深度损失加权（DLW）和基于深度损失分层（DLS），以及推理时的深度感知置信度阈值（DCT）。唯一的额外开销是在初始阶段进行深度估计的成本。 在四个基准数据集（KITTI、MS COCO、VisDrone、SUN RGB-D）上，以及两种检测器模型（YOLOv11和EfficientDet）上的实验展示了DepthPrior的有效性，在小物体的平均精度(mAP$_S$)和平均召回率(mAR$_S$)分别提高了高达9%和7%，并且推理恢复率达到惊人的95:1（真实与假阳性检测的比例）。重要的是，DepthPrior无需额外传感器、架构变化或性能成本即可提供这些益处。 代码可以在提供的URL中获取。
URL
https://arxiv.org/abs/2602.05730
