arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2410.23910cs.CV
收藏

基于证据学习的3D目标检测不确定性估计

Uncertainty Estimation for 3D Object Detection via Evidential Learning

CVLAB, EPFL(计算机视觉实验室,洛桑联邦理工学院);NVIDIA(英伟达公司);University of Ottawa(渥太华大学)

Nikita Durasov, Rafid Mahmood, Jiwoong Choi, Marc T. Law, James Lucas, Pascal Fua, Jose M. Alvarez

AI总结:

针对3D目标检测模型难以量化检测可靠性的问题,提出基于鸟瞰图证据学习的低开销通用不确定性估计框架,可提升异常场景识别等任务性能,还能优化自动标注质量。

摘要:

3D目标检测是自动驾驶车辆与机器人领域计算机视觉应用的核心任务。然而,现有模型通常难以量化检测结果的可靠性,导致在陌生场景下性能不佳。我们提出一种用于3D目标检测不确定性量化的框架,该框架在3D检测器的鸟瞰图(Bird's Eye View)表示上采用证据学习损失函数。这些不确定性估计的计算开销极低,且可跨不同架构通用。我们在分布外场景识别、定位不佳的目标识别以及漏检(假阴性)检测识别三类任务上验证了该不确定性估计的有效性与重要性;我们的框架相比基线方法平均性能提升10-20%。最后,我们将这一系列任务整合到一个系统中:由3D目标检测器对驾驶场景进行自动标注,我们的不确定性估计模块在标注用于训练第二个模型之前验证标注的正确性。在该系统中,我们的不确定性驱动验证机制使mAP提升1%,NDS提升1-2%。

英文摘要:

3D object detection is an essential task for computer vision applications in autonomous vehicles and robotics. However, models often struggle to quantify detection reliability, leading to poor performance on unfamiliar scenes. We introduce a framework for quantifying uncertainty in 3D object detection by leveraging an evidential learning loss on Bird's Eye View representations in the 3D detector. These uncertainty estimates require minimal computational overhead and are generalizable across different architectures. We demonstrate both the efficacy and importance of these uncertainty estimates on identifying out-of-distribution scenes, poorly localized objects, and missing (false negative) detections; our framework consistently improves over baselines by 10-20% on average. Finally, we integrate this suite of tasks into a system where a 3D object detector auto-labels driving scenes and our uncertainty estimates verify label correctness before the labels are used to train a second model. Here, our uncertainty-driven verification results in a 1% improvement in mAP and a 1-2% improvement in NDS.

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。

↑