计算机科学
目标检测
水准点(测量)
人工智能
激光雷达
光学(聚焦)
管道(软件)
探测器
对象(语法)
编码(集合论)
变压器
计算机视觉
数据挖掘
模式识别(心理学)
地质学
物理
电压
集合(抽象数据类型)
光学
电信
程序设计语言
地理
遥感
量子力学
大地测量学
作者
Yilun Chen,Zhiding Yu,Yukang Chen,Shiyi Lan,Anima Anandkumar,Jiaya Jia,José Manuel González y Fernández Valles
标识
DOI:10.1109/iccv51070.2023.00771
摘要
False negatives (FN) in 3D object detection, e.g., missing predictions of pedestrians, vehicles, or other obstacles, can lead to potentially dangerous situations in autonomous driving. While being fatal, this issue is understudied in many current 3D detection methods. In this work, we propose Hard Instance Probing (HIP), a general pipeline that identifies FN in a multi-stage manner and guides the models to focus on excavating difficult instances. For 3D object detection, we instantiate this method as FocalFormer3D, a simple yet effective detector that excels at excavating difficult objects and improving prediction recall. FocalFormer3D features a multi-stage query generation to discover hard objects and a box-level transformer decoder to efficiently distinguish objects from massive object candidates. Experimental results on the nuScenes and Waymo datasets validate the superior performance of FocalFormer3D. The advantage leads to strong performance on both detection and tracking, in both LiDAR and multi-modal settings. Notably, FocalFormer3D achieves a 70.5 mAP and 73.9 NDS on nuScenes detection benchmark, while the nuScenes tracking benchmark shows 72.1 AMOTA, both ranking 1st place on the nuScenes LiDAR leaderboard. Our code is available at https://github.com/NVlabs/FocalFormer3D.
科研通智能强力驱动
Strongly Powered by AbleSci AI