https://pan.baidu.com/s/1O4IPKiObzAx9FtGXBDRkSw?pwd=o37Phttps://pan.baidu.com/s/1O4IPKiObzAx9FtGXBDRkSw?pwd=o37P SeaBird: Segmentation in Bird’s View with Dice Loss Improves Monocular 3D Detection of Large Objects 简介:提出了SeaBird(在鸟视角下的分割)作为向大型物体泛化的第一步。SeaBird通过训练骰子dice损失的分割头有效地将BEV分割应用于前向检测。SeaBird在KITTI-360排行榜上实现了SoTA成绩,并在nuScenes排行榜上提高了现有检测器的性能,特别是对于大型物体