Efficient Distillation Using Channel Pruning for Point Cloud-Based 3D Object Detection

doi:10.1109/TITS.2025.3574213

	Efficient Distillation Using Channel Pruning for Point Cloud-Based 3D Object Detection
	Li, Fuyang 1; Min, Chen 2; Wang, Juan 3; Xiao, Liang 1; Zhao, Dawei 1; Nie, Yiming 1; Dai, Bin 1
	2025-06-13
发表期刊	IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS
ISSN	1524-9050
页码	15
摘要	Although point cloud-based 3D object detectors have advanced significantly in recent years, they are frequently hindered by substantial computational overheads. Lightweight model techniques, such as knowledge distillation, have recently been proven effective for 3D object detector compression. However, neural network pruning's complementary role in knowledge distillation is often overlooked. In this paper, we propose an efficient distillation using channel pruning for point cloud-based 3D object detection. Firstly, given the complete teacher model, we introduce random and magnitude channel pruning methods to generate several compact student models and investigate the effects of different combinations on 3D and 2D layers. Secondly, we introduce model compression scores to explore the impact of channel compression ratios and input resolutions, enabling us to select suitable pruned models for distillation from the given set. Furthermore, we employ multi-source knowledge distillation to facilitate more effective spatial and semantic knowledge transfer. To highlight the features of the foreground regions during distillation, we then propose a soft pivotal position selection mask. Extensive evaluations on various datasets using both pillar-and voxel-based 3D detectors validate the efficiency of our method in compressing point cloud-based 3D detectors. Codes are publicly available at https://github.com/lifuyang-1919/Efficient-Distillation.git
关键词	Knowledge distillation 3D object detection point cloud point cloud network pruning network pruning autonomous driving autonomous driving autonomous driving
DOI	10.1109/TITS.2025.3574213
收录类别	SCI
语种	英语
WOS研究方向	Engineering ; Transportation
WOS类目	Engineering, Civil ; Engineering, Electrical & Electronic ; Transportation Science & Technology
WOS记录号	WOS:001508152800001
出版者	IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
引用统计
文献类型	期刊论文
条目标识符	http://119.78.100.204/handle/2XEOYT63/42356
专题	中国科学院计算技术研究所期刊论文_英文
通讯作者	Xiao, Liang
作者单位	1.Chinese Acad Mil Sci, Def Innovat Inst, Beijing 100071, Peoples R China 2.Chinese Acad Sci, Inst Comp Technol, Beijing 100190, Peoples R China 3.Tsinghua Univ, Dept Comp Sci & Technol, Beijing 100084, Peoples R China
推荐引用方式 GB/T 7714	Li, Fuyang,Min, Chen,Wang, Juan,et al. Efficient Distillation Using Channel Pruning for Point Cloud-Based 3D Object Detection[J]. IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS,2025:15.
APA	Li, Fuyang.,Min, Chen.,Wang, Juan.,Xiao, Liang.,Zhao, Dawei.,...&Dai, Bin.(2025).Efficient Distillation Using Channel Pruning for Point Cloud-Based 3D Object Detection.IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS,15.
MLA	Li, Fuyang,et al."Efficient Distillation Using Channel Pruning for Point Cloud-Based 3D Object Detection".IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS (2025):15.