计算机应用研究2026，Vol.43Issue(5)：1281-1291,11.DOI:10.19734/j.issn.1001-3695.2025.10.0385
目标检测知识蒸馏综述
Survey on knowledge distillation in object detection
摘要
Abstract
High-precision object detection models demand substantial computational resources and contain massive parame-ters,making their deployment on resource-constrained edge devices challenging.Knowledge distillation,as an efficient model compression technique,effectively transfers knowledge from a complex teacher object detector to a lightweight student object detector,maximizing the performance of the deployed detection model.Currently,there is a lack of comprehensive surveys on knowledge distillation for object detection.To bridge this gap,this study began by categorizing mainstream knowledge distil-lation for object detection methods into three major types:logits-based distillation,feature-based distillation,and relation-based distillation.Then it reviewed the research progress in each category,comparing and summarizing their respective advan-tages and disadvantages.Furthermore,it made performance comprehensive comparison and analysis of these three approaches on the MS COCO dataset and three mainstream detector architectures.Finally,this paper outlined future research directions and challenges about knowledge distillation for object detection method.关键词
知识蒸馏/目标检测/logits蒸馏/特征蒸馏/关系蒸馏Key words
knowledge distillation/object detection/logits-based distillation/feature-based distillation/relation-based distillation分类
信息技术与安全科学引用本文复制引用
王天骐,李阳,潘志松..目标检测知识蒸馏综述[J].计算机应用研究,2026,43(5):1281-1291,11.基金项目
国家自然科学基金资助项目(62076251) （62076251）
