青岛大学学报（自然科学版）2026，Vol.39Issue(1)：28-34,7.DOI:10.3969/j.issn.1006-1037.2026.01.05
基于知识蒸馏的开放世界场景图生成算法
Open-world Scene Graph Generation Algorithm Based on Knowledge Distillation
摘要
Abstract
Open-world scene graph generation is currently hindered by the intricacy of net-work structures and the excessively large parameter sizes.Consequently,significant com-putational resources are consumed,hindering practical deployment.Therefore,a light-weight open-world scene graph generation(LO-SGG)model was proposed based on a two-stage knowledge distillation framework.Multilevel representations from a teacher model were transferred to a lightweight student model through feature distillation.Thus,the network parameters were reduced,while the deep feature extraction capabilities were pre-served.A multitask collaborative learning paradigm was established.The object detection and relation prediction tasks were jointly optimized.The experimental results demonstrate that LO-SGG maintains open-world generalization capability and achieves a 6%higher re-call than traditional closed-world models.The parameter quantity was reduced to 10%of the complex architectures,with only a 2%decrease in mean precision.The overall per-formance surpasses that of classical benchmark methods by 6%to 19%.关键词
场景图生成/知识蒸馏/轻量化模型/深度学习/开放世界Key words
scene graph generation/knowledge distillation/lightweight model/deep learn-ing/open world分类
信息技术与安全科学引用本文复制引用
顾非凡,宋世淼,葛家尚,杨杰..基于知识蒸馏的开放世界场景图生成算法[J].青岛大学学报（自然科学版）,2026,39(1):28-34,7.基金项目
山东省自然科学基金(批准号:ZR2021MF025)资助. （批准号:ZR2021MF025）
