摘要
伪装目标检测在自然场景分析与安全监控中发挥着重要作用,但伪装目标的复杂性和多样性对检测模型的性能提出了严峻挑战。现有知识蒸馏方法多用于模型压缩,通过对教师网络与学生网络的输出层特征对齐,实现轻量化。然而,现有知识蒸馏方法通常忽略了教师网络中间特征的丰富语义信息。此外,固定学习率策略难以适应教师和学生模型规模差距过大的情况,导致蒸馏过程不稳定。为此,设计了一种基于结构化知识蒸馏的轻量级伪装目标检测模型,利用结构化知识改进传统的软硬标签损失计算,从而显著提升蒸馏效果。同时,将学习率优化问题建模为一个最优化任务,以稳定蒸馏过程中的性能波动。实验结果表明,该方法在COD10K-V3和CAMO伪装目标检测数据集上,S_(m)分别达到82.9%和81.0%,且训练时间减少至6.5 h。
Camouflaged object detection(COD)plays a crucial role in natural scene analysis and security monitoring.However,the complexity and diversity of camouflaged objects pose significant challenges to the performance of detection models.Existing knowledge distillation methods are primarily used for model compression by aligning the output features of teacher and student networks to achieve lightweight models.Nonetheless,these methods often overlook the rich semantic information contained in the intermediate features of teacher networks.Additionally,fixed learning rate strategies struggle to adapt to the significant scale differences between teacher and student models,leading to instability during the distillation process.To address these issues,this paper proposes a lightweight camouflaged object detection model based on structured knowledge distillation.The method leverages structured knowledge to improve the traditional soft and hard label loss calculation,significantly enhancing the distillation performance.Furthermore,the learning rate optimization problem is modeled as an optimization task to stabilize performance fluctuations during the distillation process.Experimental results demonstrate that the proposed method achieves an S_(m)of 82.9%and 81.0%on the COD10K-V3 and CAMO camouflaged object detection datasets,respectively,while reducing training time to 6.5 hours.
作者
宋建华
刘淳
张龑
SONG Jianhua;LIU Chun;ZHANG Yan(School of Cyber Science and Technology,Hubei University,Wuhan 430062,China;School of Computer Science and Information Engineering,Hubei University,Wuhan 430062,China;Key Laboratory of Intelligent Sensing System and Security,Ministry of Education,Wuhan 430062,China;Hubei Engineering Research Center of Cyber Security for Intelligent Connected Vehicles,Wuhan 430062,China)
出处
《计算机科学》
北大核心
2026年第4期299-307,共9页
Computer Science
基金
国家自然科学基金(62377009)
湖北省重大攻关项目(JD)(2023BAA018)
湖北省重点研发计划重点项目(2021BAA184,2021BAA188)
湖北省高等学校人文社会科学重点研究基地绩效评价信息管理研究中心课题(2020JX01)
湖北省科技计划重大科技专项(2024BAA008)。
关键词
知识蒸馏
伪装目标检测
目标检测
结构化知识
学习率
Knowledge distillation
Camouflaged object detection
Object detection
Structured knowledge
Learning rate
