电子学报2025，Vol.53Issue(10)：3659-3670,12.DOI:10.12263/DZXB.20250309
跨域元优化和双通道注意力结合的少样本多源域目标检测
Cross-Domain Meta Optimization and Dual-Channel Attention for Few-Shot Multi-Source Domain Object Detection
摘要
Abstract
This article addresses a novel and challenging problem of knowledge transfer from the source domain and the intermediate domain to a single target domain,where each category in the target domain has few labeled samples.The knowledge transfer process in this situation faces two difficulties:the target data is extremely scarce,resulting in insuffi-cient target domain feature distribution.Existing few-shot learning methods often extract features from each part indiscrimi-nately,resulting in poor performance in few-shot object detection.To solve the above problems,this paper proposes a few-shot multi-source domain object detection method.A new meta optimization mechanism is proposed to align the source do-main and target domain by introducing a mixed domain,alleviating the problem of scarce feature distribution in the target domain.Firstly,image-level mixing is used to generate mixed images,which together with corresponding labels form the first mixed domain.Then,fine-grained features are generated through a dual-channel attention mechanism,and feature level mixing is used to generate feature level mixed features,which together with corresponding labels form the second mixed do-main.Finally,region of interest features are generated through a region recommendation network and a region of interest network,and then ROI(Region Of Interest)level mixed ROI features are generated through feature-level mixing of the re-gion of interest,which together with corresponding labels form the third mixed domain.The three generated mixed domains are used together to calculate the loss function and complete the meta optimization process.A dual channel attention mecha-nism including convolutional layers and feature calibration is proposed to learn more discriminative deep feature representa-tions,where convolutional layers are used to prevent the loss of key spatial information,and feature calibration is used to se-lectively enhance important features and weaken non important features.Firstly,the convolutional layer submodules are used to generate coarse-grained feature representations.Secondly,the feature calibration submodules are used to establish attention weights based on the correlation between features,and these attention weights are integrated with the original fea-tures to selectively enhance important regions while suppressing unimportant regions.A large number of experimental re-sults on the COCO dataset and PASCAL-VOC dataset demonstrate the effectiveness and robustness of the proposed meth-od.It surpasses other methods in the same field in terms of detection performance,while maintaining good generalization performance on different datasets.Furthermore,the model's parameter count has significant advantages compared to other methods in the same field.关键词
少样本多源域目标检测/跨域元优化/双通道注意力Key words
few-shot multi-source domain object detection/cross-domain meta optimization/dual-channel attention分类
信息技术与安全科学引用本文复制引用
朱松豪,王双丞..跨域元优化和双通道注意力结合的少样本多源域目标检测[J].电子学报,2025,53(10):3659-3670,12.基金项目
国家自然科学基金(No.52405065) National Natural Science Foundation of China(No.52405065) （No.52405065）
