电讯技术2026，Vol.66Issue(9)：1436-1443,8.DOI:10.20079/j.issn.1001-893x.250417001
基于特征融合和对齐的领域自适应DINO
Domain Adaptive DINO with Feature Fusion and Alignment
摘要
Abstract
Detection Transformer with improved denoising anchor boxes(DINO)is one of the emerging detectors in recent years and has gained considerable attention for its outstanding detection performance.However,DINO is difficult to learn generic representations from the source domain samples as a supervised model.Its cross-domain generalization capability still faces significant challenges and it may suffer a performance degradation when dealing with data that has domain shift.To improve the generalization ability of the DINO model,a domain adaptive DINO framework based on feature fusion and alignment is proposed.Firstly,it introduces multi-scale feature fusion and global feature alignment strategies in the backbone to boost the model's adaptability to target scenes.Then,a local feature alignment strategy is proposed in the encoder to mitigate the impact of factors like scene layout on the model's cross-domain performance.Finally,hierarchical feature fusion and object-level alignment strategies are introduced in the decoder to improve the model's generalization and discriminative capability.The proposed method improves the mean average precision(mAP)in the target domain by 1.5%to 17.4%across various cross-domain detection tasks.关键词
目标检测/领域自适应/深度学习/DINO检测器Key words
object detection/domain adaptation/deep learning/DINO detector分类
信息技术与安全科学引用本文复制引用
朱思翰..基于特征融合和对齐的领域自适应DINO[J].电讯技术,2026,66(9):1436-1443,8.基金项目
国家自然科学基金青年科学基金(62303433) （62303433）
