光学精密工程2025，Vol.33Issue(18)：2929-2943,15.DOI:10.37188/OPE.20253318.2929
知识嵌入引导的双分支融合增强开放词汇目标检测
Knowledge integration guided dual-branch fusion enhanced open-vocabulary object detection
摘要
Abstract
To address the issues of weak understanding of new class concepts,label confusion,and insuffi-cient detection performance of new classes in open-set scenarios,a Knowledge Integration-guided Dual-branch Fusion Open-Vocabulary Object Detection(KI-DBFOVD)method was proposed in this paper.Firstly,a Knowledge Integration(KI)module was designed,where pseudo-labels generated by a Vision-Language Model were embedded into the detector to learn about new class concepts.Subsequently,a La-bel Match(LM)module was introduced to refine the label matching process through multi-level threshold adjustment and independent matching between base and new classes,thereby alleviating the label confu-sion between base and new classes during detection.Finally,a novel Dual-branch Fusion module(DBF)was constructed by fusing the traditional visual branch and the vision-language branch via geometric averag-ing.This fusion maintained the detection accuracy of base classes and more effectively detected and local-ized new class objects,then enhanced the overall detection performance of the KI-DBFOVD method.Ex-perimental results demonstrate that this method achieves a detection accuracy of 38.6%for new classes on the COCO dataset and 25.4%on the more challenging LVIS dataset,which contains a larger number of categories.These results outperform several mainstream methods and indicate that this approach is more suitable for different open-set scenarios..关键词
开放词汇目标检测/知识嵌入/标签匹配/双分支融合Key words
open-vocabulary object detection/knowledge integration/label match/dual-branch fusion分类
计算机与自动化引用本文复制引用
金友,邓箴,刘立波..知识嵌入引导的双分支融合增强开放词汇目标检测[J].光学精密工程,2025,33(18):2929-2943,15.基金项目
宁夏自然科学基金(No.2024AAC02010) （No.2024AAC02010）
国家自然科学基金(No.62262053) （No.62262053）
宁夏科技创新领军人才项目(No.2022GKLRLX03) （No.2022GKLRLX03）
2024年宁夏回族自治区重点研发计划(引才专项)项目(No.2024BEH04026) （引才专项）
