华南理工大学学报（自然科学版）2025，Vol.53Issue(3)：12-19,8.DOI:10.12141/j.issn.1000-565X.240109
一种可解决标签偏差问题的开放世界目标检测方法
An Open-World Object Detection Method of Capable of Addressing Label Bias Issues
摘要
Abstract
Open World Object Detection(OWOD)extends the problem of object detection to more complex real-world dynamic scenarios,requiring the system to recognize all known and unknown object categories in the image and possess the capability for incremental learning based on newly introduced knowledge.However,current OWOD methods typically mark regions with high object scores as unknown objects and largely rely on supervision of known objects.Although these methods can detect unknown objects that are similar to known ones,they suffer from a significant label bias problem,where regions dissimilar to known objects are often misclassified as part of the background.To address this issue,this study first proposed an unsupervised region proposal generation method based on a large visual model to enhance the model's ability to detect unknown objects.Then,considering that the sensitivity of the Region of Interest(ROI)classification stage to new categories during model training can affect the generalization performance of the Region Proposal Network(RPN)in the proposal generation stage,a decoupled joint training method for RPN region proposal generation and ROI classification was introduced to improve the model's capability to resolve label bias problems.Experimental results show that the method proposed in this study has achieved a significant improvement in detecting unknown objects on the MS-COCO dataset,with the unknown category recall rate exceeding that of the previous SOTA methods by more than twice,reaching 52.1%,while main-taining competitiveness in detecting known object categories.In terms of inference speed,the model,constructed using pure convolutional neural networks rather than dense attention mechanisms,achieves a frame rate 8.18 f/s higher than that of deformable DETR-based methods.关键词
无监督/开放世界/增量学习/目标检测Key words
unsupervision/open world/incrementally learn/object detection分类
信息技术与安全科学引用本文复制引用
黄阳阳,许勇,席星,罗荣华..一种可解决标签偏差问题的开放世界目标检测方法[J].华南理工大学学报（自然科学版）,2025,53(3):12-19,8.基金项目
国家重点研发计划项目(2024YFE0105400) （2024YFE0105400）
广州市产学研协同创新重大专项(201802010073) Supported by the National Key R&D Program of China(2024YFE0105400) （201802010073）
