Salvato in:
Dettagli Bibliografici
Autori principali: Tang, XiaoJun, Wang, Jingru, Shangguan, Zeyu, Tang, Darun, Liu, Yuyu
Natura: Preprint
Pubblicazione: 2024
Soggetti:
Accesso online:https://arxiv.org/abs/2410.15569
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866910658027585536
author Tang, XiaoJun
Wang, Jingru
Shangguan, Zeyu
Tang, Darun
Liu, Yuyu
author_facet Tang, XiaoJun
Wang, Jingru
Shangguan, Zeyu
Tang, Darun
Liu, Yuyu
contents The Unified Object Detection (UOD) task aims to achieve object detection of all merged categories through training on multiple datasets, and is of great significance in comprehensive object detection scenarios. In this paper, we conduct a thorough analysis of the cross datasets missing annotations issue, and propose an Online Pseudo-Label Unified Object Detection scheme. Our method uses a periodically updated teacher model to generate pseudo-labels for the unlabelled objects in each sub-dataset. This periodical update strategy could better ensure that the accuracy of the teacher model reaches the local maxima and maximized the quality of pseudo-labels. In addition, we survey the influence of overlapped region proposals on the accuracy of box regression. We propose a category specific box regression and a pseudo-label RPN head to improve the recall rate of the Region Proposal Network (PRN). Our experimental results on common used benchmarks (\eg COCO, Object365 and OpenImages) indicates that our online pseudo-label UOD method achieves higher accuracy than existing SOTA methods.
format Preprint
id arxiv_https___arxiv_org_abs_2410_15569
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Online Pseudo-Label Unified Object Detection for Multiple Datasets Training
Tang, XiaoJun
Wang, Jingru
Shangguan, Zeyu
Tang, Darun
Liu, Yuyu
Computer Vision and Pattern Recognition
The Unified Object Detection (UOD) task aims to achieve object detection of all merged categories through training on multiple datasets, and is of great significance in comprehensive object detection scenarios. In this paper, we conduct a thorough analysis of the cross datasets missing annotations issue, and propose an Online Pseudo-Label Unified Object Detection scheme. Our method uses a periodically updated teacher model to generate pseudo-labels for the unlabelled objects in each sub-dataset. This periodical update strategy could better ensure that the accuracy of the teacher model reaches the local maxima and maximized the quality of pseudo-labels. In addition, we survey the influence of overlapped region proposals on the accuracy of box regression. We propose a category specific box regression and a pseudo-label RPN head to improve the recall rate of the Region Proposal Network (PRN). Our experimental results on common used benchmarks (\eg COCO, Object365 and OpenImages) indicates that our online pseudo-label UOD method achieves higher accuracy than existing SOTA methods.
title Online Pseudo-Label Unified Object Detection for Multiple Datasets Training
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2410.15569