Salvato in:
| Autori principali: | , , , , |
|---|---|
| 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 |