Back to Search Start Over

Dynamic supervisor for cross-dataset object detection

Authors :
Yaowu Chen
Shengyu Li
Xiang Tian
Ze Chen
Rongxin Jiang
Jianqiang Huang
Zhihang Fu
Xian-Sheng Hua
Mingyuan Tao
Source :
Neurocomputing. 469:310-320
Publication Year :
2022
Publisher :
Elsevier BV, 2022.

Abstract

The application of cross-dataset training in object detection tasks is complicated because the inconsistency in the category range across datasets transforms fully supervised learning into semi-supervised learning. To address this problem, recent studies focus on the generation of high-quality missing annotations. In this study, we first specify that it is not enough to generate high-quality annotations using a single model, which looks only once for annotations. Through detailed experimental analyses, we further conclude that hard-label training is conducive for generating high-recall annotations, whereas soft-label training tends to obtain high-precision annotations. Inspired by the aspects mentioned above, we propose a dynamic supervisor framework that updates the annotations multiple times through multiple-updated submodels trained using hard and soft labels. In the final generated annotations, recall and precision improve significantly through the integration of hard-label training with soft-label training. Extensive experiments conducted on various dataset combination settings support our analyses and demonstrate the superior performance of the proposed dynamic supervisor.

Details

ISSN :
09252312
Volume :
469
Database :
OpenAIRE
Journal :
Neurocomputing
Accession number :
edsair.doi.dedup.....c08c0a61bebcacf12b1a386e2a469014
Full Text :
https://doi.org/10.1016/j.neucom.2021.09.076