Weakly supervised object detection based on deep metric learning

Author:

Dong Weiming,Zhang Xiaoming,Zhao Ping

Abstract

Abstract Weakly supervised object detection is a hot issue in the computer vision field, which aims to train a high performance detection model with low cost annotation data. The existing methods of weakly supervised object detection only summarize the object category but don’t consider the similarity between the objects in the optimization process. For solving this problem to improve detection accuracy, this paper proposes a weakly supervised object detection model based on deep metric learning. In the initial training phase, an initial metric has been learned in advance to measure the similarity between these objects; in the correction phase, we propose an adjacent instance mining method based on proxy samples, this approach expands the model’s recognition view, and prevents premature locking the wrong object position. We design a series of experiments on the PASCAL VOC2007 dataset to prove the effectiveness of this method.

Publisher

IOP Publishing

Subject

General Physics and Astronomy

Reference11 articles.

1. MOTS: Multi-object tracking and segmentation;Voigtlaender,2019

2. Sedentary behavior: understanding and influencing adults’ prolonged sitting time;Owen;J. Preventive Medicine.,2012

3. Hybrid task cascade for instance segmentation;Chen,2019

4. Weakly supervised deep detection networks;Bilen,2016

5. Weakly supervised object localization with multi-fold multiple instance learning;Cinbis;J. IEEE Transactions on pattern analysis and machine intelligence.,2016

同舟云学术

1.学者识别学者识别

2.学术分析学术分析

3.人才评估人才评估

"同舟云学术"是以全球学者为主线,采集、加工和组织学术论文而形成的新型学术文献查询和分析系统,可以对全球学者进行文献检索和人才价值评估。用户可以通过关注某些学科领域的顶尖人物而持续追踪该领域的学科进展和研究前沿。经过近期的数据扩容,当前同舟云学术共收录了国内外主流学术期刊6万余种,收集的期刊论文及会议论文总量共计约1.5亿篇,并以每天添加12000余篇中外论文的速度递增。我们也可以为用户提供个性化、定制化的学者数据。欢迎来电咨询!咨询电话:010-8811{复制后删除}0370

www.globalauthorid.com

TOP

Copyright © 2019-2024 北京同舟云网络信息技术有限公司
京公网安备11010802033243号  京ICP备18003416号-3