Adversarial Learning for Effective Detector Training via Synthetic Data

V. Gorbachev, A. Nikitin, I. Basharov
{"title":"Adversarial Learning for Effective Detector Training via Synthetic Data","authors":"V. Gorbachev, A. Nikitin, I. Basharov","doi":"10.51130/graphicon-2020-2-4-16","DOIUrl":null,"url":null,"abstract":"Current neural network-based algorithms for object detection require a huge amount of training data. Creation and annotation of specific datasets for real-life applications require significant human and time resources that are not always available. This issue substantially prevents the successful deployment of AI algorithms in industrial tasks. One possible solutions is a synthesis of train images by rendering 3D models of target objects, which allows effortless automatic annotation. However, direct use of synthetic training datasets does not usually result in an increase of the algorithms’ quality on test data due to differences in data domains. In this paper, we propose the adversarial architecture and training method for a CNN-based detector, which allows the effective use of synthesized images in case of a lack of labeled real-world data. The method was successfully tested on real data and applied for the development of unmanned aerial vehicle (UAV) detection and localization system.","PeriodicalId":344054,"journal":{"name":"Proceedings of the 30th International Conference on Computer Graphics and Machine Vision (GraphiCon 2020). Part 2","volume":"140 1 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2020-12-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"1","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Proceedings of the 30th International Conference on Computer Graphics and Machine Vision (GraphiCon 2020). Part 2","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.51130/graphicon-2020-2-4-16","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 1

Abstract

Current neural network-based algorithms for object detection require a huge amount of training data. Creation and annotation of specific datasets for real-life applications require significant human and time resources that are not always available. This issue substantially prevents the successful deployment of AI algorithms in industrial tasks. One possible solutions is a synthesis of train images by rendering 3D models of target objects, which allows effortless automatic annotation. However, direct use of synthetic training datasets does not usually result in an increase of the algorithms’ quality on test data due to differences in data domains. In this paper, we propose the adversarial architecture and training method for a CNN-based detector, which allows the effective use of synthesized images in case of a lack of labeled real-world data. The method was successfully tested on real data and applied for the development of unmanned aerial vehicle (UAV) detection and localization system.
基于合成数据的有效检测器训练对抗学习
当前基于神经网络的目标检测算法需要大量的训练数据。为实际应用程序创建和注释特定数据集需要大量的人力和时间资源,而这些资源并不总是可用的。这个问题极大地阻碍了人工智能算法在工业任务中的成功部署。一种可能的解决方案是通过渲染目标物体的3D模型来合成火车图像,从而实现轻松的自动注释。然而,由于数据域的差异,直接使用合成训练数据集通常不会导致算法在测试数据上的质量提高。在本文中,我们提出了一种基于cnn的检测器的对抗架构和训练方法,它允许在缺乏标记的真实世界数据的情况下有效地使用合成图像。该方法在实际数据上进行了成功的测试,并应用于无人机检测与定位系统的开发。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
求助全文
约1分钟内获得全文 求助全文
来源期刊
自引率
0.00%
发文量
0
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:604180095
Book学术官方微信