公司标志检测小物体改进方案

C. Eggert, D. Zecha, Stephan Brehm, R. Lienhart
{"title":"公司标志检测小物体改进方案","authors":"C. Eggert, D. Zecha, Stephan Brehm, R. Lienhart","doi":"10.1145/3078971.3078990","DOIUrl":null,"url":null,"abstract":"Many modern approaches for object detection are two-staged pipelines. The first stage identifies regions of interest which are then classified in the second stage. Faster R-CNN is such an approach for object detection which combines both stages into a single pipeline. In this paper we apply Faster R-CNN to the task of company logo detection. Motivated by its weak performance on small object instances, we examine in detail both the proposal and the classification stage with respect to a wide range of object sizes. We investigate the influence of feature map resolution on the performance of those stages. Based on theoretical considerations, we introduce an improved scheme for generating anchor proposals and propose a modification to Faster R-CNN which leverages higher-resolution feature maps for small objects. We evaluate our approach on the FlickrLogos dataset improving the RPN performance from 0.52 to 0.71 (MABO) and the detection performance from 0.52 to $0.67$ (mAP).","PeriodicalId":403556,"journal":{"name":"Proceedings of the 2017 ACM on International Conference on Multimedia Retrieval","volume":"121 2","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2017-04-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"66","resultStr":"{\"title\":\"Improving Small Object Proposals for Company Logo Detection\",\"authors\":\"C. Eggert, D. Zecha, Stephan Brehm, R. Lienhart\",\"doi\":\"10.1145/3078971.3078990\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Many modern approaches for object detection are two-staged pipelines. The first stage identifies regions of interest which are then classified in the second stage. Faster R-CNN is such an approach for object detection which combines both stages into a single pipeline. In this paper we apply Faster R-CNN to the task of company logo detection. Motivated by its weak performance on small object instances, we examine in detail both the proposal and the classification stage with respect to a wide range of object sizes. We investigate the influence of feature map resolution on the performance of those stages. Based on theoretical considerations, we introduce an improved scheme for generating anchor proposals and propose a modification to Faster R-CNN which leverages higher-resolution feature maps for small objects. We evaluate our approach on the FlickrLogos dataset improving the RPN performance from 0.52 to 0.71 (MABO) and the detection performance from 0.52 to $0.67$ (mAP).\",\"PeriodicalId\":403556,\"journal\":{\"name\":\"Proceedings of the 2017 ACM on International Conference on Multimedia Retrieval\",\"volume\":\"121 2\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2017-04-28\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"66\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Proceedings of the 2017 ACM on International Conference on Multimedia Retrieval\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1145/3078971.3078990\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Proceedings of the 2017 ACM on International Conference on Multimedia Retrieval","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1145/3078971.3078990","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 66

摘要

许多现代的目标检测方法都是两阶段的管道。第一阶段确定感兴趣的区域,然后在第二阶段进行分类。更快的R-CNN就是这样一种对象检测方法,它将两个阶段结合到一个单一的管道中。在本文中,我们将Faster R-CNN应用于公司标志检测任务。由于其在小对象实例上的弱性能,我们详细研究了关于大范围对象大小的提议和分类阶段。我们研究了特征映射分辨率对这些阶段性能的影响。基于理论考虑,我们引入了一种生成锚点建议的改进方案,并提出了对Faster R-CNN的修改,该方案利用小对象的更高分辨率特征映射。我们在FlickrLogos数据集上评估了我们的方法,将RPN性能从0.52提高到0.71 (MABO),检测性能从0.52提高到0.67美元(mAP)。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
Improving Small Object Proposals for Company Logo Detection
Many modern approaches for object detection are two-staged pipelines. The first stage identifies regions of interest which are then classified in the second stage. Faster R-CNN is such an approach for object detection which combines both stages into a single pipeline. In this paper we apply Faster R-CNN to the task of company logo detection. Motivated by its weak performance on small object instances, we examine in detail both the proposal and the classification stage with respect to a wide range of object sizes. We investigate the influence of feature map resolution on the performance of those stages. Based on theoretical considerations, we introduce an improved scheme for generating anchor proposals and propose a modification to Faster R-CNN which leverages higher-resolution feature maps for small objects. We evaluate our approach on the FlickrLogos dataset improving the RPN performance from 0.52 to 0.71 (MABO) and the detection performance from 0.52 to $0.67$ (mAP).
求助全文
通过发布文献求助,成功后即可免费获取论文全文。 去求助
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