FI-FPN:用于目标检测的特征集成特征金字塔网络

IF 1.4 4区 计算机科学 Q4 COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE
Qichen Su, Guangjian Zhang, Shuang Wu, Yiming Yin
{"title":"FI-FPN:用于目标检测的特征集成特征金字塔网络","authors":"Qichen Su, Guangjian Zhang, Shuang Wu, Yiming Yin","doi":"10.3233/aic-220183","DOIUrl":null,"url":null,"abstract":"The multi-layer feature pyramid structure, represented by FPN, is widely used in object detection. However, due to the aliasing effect brought by up-sampling, the current feature pyramid structure still has defects, such as loss of high-level feature information and weakening of low-level small object features. In this paper, we propose FI-FPN to solve these problems, which is mainly composed of a multi-receptive field fusion (MRF) module, contextual information filtering (CIF) module, and efficient semantic information fusion (ESF) module. Particularly, MRF stacks dilated convolutional layers and max-pooling layers to obtain receptive fields of different scales, reducing the information loss of high-level features; CIF introduces a channel attention mechanism, and the channel attention weights are reassigned; ESF introduces channel concatenation instead of element-wise operation for bottom-up feature fusion and alleviating aliasing effects, facilitating efficient information flow. Experiments show that under the ResNet50 backbone, our method improves the performance of Faster RCNN and RetinaNet by 3.5 and 4.6 mAP, respectively. Our method has competitive performance compared to other advanced methods.","PeriodicalId":50835,"journal":{"name":"AI Communications","volume":"2004 1","pages":"191-203"},"PeriodicalIF":1.4000,"publicationDate":"2023-06-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"FI-FPN: Feature-integration feature pyramid network for object detection\",\"authors\":\"Qichen Su, Guangjian Zhang, Shuang Wu, Yiming Yin\",\"doi\":\"10.3233/aic-220183\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"The multi-layer feature pyramid structure, represented by FPN, is widely used in object detection. However, due to the aliasing effect brought by up-sampling, the current feature pyramid structure still has defects, such as loss of high-level feature information and weakening of low-level small object features. In this paper, we propose FI-FPN to solve these problems, which is mainly composed of a multi-receptive field fusion (MRF) module, contextual information filtering (CIF) module, and efficient semantic information fusion (ESF) module. Particularly, MRF stacks dilated convolutional layers and max-pooling layers to obtain receptive fields of different scales, reducing the information loss of high-level features; CIF introduces a channel attention mechanism, and the channel attention weights are reassigned; ESF introduces channel concatenation instead of element-wise operation for bottom-up feature fusion and alleviating aliasing effects, facilitating efficient information flow. Experiments show that under the ResNet50 backbone, our method improves the performance of Faster RCNN and RetinaNet by 3.5 and 4.6 mAP, respectively. Our method has competitive performance compared to other advanced methods.\",\"PeriodicalId\":50835,\"journal\":{\"name\":\"AI Communications\",\"volume\":\"2004 1\",\"pages\":\"191-203\"},\"PeriodicalIF\":1.4000,\"publicationDate\":\"2023-06-05\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"AI Communications\",\"FirstCategoryId\":\"94\",\"ListUrlMain\":\"https://doi.org/10.3233/aic-220183\",\"RegionNum\":4,\"RegionCategory\":\"计算机科学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q4\",\"JCRName\":\"COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"AI Communications","FirstCategoryId":"94","ListUrlMain":"https://doi.org/10.3233/aic-220183","RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q4","JCRName":"COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE","Score":null,"Total":0}
引用次数: 0

摘要

以FPN为代表的多层特征金字塔结构在目标检测中得到了广泛应用。然而,由于上采样带来的混叠效应,目前的特征金字塔结构仍然存在缺失高层特征信息和底层小目标特征弱化等缺陷。本文提出的FI-FPN主要由多感受场融合(MRF)模块、上下文信息过滤(CIF)模块和高效语义信息融合(ESF)模块组成。特别是,MRF将扩展卷积层和最大池化层叠加在一起,获得不同尺度的感受场,减少了高级特征的信息损失;CIF引入了信道关注机制,重新分配了信道关注权重;ESF采用通道连接而不是元素操作,用于自底向上的特征融合和减轻混叠效应,促进有效的信息流动。实验表明,在ResNet50骨干网下,我们的方法将Faster RCNN和RetinaNet的性能分别提高了3.5 mAP和4.6 mAP。与其他先进的方法相比,我们的方法具有竞争力。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
FI-FPN: Feature-integration feature pyramid network for object detection
The multi-layer feature pyramid structure, represented by FPN, is widely used in object detection. However, due to the aliasing effect brought by up-sampling, the current feature pyramid structure still has defects, such as loss of high-level feature information and weakening of low-level small object features. In this paper, we propose FI-FPN to solve these problems, which is mainly composed of a multi-receptive field fusion (MRF) module, contextual information filtering (CIF) module, and efficient semantic information fusion (ESF) module. Particularly, MRF stacks dilated convolutional layers and max-pooling layers to obtain receptive fields of different scales, reducing the information loss of high-level features; CIF introduces a channel attention mechanism, and the channel attention weights are reassigned; ESF introduces channel concatenation instead of element-wise operation for bottom-up feature fusion and alleviating aliasing effects, facilitating efficient information flow. Experiments show that under the ResNet50 backbone, our method improves the performance of Faster RCNN and RetinaNet by 3.5 and 4.6 mAP, respectively. Our method has competitive performance compared to other advanced methods.
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
AI Communications
AI Communications 工程技术-计算机:人工智能
CiteScore
2.30
自引率
12.50%
发文量
34
审稿时长
4.5 months
期刊介绍: AI Communications is a journal on artificial intelligence (AI) which has a close relationship to EurAI (European Association for Artificial Intelligence, formerly ECCAI). It covers the whole AI community: Scientific institutions as well as commercial and industrial companies. AI Communications aims to enhance contacts and information exchange between AI researchers and developers, and to provide supranational information to those concerned with AI and advanced information processing. AI Communications publishes refereed articles concerning scientific and technical AI procedures, provided they are of sufficient interest to a large readership of both scientific and practical background. In addition it contains high-level background material, both at the technical level as well as the level of opinions, policies and news.
×
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:481959085
Book学术官方微信