MDNet: A Multi-image Input Real-Time Semantic Segmentation Model with Decoupled Supervision

Yunze Wu
{"title":"MDNet: A Multi-image Input Real-Time Semantic Segmentation Model with Decoupled Supervision","authors":"Yunze Wu","doi":"10.1145/3471287.3471301","DOIUrl":null,"url":null,"abstract":"Current state-of-the-art Real-Time Semantic Segmentation Model is still not fast enough. They spend too much time on processing images in a deep CNN to grab the spatial and context information. Somehow, this information may not be so deterministic. In this work, we come up with a multi-image input real-time semantic segmentation model with decoupled label supervision. It can decrease the computational time and keep a relatively high precision of semantic segmentation meanwhile. The novelty of our model lies is picking up the decoupled label supervision to be our loss function and combining it with a multi-branch image processing framework. The edge detection module can not only improve the recognition of the differences between object body and edge but also guarantee the processing procedure of our network to be faster enough. Apart from this, the multi-branch image processing framework is not a burden of running time. Our network is trained on difficult datasets like CamVid and has favourable quality in real-time testing. The mean class IoU of our network is 66.6. It is the highest one among all of the other comparisons.","PeriodicalId":306474,"journal":{"name":"2021 the 5th International Conference on Information System and Data Mining","volume":"24 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2021-05-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"2021 the 5th International Conference on Information System and Data Mining","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1145/3471287.3471301","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 0

Abstract

Current state-of-the-art Real-Time Semantic Segmentation Model is still not fast enough. They spend too much time on processing images in a deep CNN to grab the spatial and context information. Somehow, this information may not be so deterministic. In this work, we come up with a multi-image input real-time semantic segmentation model with decoupled label supervision. It can decrease the computational time and keep a relatively high precision of semantic segmentation meanwhile. The novelty of our model lies is picking up the decoupled label supervision to be our loss function and combining it with a multi-branch image processing framework. The edge detection module can not only improve the recognition of the differences between object body and edge but also guarantee the processing procedure of our network to be faster enough. Apart from this, the multi-branch image processing framework is not a burden of running time. Our network is trained on difficult datasets like CamVid and has favourable quality in real-time testing. The mean class IoU of our network is 66.6. It is the highest one among all of the other comparisons.
查看原文
分享 分享
微信好友 朋友圈 QQ好友 复制链接
本刊更多论文
一种具有解耦监督的多图像输入实时语义分割模型
目前最先进的实时语义分割模型仍然不够快。他们在深度CNN中花费了太多的时间来处理图像,以获取空间和上下文信息。不知何故,这些信息可能不那么确定。在这项工作中,我们提出了一个具有解耦标签监督的多图像输入实时语义分割模型。它可以减少计算时间,同时保持较高的语义分割精度。该模型的新颖之处在于将解耦的标签监督作为损失函数,并将其与多分支图像处理框架相结合。边缘检测模块不仅可以提高对物体和边缘的识别,而且可以保证网络的处理过程足够快。此外,多分支图像处理框架不会增加运行时间的负担。我们的网络是在CamVid等困难的数据集上训练的,在实时测试中具有良好的质量。我们网络的平均欠条是66.6。这是所有其他比较中最高的一个。
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 去求助
来源期刊
自引率
0.00%
发文量
0
期刊最新文献
Ethnicity Based Consumer Buying Behavior Analysis and Prediction on Online Clothing Platforms in Sri Lanka Email Clustering & Generating Email Templates Based on Their Topics LASTD: A Manually Annotated and Tested Large Arabic Sentiment Tweets Dataset Selection and Verification of Privacy Parameters for Local Differentially Private Data Aggregation MDNet: A Multi-image Input Real-Time Semantic Segmentation Model with Decoupled Supervision
×
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
现在去查看 取消
×
提示
确定
0
微信
客服QQ
Book学术公众号 扫码关注我们
反馈
×
意见反馈
请填写您的意见或建议
请填写您的手机或邮箱
已复制链接
已复制链接
快去分享给好友吧!
我知道了
×
扫码分享
扫码分享
Book学术官方微信
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术
文献互助 智能选刊 最新文献 互助须知 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 Book学术 All rights reserved.
ghs 京公网安备 11010802042870号 京ICP备2023020795号-1