当前位置:网站首页>An overview of the latest research progress of "efficient deep segmentation of labels" at Shanghai Jiaotong University, which comprehensively expounds the deep segmentation methods of unsupervised, ro
An overview of the latest research progress of "efficient deep segmentation of labels" at Shanghai Jiaotong University, which comprehensively expounds the deep segmentation methods of unsupervised, ro
2022-07-07 21:18:00 【Zhiyuan community】
Thesis link :https://arxiv.org/pdf/2207.01223.pdf
With the rapid development of deep learning , Segmentation technology, one of the basic tasks of computer vision, has made great progress . However , Current segmentation algorithms mainly rely on the availability of pixel level annotation , This is usually expensive 、 Cumbersome and laborious . To lighten the burden , In the past few years , People pay more and more attention to the establishment of efficient labels 、 Segmentation algorithm based on deep learning . This paper gives a comprehensive overview of efficient label segmentation methods . So , We will start with different types of weak tags ( Including unsupervised 、 Rough supervision 、 Incomplete supervision and Noise Supervision ) Supervision provided , And supplemented by the type of segmentation problem ( Including semantic segmentation 、 Instance segmentation and panoramic segmentation ), A taxonomy has been developed to organize these methods . Next , We summarize the existing efficient label segmentation methods from a unified perspective , An important issue was discussed : How to bridge the gap between weak supervision and intensive prediction —— Most of the current methods are based on heuristic Apriori , Such as cross pixel similarity 、 Cross label constraints 、 Cross view consistency 、 Cross image relationships, etc . Last , We put forward our own views on the future research direction of efficient deep segmentation of tags .
边栏推荐
- Demon daddy B3 read extensively in a small amount, and completed 20000 vocabulary+
- I have to use my ID card to open an account. Is the bank card safe? I don't understand it
- The difference between NPM uninstall and RM direct deletion
- The latest version of codesonar has improved functional security and supports Misra, c++ parsing and visualization
- Referrer和Referrer-Policy简介
- 权限不足
- MySQL约束之默认约束default与零填充约束zerofill
- What stocks can a new account holder buy? Is the stock trading account safe
- Tensorflow2. How to run under x 1 Code of X
- Validutil, "Rethinking the setting of semi supervised learning on graphs"
猜你喜欢
SQL injection error report injection function graphic explanation
Make this crmeb single merchant wechat mall system popular, so easy to use!
AADL inspector fault tree safety analysis module
程序猿赚的那点钱算个P啊!
95年专注安全这一件事 沃尔沃未来聚焦智能驾驶与电气化领域安全
Implement secondary index with Gaussian redis
CodeSonar如何帮助无人机查找软件缺陷?
【C语言】指针进阶---指针你真的学懂了吗?
Mysql子查询关键字的使用方式(exists)
使用枚举实现英文转盲文
随机推荐
[function recursion] do you know all five classic examples of simple recursion?
【C语言】指针进阶---指针你真的学懂了吗?
Implement secondary index with Gaussian redis
Apifox interface integrated management new artifact
Alibaba cloud award winning experience: how to mount NAS file system through ECS
The difference between NPM uninstall and RM direct deletion
使用高斯Redis实现二级索引
Word inversion implements "suggestions collection"
Validutil, "Rethinking the setting of semi supervised learning on graphs"
Codesonar Webinar
Solve the problem of using uni app mediaerror mediaerror errorcode -5
awk处理JSON处理
论文解读(ValidUtil)《Rethinking the Setting of Semi-supervised Learning on Graphs》
Data sorting in string
智能交通焕发勃勃生机,未来会呈现哪些巨变?[通俗易懂]
Guava multithreading, futurecallback thread calls are uneven
阿里云有奖体验:如何通过ECS挂载NAS文件系统
Lex & yacc of Pisa proxy SQL parsing
HDU4876ZCC loves cards(多校题)
Is embedded system really safe? [how does onespin comprehensively solve the IC integrity problem for the development team]