当前位置:网站首页>Unsupervised learning of visual features by contracting cluster assignments
Unsupervised learning of visual features by contracting cluster assignments
2022-07-07 11:17:00 【InfoQ】

- The comparative study of the gods in the twilight age
- “ The arms race ” The comparative study of the period is good .
- Will the whole imagenet Make a dictionary , Extract one from mini batch As a positive sample . And then randomly extract from it 4096 As a negative sample .
- Extract one from the data set mini batch Expand it , Using a twin network , Put the original image into a network , Put the enhanced graph into another network , Both are trained at the same time , Use one for both NCE loss perhaps infoNCE loss. A picture and its enlargement as a positive sample , The rest of the images and their extensions are taken as negative samples .
- Extract one from the data set mini batch Expand it twice , Using a twin network , Put a set of image enhancements into a network , Put another set of image enhancements into another network , Both are trained at the same time , Use one for both NCE loss perhaps infoNCE loss.
- It may repeatedly extract the same data . Although your data set has many pictures , But you may draw the same picture from it . In extreme cases , If you take a group of pictures as a positive sample , Then you take a group of pictures with the same repetition as the negative sample . That will affect the training .
- It may not be representative of the entire data set . For example, there are many kinds of animals in this data , But all you get is dogs , So the data is not representative .
- Of course, the more comprehensive the selection, the better the effect , But if you choose too many negative samples, it will cause a waste of computing resources .

- Let's start with the repeating question : Because you use the cluster center for comparison . Although it is a different cluster center , Then it is certainly impossible for him to repeat .
- Again, there is no representative problem : Clustering is to gather many pictures into different categories . Compare with the center of each category , Is absolutely representative .
- Let's talk about the waste of resources caused by too many negative samples in the past . If you want to make an analogy with many negative samples , You may need thousands of negative samples , And even so, it is only an approximation , And if you just compare with the cluster center , You can use hundreds or at most 3,000 Cluster centers , That's enough to say . Greatly reduce the consumption of computing resources .

边栏推荐
- Mysql的json格式查询
- About the application of writing shell script JSON in JMeter
- V-for img SRC rendering fails
- 数据库同步工具 DBSync 新增对MongoDB、ES的支持
- Transaction rolled back because it has been marked as rollback-only解决
- JS array delete the specified element
- Creative information was surveyed by 2 institutions: greatdb database has been deployed in 9 places
- 如何在博客中添加Aplayer音乐播放器
- 滚动踩坑--UNI_APP(八)
- Static semantic check of clang tidy in cicd
猜你喜欢
Idea shortcut keys
关于SIoU《SIoU Loss: More Powerful Learning for Bounding Box Regression Zhora Gevorgyan 》的一些看法及代码实现
seata 1.3.0 四種模式解决分布式事務(AT、TCC、SAGA、XA)
测试优惠券要怎么写测试用例?
在我有限的软件测试经历里,一段专职的自动化测试经验总结
【C#】WinForm运行缩放(变糊)的解决方法
高考作文,高频提及科技那些事儿……
RationalDMIS2022阵列工件测量
Debezium同步之Debezium架构详解
普通测试年薪15w,测试开发年薪30w+,二者差距在哪?
随机推荐
书签整理-程序员常用网站导航
Antd select selector drop-down box follows the scroll bar to scroll through the solution
科普达人丨一文弄懂什么是云计算?
From pornographic live broadcast to live broadcast E-commerce
MIF file format record
seata 1.3.0 四种模式解决分布式事务(AT、TCC、SAGA、XA)
Vuthink proper installation process
seata 1.3.0 四種模式解决分布式事務(AT、TCC、SAGA、XA)
The fifth training assignment
如何在博客中添加Aplayer音乐播放器
Using ENSP to do MPLS pseudo wire test
Table replication in PostgreSQL
【pyqt】tableWidget里的cellWidget使用信号与槽机制
Multithreaded application (thread pool, singleton mode)
Mpx 插件
Wallhaven wallpaper desktop version
The concept, implementation and analysis of binary search tree (BST)
Network foundation (1)
The use of list and Its Simulation Implementation
How to remove addition and subtraction from inputnumber input box