当前位置:网站首页>Zero shot, one shot and few shot
Zero shot, one shot and few shot
2022-07-07 12:00:00 【Smoked Luoting purple Pavilion】
Catalog
One 、Zero-shot learning ( Zero sample learning , abbreviation ZSL)
For the division of these concepts , Mainly from the test volume category , From the perspective of the training set category and the number of samples corresponding to the category .
One 、Zero-shot learning ( Zero sample learning , abbreviation ZSL)
Task definition :
Use training set data to train the model , It enables the model to classify the objects of the test set , But there is no intersection between training set categories and test set categories ; During this period, you need to use the description of the category , To establish the connection between the training set and the test set , Thus making the model effective .
ZSL It is hoped that our model can classify categories it has never seen , Let the machine have reasoning ability , Realize true intelligence . Zero of them (Zero-shot) It refers to the category objects to be classified , Don't study once .
such as : Suppose our model has been able to identify horses , Tigers and pandas , Now we need this model to recognize zebras , Then we need to tell the model , What kind of object is a zebra , But you can't directly let the model see the zebra . So the information that the model needs to know is the horse sample 、 Samples of tigers 、 Samples of pandas and labels of samples , And descriptions of the first three animals and zebras .
Two 、One-shot learning
If the training is concentrated , There is only one sample of different categories , Then become One-shot learning.
One-shot learning Belong to Few-shot learning A special case of .
3、 ... and 、Few-shot learning
If the training is concentrated , There are only a few samples in different categories , Then become Few-shot learning.
It is to give a small number of samples of the category to be predicted by the model , Then let the model predict the category by looking at other samples of the category . such as : Show children a picture of a panda , Then when children go to the zoo and see pictures of pandas , It can be identified as a panda .
Recommended reading small sample learning summary :
边栏推荐
- Talk about SOC startup (x) kernel startup pilot knowledge
- Camera calibration (1): basic principles of monocular camera calibration and Zhang Zhengyou calibration
- Programming examples of stm32f1 and stm32subeide -315m super regenerative wireless remote control module drive
- 大佬们有没有人遇到过 flink oracle cdc,读取一个没有更新操作的表,隔十几秒就重复读取
- Mastering the new functions of swiftui 4 weatherkit and swift charts
- How to connect 5V serial port to 3.3V MCU serial port?
- Common SQL statement collation: MySQL
- Talk about SOC startup (IX) adding a new board to uboot
- Common locking table processing methods in Oracle
- Flet教程之 15 GridView 基础入门(教程含源码)
猜你喜欢
【全栈计划 —— 编程语言之C#】基础入门知识一文懂
【神经网络】卷积神经网络CNN【含Matlab源码 1932期】
The Oracle message permission under the local Navicat connection liunx is insufficient
Rationaldmis2022 array workpiece measurement
Improve application security through nonce field of play integrity API
Automated testing framework
Rationaldmis2022 advanced programming macro program
MySQL安装常见报错处理大全
禁锢自己的因素,原来有这么多
SwiftUI 教程之如何在 2 秒内实现自动滚动功能
随机推荐
Swiftui swift internal skill: five skills of using opaque type in swift
Use references
Talk about SOC startup (VI) uboot startup process II
超标量处理器设计 姚永斌 第8章 指令发射 摘录
【最短路】Acwing1128信使:floyd最短路
Superscalar processor design yaoyongbin Chapter 10 instruction submission excerpt
[shortest circuit] acwing1128 Messenger: Floyd shortest circuit
Ask about the version of flinkcdc2.2.0, which supports concurrency. Does this concurrency mean Multiple Parallelism? Now I find that mysqlcdc is full
Neural approvals to conversational AI (1)
STM32F1与STM32CubeIDE编程实例-315M超再生无线遥控模块驱动
Stm32f1 and stm32subeide programming example -max7219 drives 8-bit 7-segment nixie tube (based on SPI)
Flet教程之 18 Divider 分隔符组件 基础入门(教程含源码)
UP Meta—Web3.0世界创新型元宇宙金融协议
In SQL, I want to set foreign keys. Why is this problem
一起探索云服务之云数据库
Some opinions and code implementation of Siou loss: more powerful learning for bounding box regression zhora gevorgyan
[texture feature extraction] LBP image texture feature extraction based on MATLAB local binary mode [including Matlab source code 1931]
【数据聚类】基于多元宇宙优化DBSCAN实现数据聚类分析附matlab代码
Enclosed please find. Net Maui's latest learning resources
Network protocol concept