当前位置:网站首页>Icml2022 | interventional contrastive learning based on meta semantic regularization
Icml2022 | interventional contrastive learning based on meta semantic regularization
2022-07-01 21:51:00 【Zhiyuan community】
Thesis link :https://arxiv.org/abs/2206.14702
Based on comparative learning (CL) The self supervised learning model of learning visual representations in pairs . Although the current popular CL The model has made great progress , But in this article , We found a phenomenon that has been neglected : When using full image training CL Model time , The performance tested in the full image is better than that tested in the foreground area ; When using foreground area training CL Model time , The performance tested in the complete image is worse than that tested in the foreground area . This observation shows that , The background in the image may interfere with the semantic information of model learning , Its influence has not been completely eliminated . To solve this problem , We build a structural causal model (SCM), Modeling the background as a confounding agent . We propose a regularization method based on backdoor adjustment , That is, interventional contrastive learning based on meta semantic regularization (ICLMSR), Conduct causal intervention on the proposed supply chain management .ICL-MSR Can be integrated into any existing CL In the method , To reduce the background interference of representation learning . It is proved theoretically ICL-MSR It has a smaller error bound . Empirically , Our experiments on several benchmark datasets show that ,ICL-MSR Can improve the most advanced CL Method performance .
边栏推荐
猜你喜欢
薛定谔的日语学习小程序源码
One of the basic learning of function
K-means based user portrait clustering model
【Opencv450】HOG+SVM 与Hog+cascade进行行人检测
2022年高处安装、维护、拆除考题模拟考试平台操作
杰理之、产线装配环节【篇】
PWN攻防世界cgpwn2
List announced | outstanding intellectual property service team in China in 2021
以飞地园区为样本,看雨花与韶山如何奏响长株潭一体化发展高歌
JS how to get a list of elements in a collection object
随机推荐
leetcode刷题:二叉树03(二叉树的后序遍历)
[NOIP2013]积木大赛 [NOIP2018]道路铺设 贪心/差分
Case of camera opening by tour
选择在同花顺上炒股开户可以吗?安全吗?
打出三位数的所有水仙花数「建议收藏」
基于K-means的用户画像聚类模型
编程英语生词笔记本
浏览器tab页之间的通信
收到一封CTO来信,邀约面试机器学习工程师
如果浏览器被意外关闭,react怎么缓存用户填写的表单?
运放-滞回(迟滞)比较器全流程实战计算
tensorflow 张量做卷积,输入量与卷积核维度的理解
开环和闭环是什么意思?
使用闭包实现点击按钮切换 toggle
一次调试去了解redis集群的slot机制
One of the basic learning of function
MySQL数据库驱动(JDBC Driver)jar包下载
《QTreeView+QAbstractItemModel自定义模型》:系列教程之三[通俗易懂]
Manually implement function isinstanceof (child, parent)
游览器打开摄像头案例