xlearning-scu / 2021-cvpr-completer Goto Github PK
View Code? Open in Web Editor NEWPyTorch implementation for COMPLETER: Incomplete Multi-view Clustering via Contrastive Prediction (CVPR 2021)
License: MIT License
PyTorch implementation for COMPLETER: Incomplete Multi-view Clustering via Contrastive Prediction (CVPR 2021)
License: MIT License
I guess it should be decoder_layers
here ?
你好!请问自动编码器层可以单独拿出来训练多视图的重构损失吗?
查看未处理的数据集时第一个view的值全为0,请问是否是正常状态?如果不是正常状态,可否重新上传正常的该数据集?谢谢!
AE2-Nets [1] is used as a baseline in the paper. But it seems that it's not originally designed for the incomplete scenario. Why can it be used as a baseline ? How is it adapted for such scenario ?
在代码运行中,发现Reconstrucion loss,Dual prediction loss与CL loss的大小相差较大(CL loss约为其他两个loss的一千倍),请问这种设计的原因是什么?训练中是怎么解决因这种大小差距导致的优化不平衡的问题的呢?
Dear author, I don't quite understand one point. Is this representation Z discrete or continuous? If Z is discrete, why is the variational distribution Q simulated by Gaussian distribution instead of Bernoulli distribution?
您好,
我尝试用您的模型跑自己的数据集(两个视图),但是出现了对比损失为负数,且聚类指标越来越低的情况。这可能是什么原因呢?
大佬您好,有证明说 对比学习其实也是在做最大化互信息这件事情。但是我把模型的最大化互信息替换成infoNCE后(也就是您们组里面的CC那个实例级损失函数),发现效果没有那么惊艳,请问大佬尝试过相关实验吗?比如我在NoisyMnist数据集上尝试,发现infoNCE+重构的效果并不是很好,大概acc在76左右,而互信息+重构能够到达90+;我能想到的一些方面: 调参、归一化等问题。
Hi,
I wonder, why the missing rate is halved here?
Dear author, it seems that this code can only execute two view data. Do you have a multi view version?
Dear author:
Hello guys, great work! Could you kindly post your supplementary material. I can't find it in Prof Peng Xi's website. I want to see the detail presentation of Eq 6.
With great thanks!
A declarative, efficient, and flexible JavaScript library for building user interfaces.
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
An Open Source Machine Learning Framework for Everyone
The Web framework for perfectionists with deadlines.
A PHP framework for web artisans
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
Some thing interesting about web. New door for the world.
A server is a program made to process requests and deliver data to clients.
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
Some thing interesting about visualization, use data art
Some thing interesting about game, make everyone happy.
We are working to build community through open source technology. NB: members must have two-factor auth.
Open source projects and samples from Microsoft.
Google ❤️ Open Source for everyone.
Alibaba Open Source for everyone
Data-Driven Documents codes.
China tencent open source team.