Comments (4)
Good catch. Your understanding is correct. Setting tau as 0 would make DebiasPL the same as FixMatch in our implementation.
I think the difference lies in the learning rate scheduler. As you can see the best accuracy of the experiments you ran is similar (also similar to our reported results). The problem is, these imbalanced algorithms do not use any schedulers (in their paper setup and open-source code), so I set the scheduler as None in ImbAlgorithm Base class at here:
This means DebiasPL with tau=0 would also not use any scheduler.
But if you run FixMatch, it falls into original Algorithm Base class, which will use the cosine scheduler, causing performance drop at later iterations.
from semi-supervised-learning.
Thanks, after checking the training logs, I found the differences.
However, I also checked the paper and open-source code of DebiasPL. It seems DebiasPL uses cosine scheduler as well. Could you kindly give me some sources of why imbalanced algorithms do not use any schedulers?
from semi-supervised-learning.
You can check ABC paper: https://arxiv.org/pdf/2110.10368.pdf.
I believed other papers like DARP and DASO also mentioned no learning rate scheduler in their paper.
from semi-supervised-learning.
thank you so much!
from semi-supervised-learning.
Related Issues (20)
- A Newbie Question: What does classic_cv and usb_cv mean, and what are their difference? HOT 2
- Any plan to add meta pseudo labels? HOT 2
- Question about the acceleration of training HOT 2
- Support torch.compile HOT 2
- Can not reproduce the results of freeMatch HOT 9
- Training problem HOT 4
- Time series analysis HOT 5
- FreeMatch SAF loss is a negative value? HOT 4
- Question about the Augmentation on Two-Moon dataset used in FreeMatch and SoftMatch HOT 3
- Bug when running the instance code HOT 2
- how to use timm.model as net HOT 2
- Customize datasets tutorial cant work HOT 2
- I can't load model correctly HOT 1
- colab code can not run in Custom_Dataset.ipynb” HOT 1
- 为什么我在自己的数据集上面,100-600-1200不同的有标签数量训练之后,在测试集的效果是一样的差。 HOT 2
- SAT.ass HOT 1
- About config, how to decide the hyperparameters? HOT 3
- There seems to be something strange when the data is loading HOT 6
- Issues related to voice datasets HOT 1
- R..net..\..m..;M// HOT 1
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from semi-supervised-learning.