Comments (4)
Hi @PkuRainBow
- Yes, your understanding is correct. We here use the same number of iterations for all the data splits, this is because we need to iterate through the unlabeled set enough times (if you count the number of epochs based on the unlabeled set, then they are the same).
- Yes, those 92 images are also in the unlabeled set. I follow the common practice in SSL classification here.
BTW, we sample those 92 images so that the number of pixels for each class is roughly balanced. You might not always get a good result if you pick arbitrary 92 images (see Appendix C).
from wss.
@Yuliang-Zou Great thanks for your explanation. We still have a small concern about your experimental settings.
According to your explanation, in fact, your method will train over the 92 images (labeled set) for 20869 epochs, which might cause serious overfitting problems on the supervised loss training part. We also find that the authors of CutMix face the same challenge and we paste the discussion here: Britefury/cutmix-semisup-seg#5 (comment)
So we are really interested in how your experimental setting can address the overfitting problem? Hope for your explanation!
from wss.
I don't have a clear answer yet. But I guess it could be related to the training schedule. In the beginning, the supervised loss dominates the optimization; as we train for more and more iterations, the unsupervised loss starts to take effects and gradually dominates the loss. Just for your reference, FixMatch (semi-supervised classification) has an experiment, training cifar10 on 10 images only, but it works quite well.
from wss.
@Yuliang-Zou Thanks for your reply. The balance between the supervised loss and the unsupervised loss might be a good point to avoid this problem. If my understanding is correct, it is very important to ensure the unsupervised loss to dominate in the late stage. However, there seem no explicit mechanisms to ensure such a scheme, therefore, we guess that an explicit re-weighting scheme might address this problem.
from wss.
Related Issues (14)
- Influence of the color jittering parameters HOT 2
- About the device HOT 3
- About the results showed in talbe 1 HOT 6
- If I want to use your method on custom datasets including image level labels, how can I generate the tfrecord file with image level labels? HOT 1
- Concrete results on COCO HOT 3
- Security Policy violation Binary Artifacts HOT 127
- More data splits information - Cityscape
- More data splits information HOT 3
- Question about Tab.5 which compares different pseudo labeling strategies HOT 6
- tfrecord file? HOT 1
- Segmentation fault HOT 17
- data split name 2_clean not recognized
- class problem of the addational data training 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 wss.