Comments (4)
Negative loss doesn't affect the gradient
from semi-supervised-learning.
thank you for your fast reply!
I am just curious about the intuition behind this loss. By minimizing
from semi-supervised-learning.
thank you for your fast reply! I am just curious about the intuition behind this loss. By minimizing Lf in eq11, aren't you pushing SumNorm (p˜t/h˜t) and SumNorm(p¯/h¯) to be further apart? I thought you want to make them closer?
The loss encourages fairness on average predictions. We expect the average predictions to be close to uniform. Reflected on the entropy loss, it corresponds to maximizing the entropy. We replace the target term with a momentum-smoothed average prediction for stability. That's the intuition behind this loss. I think the paper and relevant works mentioned in the paper discussed this in more detail.
from semi-supervised-learning.
thank you for explaining it!
from semi-supervised-learning.
Related Issues (20)
- How to decide the number of labels in experiments HOT 1
- Questions about batch normalization handling. HOT 1
- Can this run a multilabel problem HOT 1
- Testing models on audio datasets HOT 1
- semilearn get config from file
- Semi-supervised-learning/semilearn/datasets/cv_datasets /cifar.py代码是否有误? HOT 1
- som question about get_cosine_schedule_with_warmup HOT 3
- there‘s a bug in the net resnet50,the self.fc(x) is missing HOT 2
- Add Unimatch ? HOT 2
- There seems to exist a bug when using trainer class
- There is CIFAR-400 in the papaer HOT 2
- Assertion on pseudolabel HOT 2
- Cannot reproduce softmatch result on ag_news dataset HOT 4
- RuntimeError: The size of tensor a (1025) must match the size of tensor b (257) at non-singleton dimension 1 HOT 3
- About Multi-process Distributed Training HOT 1
- Is this a bug of algorithm mean teacher? HOT 1
- About ImageNet127 dataset HOT 1
- Custom Dataset Integration in USB
- Feature request: Meta pseudo labels HOT 1
- configure the iteration count HOT 2
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.