Comments (1)
@Hugo-cell111 FYI, larger γ corresponds to larger differences in loss weighting. Since loss weighting is the core of the dynamic loss, hereby the use of the expression "emphasize".
- γ1 is used when models predict the same label, which corresponds to entropy minimization.
- γ2 is used when models predict different labels, which corresponds to mutual learning.
As for the last statement on high-noise and disagreement, it is more empirical. You can understand it as the effects of a overall low learning rate (although not exactly so considering the exponential dynamic weight), the models won't make large steps towards noisy labels or each other.
from dst-cbc.
Related Issues (16)
- [Kept for Feedback] Multi-GPU & New models HOT 21
- Question about label mapping for cityscapes dataset HOT 6
- About using a better model HOT 3
- Sudden drop in accuracy HOT 18
- pretrain model can not be reached HOT 4
- Visualize the final experimental results HOT 16
- 迭代 HOT 9
- 作者您好,这是我使用自己的数据集训练出的结果,为什么迭代过程中的miou没有初始化的miou高? HOT 4
- miou problem in segmentation HOT 26
- When I run the semi supervised section,The program reported an error,could you help HOT 19
- A warning appears during the running of the program, will this affect the accuracy? HOT 2
- How HOT 4
- When I run segmentation code with my own dataset, it occurs the error... HOT 4
- What's the meaning of splits? HOT 3
- Nan values in confusion matrix HOT 10
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 dst-cbc.