Comments (1)
Ah, I'm sorry. seems I've never explained about the figure in the readme.
However, in the 198th line of main.py, there is a comment about the ground truth loss.
Since we have the actual ground truth labels, we can compute (not predict) the ground truth loss (i.e., cross-entropy-loss) without using the loss prediction module. So I wanted to figure out what happens if I switched the loss prediction module and the cross-entropy-loss in active learning cycles. Therefore I used the cross-entropy-loss to measure the uncertainty of each unlabeled sample and then collect the data points for the next cycle.
Strangely, the result is worse than that of the loss prediction module. An active learning process is improved but not because the loss prediction module predicts loss well but there might be other reasons. (if my experiment is not wrong)
Any other comments or further discussions are welcome.
from learning-loss-for-active-learning.
Related Issues (19)
- question about your Reproduced Results HOT 3
- How do i get reproduced result graph HOT 1
- Which performance is better between confidence only and learning loss HOT 4
- Random sample of unlabled sample HOT 1
- Question about experiment on CIFAR-100 HOT 3
- How to reproduce the results?
- Why is the uncertainty negative ?
- question about un-official Resnet HOT 1
- question about the backbone model HOT 2
- module 'visdom' has no attribute 'Visdom' HOT 1
- The test accuracy is not matched with your image. HOT 10
- About object detection in this article HOT 1
- Why you randomly sample 10000 unlabeled data points first? HOT 2
- why not reinstantiate the network model in Active learning cycles?I am wondering that the way of your writing will make the model aware of the test set in advance? HOT 3
- uncertainty argsort wrong order HOT 2
- About the performance of active learning methods HOT 1
- question about then loss function HOT 3
- Questions about the performance of the figure 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 learning-loss-for-active-learning.