Awesome
FINE Samples for Learning with Noisy Labels
This repository is the implementation of "FINE Samples for Learning with Noisy Labels" paper presented in NeurIPS 2021. This repository was used before official release. Future code modifications and official developments will take place in https://github.com/Kthyeon/FINE_official (OFFICIAL RELEASE repo.). Please refer to official release.
Reference Codes
We refer to some official implementation codes
Requirements
- This codebase is written for
python3
(usedpython 3.7.6
while implementing). - To install necessary python packages, run
pip install -r requirements.txt
.
Training
Sample-Selection Approaches and Collaboration with Noise-Robust loss functions
- Most code strucutres are similar with the original implementation code in https://github.com/bhanML/Co-teaching and https://github.com/shengliu66/ELR.
- If you want to train the model with
FINE
, move to the folderdynamic_selection
and run the bash files by following theREADME.md
.
Semi-Supervised Approaches
- Most codes are similar with the original implementation code in https://github.com/LiJunnan1992/DivideMix.
- If you want to train the model with
FINE
(f-dividemix
), move to the folderdividemix
and run the bash files by following theREADME.md
in thedividemix
folder.
Results
You can reproduce all results in the paper with our code. All results have been described in our paper including Appendix. The results of our experiments are so numerous that it is difficult to post everything here. However, if you experiment several times by modifying the hyperparameter value in the .sh file, you will be able to reproduce all of our analysis.
Contact
- Jongwoo Ko : Jongwoo.ko@kaist.ac.kr
- Taehyeon Kim : potter32@kaist.ac.kr
<b>License</b>
This project is licensed under the terms of the MIT license.