DivideMix

KO | EN

gitlite — search

#llm #golang #machine-learning #rust #deep-learning #linux #docker #macos #nodejs #awesome #cli #vue #awesome-list #mcp

(★ 577)

Code for paper: DivideMix: Learning with Noisy Labels as Semi-supervised Learning

파일 탐색기

최종 버전 다운로드 (.zip)

- framework.png
dataloader_cifar.py
dataloader_clothing1M.py
dataloader_webvision.py
InceptionResNetV2.py
LICENSE
PreResNet.py
README.md
Train_cifar.py
Train_clothing1M.py
Train_webvision.py
Train_webvision_parallel.py

// repository documentation

Was this content helpful?

★ 0 (0 ratings)

# DivideMix: Learning with Noisy Labels as Semi-supervised Learning
PyTorch Code for the following paper at ICLR2020:\
Title: DivideMix: Learning with Noisy Labels as Semi-supervised Learning <a href="https://openreview.net/pdf?id=HJgExaVtwr">[pdf]</a>\
Authors:Junnan Li, Richard Socher, Steven C.H. Hoi\
Institute: Salesforce Research

Abstract\
Deep neural networks are known to be annotation-hungry. Numerous efforts have been devoted to reduce the annotation cost when learning with deep networks. Two prominent directions include learning with noisy labels and semi-supervised learning by exploiting unlabeled data. In this work, we propose DivideMix, a novel framework for learning with noisy labels by leveraging semi-supervised learning techniques. In particular, DivideMix models the per-sample loss distribution with a mixture model to dynamically divide the training data into a labeled set with clean samples and an unlabeled set with noisy samples, and trains the model on both the labeled and unlabeled data in a semi-supervised manner. To avoid confirmation bias, we simultaneously train two diverged networks where each network uses the dataset division from the other network. During the semi-supervised training phase, we improve the MixMatch strategy by performing label co-refinement and label co-guessing on labeled and unlabeled samples, respectively. Experiments on multiple benchmark datasets demonstrate substantial improvements over state-of-the-art methods.

Illustration\
<img src="./img/framework.png">

Experiments\
First, please create a folder named checkpoint to store the results.\
<code>mkdir checkpoint</code>\
Next, run \
<code>python Train_{dataset_name}.py --data_path path-to-your-data</code>

Cite DivideMix\
If you find the code useful in your research, please consider citing our paper:

<pre>
@inproceedings{
 li2020dividemix,
 title={DivideMix: Learning with Noisy Labels as Semi-supervised Learning},
 author={Junnan Li and Richard Socher and Steven C.H. Hoi},
 booktitle={International Conference on Learning Representations},
 year={2020},
}</pre>

License\
This project is licensed under the terms of the MIT license.

DivideMix

파일 탐색기

오늘의 추천 프로젝트

Was this content helpful?

Recent Feedback

DivideMix

파일 탐색기

오늘의 추천 프로젝트

Was this content helpful?

Recent Feedback

Download README