DivideMix
Semi-supervised learner
A PyTorch implementation of a semi-supervised learning framework for training deep neural networks with noisy labels by dynamically dividing the data into clean and noisy sets.
Code for paper: DivideMix: Learning with Noisy Labels as Semi-supervised Learning
543 stars
9 watching
84 forks
Language: Python
last commit: about 4 years ago Related projects:
| Repository | Description | Stars |
|---|---|---|
 benedekrozemberczki/splitter | A PyTorch implementation of node representation learning using multiple social contexts | 213 |
 illidanlab/splitmix | An algorithm for distributed learning with flexible model customization during training and testing | 40 |
 kthyeon/fine_official | An implementation of a method for training machine learning models using noisy labels | 38 |
 minglllli/cbafed | A PyTorch implementation of a method for improving semi-supervised learning in federated settings by adapting pseudo labels to balance classes. | 7 |
 diaoenmao/semifl-semi-supervised-federated-learning-for-unlabeled-clients-with-alternate-training | An implementation of semi-supervised federated learning for improving the performance of a server using distributed clients with unlabeled data | 34 |
 wohlert/semi-supervised-pytorch | A collection of semi-supervised learning and generative models implemented in PyTorch | 707 |
 tmadl/semisup-learn | A framework for training semi-supervised machine learning models using various techniques | 502 |
 js-mim/mss_pytorch | This project provides a PyTorch implementation of a singing voice separation algorithm using recurrent inference and skip-filtering connections. | 171 |
 dmizr/phuber | An implementation of gradient clipping as a method to mitigate the effects of noisy labels in machine learning models | 14 |
 spandan-madan/pytorch_fine_tuning_tutorial | Provides guidance on fine-tuning pre-trained models for image classification tasks using PyTorch. | 279 |
 open-mmlab/mmengine | Provides a flexible and configurable framework for training deep learning models with PyTorch. | 1,179 |
 moucheng2017/med-noisy-labels | Provides PyTorch implementation of a method to address noisy labels in medical image segmentation. | 71 |
 nust-machine-intelligence-laboratory/jo-src | An implementation of a contrastive learning approach to address noisy labels in machine learning models | 5 |
 uds-lsv/multi-tasking_learning_with_unreliable_labels | An open source software project that extends an existing algorithm to handle noisy labels in machine learning for low-resource data generation. | 8 |
 zhanghang1989/pytorch-encoding | A Python framework for building deep learning models with optimized encoding layers and batch normalization. | 2,041 |