meta-weight-net
Class balance fixer
This is an implementation of a meta-learning algorithm to address class imbalance issues in deep learning models with noisy labels.
NeurIPS'19: Meta-Weight-Net: Learning an Explicit Mapping For Sample Weighting (Pytorch implementation for noisy labels).
284 stars
7 watching
68 forks
Language: Python
last commit: almost 5 years agoclass-imbalancemeta-learningnoisy-labelssample-reweighting
Related projects:
| Repository | Description | Stars |
|---|---|---|
 uber-research/learning-to-reweight-examples | Project implementing a method to improve deep learning model robustness by re-weighting examples with noisy labels | 269 |
 ikostrikov/pytorch-meta-optimizer | A PyTorch implementation of meta-learning using gradient descent to adapt to new tasks. | 312 |
 xiaoboxia/classification-with-noisy-labels-by-importance-reweighting | An implementation of a method to improve classification accuracy on noisy labels by reweighting their importance | 39 |
 tristandeleu/pytorch-meta | Provides tools and datasets for meta-learning and few-shot learning in deep learning | 1,996 |
 younghjung/onlinemlrboostingwithvfdt | An implementation of online multi-label ranking boosting using VFDT as weak learners | 4 |
 kthyeon/fine_official | Implementation of a method to improve machine learning models trained with noisy labels by selecting and collaborating with high-quality samples | 39 |
 zhiningliu1998/imbalanced-ensemble | A library that enables quick and efficient ensemble learning on imbalanced datasets through various over-/under-sampling methods and algorithms | 340 |
 pxiangwu/topofilter | Develops and evaluates machine learning algorithms to mitigate the effects of noisy labels in supervised learning. | 30 |
 stormraiser/gan-weight-norm | Improves the performance of Generative Adversarial Networks by normalizing weights and batch data | 181 |
 minglllli/cbafed | A PyTorch implementation of a method for improving semi-supervised learning in federated settings by adapting pseudo labels to balance classes. | 7 |
| xiaoboxia/cdr | An implementation of a PyTorch-based deep learning method to improve robustness against noisy labels in image classification tasks | 75 |
| xiaoboxia/t-revision | A PyTorch implementation of a method for learning with noisy labels in deep neural networks | 97 |
 alykhantejani/nninit | Provides weight initialization schemes for PyTorch neural networks | 70 |
 moucheng2017/med-noisy-labels | Provides PyTorch implementation of a method to address noisy labels in medical image segmentation. | 71 |
 lijunnan1992/dividemix | 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. | 546 |