glc

Label noise correction

A method to train deep learning classifiers on noisy labels using a small set of trusted data

Gold Loss Correction

GitHub

86 stars
3 watching
14 forks
Language: Python
last commit: almost 8 years ago

Related projects:

RepositoryDescriptionStars
xiaoboxia/cdrAn implementation of a PyTorch-based deep learning method to improve robustness against noisy labels in image classification tasks75
moucheng2017/med-noisy-labelsProvides PyTorch implementation of a method to address noisy labels in medical image segmentation.71
pxiangwu/topofilterDevelops and evaluates machine learning algorithms to mitigate the effects of noisy labels in supervised learning.30
hongxin001/odnlAn implementation of a method to improve model robustness against inherent label noise in machine learning models19
paulalbert31/labelnoisecorrectionAn implementation of an unsupervised label noise modeling and loss correction approach for deep learning.221
delchiaro/training-cnn-noisy-labels-kerasAn implementation of a deep learning training method for handling noisy labels in convolutional neural networks using the VGG-16 network architecture.6
pokaxpoka/rognoisylabelA Python package for robust inference via generative classifiers for handling noisy labels in machine learning.33
xiaoboxia/t-revisionA PyTorch implementation of a method for learning with noisy labels in deep neural networks97
hitcszx/lnl_srAn implementation of a regularization technique to improve the accuracy of deep learning models trained with noisy labels.46
digitalglobe/mltoolsTools for building machine learning solutions on satellite imagery81
dmizr/phuberAn implementation of gradient clipping as a method to mitigate the effects of noisy labels in machine learning models14
hjimce/o2u-netAn approach to detect noise in labels used with deep neural networks during training77
gorkemalgan/deep_learning_with_noisy_labels_literatureA collection of papers and repos on deep learning with noisy labels.235
chenpf1025/idnProvides tools and data for studying instance-dependent label noise in deep neural networks, with a focus on combating noisy labels35
pingqingsheng/lrtAn algorithm designed to robustly correct noisy labels in training data by iteratively refining the network's confidence and updating the loss function.22