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 6 years ago

Related projects:

Repository Description Stars
xiaoboxia/cdr An implementation of a PyTorch-based deep learning method to improve robustness against noisy labels in image classification tasks 75
moucheng2017/med-noisy-labels Provides PyTorch implementation of a method to address noisy labels in medical image segmentation. 71
pxiangwu/topofilter Develops and evaluates machine learning algorithms to mitigate the effects of noisy labels in supervised learning. 29
hongxin001/odnl An implementation of a method to improve model robustness against inherent label noise in machine learning models 19
paulalbert31/labelnoisecorrection An implementation of an unsupervised label noise modeling and loss correction approach for deep learning. 220
delchiaro/training-cnn-noisy-labels-keras An implementation of a deep learning training method for handling noisy labels in convolutional neural networks using the VGG-16 network architecture. 6
pokaxpoka/rognoisylabel A Python package for robust inference via generative classifiers for handling noisy labels in machine learning. 33
xiaoboxia/t-revision A PyTorch implementation of a method for learning with noisy labels in deep neural networks 98
hitcszx/lnl_sr An implementation of a regularization technique to improve the accuracy of deep learning models trained with noisy labels. 46
digitalglobe/mltools Tools for building machine learning solutions on satellite imagery 82
dmizr/phuber An implementation of gradient clipping as a method to mitigate the effects of noisy labels in machine learning models 14
hjimce/o2u-net An approach to detect noise in labels used with deep neural networks during training 77
gorkemalgan/deep_learning_with_noisy_labels_literature A collection of papers and repos on deep learning with noisy labels. 235
chenpf1025/idn Provides tools and data for studying instance-dependent label noise in deep neural networks, with a focus on combating noisy labels 35
pingqingsheng/lrt An algorithm designed to robustly correct noisy labels in training data by iteratively refining the network's confidence and updating the loss function. 21