noisy_labels

Label correction mechanism

This project explores how to adapt neural networks to noisy labels by introducing a mechanism that can learn to correct the errors.

TRAINING DEEP NEURAL-NETWORKS USING A NOISE ADAPTATION LAYER

GitHub

118 stars
6 watching
38 forks
Language: Jupyter Notebook
last commit: over 9 years ago
Linked from 2 awesome lists


Backlinks from these awesome lists:

Related projects:

RepositoryDescriptionStars
dr-darryl-wright/noisy-labels-with-bootstrappingAn implementation of training deep neural networks on noisy labels with bootstrapping using Keras22
chenpf1025/noisy_label_understanding_utilizingAn investigation into deep learning models trained with noisy labels and methods to improve their accuracy.90
uds-lsv/multi-tasking_learning_with_unreliable_labelsAn open source software project that extends an existing algorithm to handle noisy labels in machine learning for low-resource data generation.8
chenpf1025/idnProvides tools and data for studying instance-dependent label noise in deep neural networks, with a focus on combating noisy labels35
xiaoboxia/t-revisionA PyTorch implementation of a method for learning with noisy labels in deep neural networks97
paulalbert31/labelnoisecorrectionAn implementation of an unsupervised label noise modeling and loss correction approach for deep learning.221
vdenberg/noisy-label-neural-networkAn implementation of a neural network algorithm designed to improve performance on noisy labeled data3
moucheng2017/med-noisy-labelsProvides PyTorch implementation of a method to address noisy labels in medical image segmentation.71
cysu/noisy_labelA repository providing code and scripts for training image classification models on noisy labeled data116
weijiaheng/advances-in-label-noise-learningA curated collection of papers and resources on learning with noisy labels in machine learning696
ryo-ito/noisy-labels-neural-networkAn implementation of a neural network training method using noisy labels5
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
nust-machine-intelligence-laboratory/jo-srcAn implementation of a contrastive learning approach to address noisy labels in machine learning models5
xiaoboxia/cdrAn implementation of a PyTorch-based deep learning method to improve robustness against noisy labels in image classification tasks75
hongxin001/odnlAn implementation of a method to improve model robustness against inherent label noise in machine learning models19