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
118 stars
6 watching
38 forks
Language: Jupyter Notebook
last commit: almost 8 years ago
Linked from 2 awesome lists
Related projects:
Repository | Description | Stars |
---|---|---|
| An implementation of training deep neural networks on noisy labels with bootstrapping using Keras | 22 |
| An investigation into deep learning models trained with noisy labels and methods to improve their accuracy. | 90 |
| An open source software project that extends an existing algorithm to handle noisy labels in machine learning for low-resource data generation. | 8 |
| Provides tools and data for studying instance-dependent label noise in deep neural networks, with a focus on combating noisy labels | 35 |
| A PyTorch implementation of a method for learning with noisy labels in deep neural networks | 97 |
| An implementation of an unsupervised label noise modeling and loss correction approach for deep learning. | 221 |
| An implementation of a neural network algorithm designed to improve performance on noisy labeled data | 3 |
| Provides PyTorch implementation of a method to address noisy labels in medical image segmentation. | 71 |
| A repository providing code and scripts for training image classification models on noisy labeled data | 116 |
| A curated collection of papers and resources on learning with noisy labels in machine learning | 696 |
| An implementation of a neural network training method using noisy labels | 5 |
| An implementation of a deep learning training method for handling noisy labels in convolutional neural networks using the VGG-16 network architecture. | 6 |
| An implementation of a contrastive learning approach to address noisy labels in machine learning models | 5 |
| An implementation of a PyTorch-based deep learning method to improve robustness against noisy labels in image classification tasks | 75 |
| An implementation of a method to improve model robustness against inherent label noise in machine learning models | 19 |