O2U-Net
by hjimce
paper "O2U-Net: A Simple Noisy Label Detection Approach for Deep Neural Networks" code
AI summary
Label noise detector
An approach to detect noise in labels used with deep neural networks during training
- stars
- 77
- forks
- 12
- watching
- 4
Similar projects
Found by comparing what the projects do, not just their names.
Label noise toolset
Provides tools and data for studying instance-dependent label noise in deep neural networks, with a focus on combating noisy labels
Label noise mitigator
An implementation of a method to improve model robustness against inherent label noise in machine learning models
Object detector
A Python-based object detection framework utilizing transformers and computer vision techniques to detect salient objects in RGB-thermal images
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.
Label noise study
An investigation into deep learning models trained with noisy labels and methods to improve their accuracy.
Noisy label handling tool
An open source software project that extends an existing algorithm to handle noisy labels in machine learning for low-resource data generation.
Label noise mitigation
Develops and evaluates machine learning algorithms to mitigate the effects of noisy labels in supervised learning.
Deep Learning Study
A collection of papers and repos on deep learning with noisy labels.
Object detector
A Python interface to YOLO object detection software using Darknet
Noisy label solver
An implementation of a contrastive learning approach to address noisy labels in machine learning models
Noisy label trainer
An implementation of a neural network training method using noisy labels
Label noise handler
An implementation of a deep learning training method for handling noisy labels in convolutional neural networks using the VGG-16 network architecture.
Noisy Label Training
A repository providing code and scripts for training image classification models on noisy labeled data
Sample selection
Implementation of a method to improve machine learning models trained with noisy labels by selecting and collaborating with high-quality samples
Label noise correction
A method to train deep learning classifiers on noisy labels using a small set of trusted data
