Masking
by bhanML
NeurIPS'18: Masking: A New Perspective of Noisy Supervision
AI summary
Noisy Supervision Method
An implementation of Masking, a method to improve the robustness of deep neural networks under noisy supervision
- stars
- 54
- forks
- 7
- watching
- 5
Similar projects
Found by comparing what the projects do, not just their names.
Deep learning on noisy data
An implementation of training deep neural networks on noisy labels with bootstrapping using Keras
Noisy label training method
Develops a robust training method for deep neural networks using noisy labels
Label noise study
An investigation into deep learning models trained with noisy labels and methods to improve their accuracy.
Sample selection
Implementation of a method to improve machine learning models trained with noisy labels by selecting and collaborating with high-quality samples
Task adaptation framework
Adapting a single network to multiple tasks by learning to mask weights
Object detection framework
A PyTorch implementation of the Mask R-CNN architecture
Deep Learning Study
A collection of papers and repos on deep learning with noisy labels.
Instance segmenter
An open source implementation of Mask Scoring R-CNN for instance segmentation tasks.
Co-teaching algorithm
This project implements a PyTorch-based co-teaching algorithm to improve generalization against label corruption in machine learning.
Noisy label solver
An implementation of a contrastive learning approach to address noisy labels in machine learning models
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.
Segmentation model
A deep learning implementation of an object segmentation algorithm.
Label noise mitigation
Develops and evaluates machine learning algorithms to mitigate the effects of noisy labels in supervised learning.
Noise mask neural network
A PyTorch implementation of a neural network architecture that modifies the input to its layers by applying noise masks.
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.