Masking
Noisy Supervision Solution
A project implementing a novel approach to noisy supervision in machine learning using masked loss correction and adaptation
NeurIPS'18: Masking: A New Perspective of Noisy Supervision
54 stars
5 watching
7 forks
Language: Python
last commit: almost 6 years ago Related projects:
| Repository | Description | Stars |
|---|---|---|
 dr-darryl-wright/noisy-labels-with-bootstrapping | An implementation of training deep neural networks on noisy labels with bootstrapping using Keras | 22 |
| bhanml/co-teaching | This project provides an implementation of Co-teaching, a method for training deep neural networks with extremely noisy labels. | 492 |
 chenpf1025/noisy_label_understanding_utilizing | An investigation into deep learning models trained with noisy labels and methods to improve their accuracy. | 90 |
 kthyeon/fine_official | An implementation of a method for training machine learning models using noisy labels | 38 |
 arunmallya/piggyback | Adapting a single network to multiple tasks by learning to mask weights | 181 |
 wannabeog/mask-rcnn | A PyTorch implementation of the Mask R-CNN architecture | 992 |
 gorkemalgan/deep_learning_with_noisy_labels_literature | A collection of papers and repos on deep learning with noisy labels. | 235 |
 zjhuang22/maskscoring_rcnn | An open source implementation of Mask Scoring R-CNN for instance segmentation tasks. | 1,900 |
| bhanml/coteaching_plus | This project implements a PyTorch-based co-teaching algorithm to improve generalization against label corruption in machine learning. | 21 |
 nust-machine-intelligence-laboratory/jo-src | An implementation of a contrastive learning approach to address noisy labels in machine learning models | 5 |
 udibr/noisy_labels | This project explores how to adapt neural networks to noisy labels by introducing a mechanism that can learn to correct the errors. | 118 |
 abbypa/nnproject_deepmask | A deep learning implementation of an object segmentation algorithm. | 187 |
 pxiangwu/topofilter | Develops and evaluates machine learning algorithms to mitigate the effects of noisy labels in supervised learning. | 29 |
 michaelklachko/pnn.pytorch | A PyTorch implementation of a neural network architecture that modifies the input to its layers by applying noise masks. | 57 |
 uds-lsv/multi-tasking_learning_with_unreliable_labels | An open source software project that extends an existing algorithm to handle noisy labels in machine learning for low-resource data generation. | 8 |