Awesome-Noisy-Labels

awesome listpushed over 3 years ago

A Survey

AI summary

Noisy label handling survey

This repository provides a comprehensive survey and collection of papers on techniques for handling noisy labels in machine learning with deep neural networks.

stars: 545
forks: 31
watching: 5
awesome list: 1
entries: 134

What's in the list

134 links in 7 sections, with live GitHub stats.activeno commit in 2y

Links

arxiv version
[ ]

A. Robust Architecture

Webly supervised learning of convolutional networks
Official (Caffe)
7over 8 years
Training convolutional networks with noisy labels
Unofficial (Keras)
6over 9 years
Learning deep networks from noisy labels with dropout regularization
Official (MATLAB)
118 years
Training deep neural-networks based on unreliable labels
Unofficial (Chainer)
5over 9 years
Training deep neural-networks using a noise adaptation layer
Official (Keras)
118over 9 years
Learning from massive noisy labeled data for image classification
Official (Caffe)
116over 7 years
Masking: A new perspective of noisy supervision
Official (TensorFlow)
54almost 8 years
Deep learning from noisy image labels with quality embedding
Robust inference via generative classifiers for handling noisy labels
Official (PyTorch)
337 years

B. Robust Regularization

C. Robust Loss Function

D. Loss Adjustment

E. Sample Selection

Learning from Noisy Labels towards Realistic Scenarios

Online Continual Learning on a Contaminated Data Stream with Blurry Task Boundaries
, CVPR 2022, [ ] This paper addresses the problem of noisy labels in the online continual learning setup
Learning from Multiple Annotator Noisy Labels via Sample-wise Label Fusion
, ECCV 2022, [ ] This paper addresses the scenario in which each data instance has multiple noisy labels from annotators (instead of a single label)

Featured in 1 awesome list

Each link jumps to the spot where the list mentions Awesome-Noisy-Labels.

subeeshvasu/awesome-learning-with-label-noise