Learning from noisy labels with deep neural networks: A survey
Deep learning has achieved remarkable success in numerous domains with help from large
amounts of big data. However, the quality of data labels is a concern because of the lack of …
amounts of big data. However, the quality of data labels is a concern because of the lack of …
Beyond class-conditional assumption: A primary attempt to combat instance-dependent label noise
Supervised learning under label noise has seen numerous advances recently, while
existing theoretical findings and empirical results broadly build up on the class-conditional …
existing theoretical findings and empirical results broadly build up on the class-conditional …
Confidence scores make instance-dependent label-noise learning possible
In learning with noisy labels, for every instance, its label can randomly walk to other classes
following a transition distribution which is named a noise model. Well-studied noise models …
following a transition distribution which is named a noise model. Well-studied noise models …
Noise models in classification: Unified nomenclature, extended taxonomy and pragmatic categorization
JA Sáez - Mathematics, 2022 - mdpi.com
This paper presents the first review of noise models in classification covering both label and
attribute noise. Their study reveals the lack of a unified nomenclature in this field. In order to …
attribute noise. Their study reveals the lack of a unified nomenclature in this field. In order to …
Fairness evaluation in presence of biased noisy labels
R Fogliato, A Chouldechova… - … conference on artificial …, 2020 - proceedings.mlr.press
Risk assessment tools are widely used around the country to inform decision making within
the criminal justice system. Recently, considerable attention has been devoted to the …
the criminal justice system. Recently, considerable attention has been devoted to the …
Noise-robust learning from multiple unsupervised sources of inferred labels
Abstract Deep Neural Networks (DNNs) generally require large-scale datasets for training.
Since manually obtaining clean labels for large datasets is extremely expensive …
Since manually obtaining clean labels for large datasets is extremely expensive …
Noise simulation in classification with the noisemodel R package: Applications analyzing the impact of errors with chemical data
JA Sáez - Journal of Chemometrics, 2023 - Wiley Online Library
Classification datasets created from chemical processes can be affected by errors, which
impair the accuracy of the models built. This fact highlights the importance of analyzing the …
impair the accuracy of the models built. This fact highlights the importance of analyzing the …
[图书][B] Artificial intelligence applications and innovations
I Maglogiannis, M Bramer, K Karpouzis - 2021 - Springer
Artificial intelligence (AI) is a relatively new scientific area that emerged from the efforts of a
handful of scientists from diverse fields approximately 70 years ago. The achievements of AI …
handful of scientists from diverse fields approximately 70 years ago. The achievements of AI …
Towards an improved label noise proportion estimation in small data: a Bayesian approach
J Bootkrajang, J Chaijaruwanich - International Journal of Machine …, 2022 - Springer
Today's classification task is getting more and more complex. This inevitably renders
unanticipated compromises on the quality of data labels. In this paper, we consider learning …
unanticipated compromises on the quality of data labels. In this paper, we consider learning …
[HTML][HTML] Elucidating robust learning with uncertainty-aware corruption pattern estimation
Robust learning methods aim to learn a clean target distribution from noisy and corrupted
training data where a specific corruption pattern is often assumed a priori. Our proposed …
training data where a specific corruption pattern is often assumed a priori. Our proposed …