Tackling Instance-Dependent Label Noise via a Universal Probabilistic Model

01/14/2021
by   Qizhou Wang, et al.
0

The drastic increase of data quantity often brings the severe decrease of data quality, such as incorrect label annotations, which poses a great challenge for robustly training Deep Neural Networks (DNNs). Existing learning with label noise either employ ad-hoc heuristics or restrict to specific noise assumptions. However, more general situations, such as instance-dependent label noise, have not been fully explored, as scarce studies focus on their label corruption process. By categorizing instances into confusing and unconfusing instances, this paper proposes a simple yet universal probabilistic model, which explicitly relates noisy labels to their instances. The resultant model can be realized by DNNs, where the training procedure is accomplished by employing an alternating optimization algorithm. Experiments on datasets with both synthetic and real-world label noise verify that the proposed method yields significant improvements on robustness over state-of-the-art counterparts.

READ FULL TEXT

page 2

page 7

research
09/07/2021

Instance-dependent Label-noise Learning under a Structural Causal Model

Label noise will degenerate the performance of deep learning algorithms ...
research
06/14/2020

Parts-dependent Label Noise: Towards Instance-dependent Label Noise

Learning with the instance-dependent label noise is challenging, because...
research
05/13/2019

Understanding and Utilizing Deep Neural Networks Trained with Noisy Labels

Noisy labels are ubiquitous in real-world datasets, which poses a challe...
research
05/22/2021

Generation and Analysis of Feature-Dependent Pseudo Noise for Training Deep Neural Networks

Training Deep neural networks (DNNs) on noisy labeled datasets is a chal...
research
10/26/2022

Deep Learning is Provably Robust to Symmetric Label Noise

Deep neural networks (DNNs) are capable of perfectly fitting the trainin...
research
03/21/2023

Dynamic-Aware Loss for Learning with Label Noise

Label noise poses a serious threat to deep neural networks (DNNs). Emplo...
research
05/27/2019

Emphasis Regularisation by Gradient Rescaling for Training Deep Neural Networks with Noisy Labels

It is fundamental and challenging to train robust and accurate Deep Neur...

Please sign up or login with your details

Forgot password? Click here to reset