DST: Data Selection and joint Training for Learning with Noisy Labels

by   Yi Wei, et al.

Training a deep neural network heavily relies on a large amount of training data with accurate annotations. To alleviate this problem, various methods have been proposed to annotate the data automatically. However, automatically generating annotations will inevitably yields noisy labels. In this paper, we propose a Data Selection and joint Training (DST) method to automatically select training samples with accurate annotations. Specifically, DST fits a mixture model according to the original annotation as well as the predicted label for each training sample, and the mixture model is utilized to dynamically divide the training dataset into a correctly labeled dataset, a correctly predicted set and a wrong dataset. Then, DST is trained with these datasets in a supervised manner. Due to confirmation bias problem, we train the two networks alternately, and each network is tasked to establish the data division to teach another network. For each iteration, the correctly labeled and predicted labels are reweighted respectively by the probabilities from the mixture model, and a uniform distribution is used to generate the probabilities of the wrong samples. Experiments on CIFAR-10, CIFAR-100 and Clothing1M demonstrate that DST is the comparable or superior to the state-of-the-art methods.


page 4

page 5


Reliable Label Correction is a Good Booster When Learning with Extremely Noisy Labels

Learning with noisy labels has aroused much research interest since data...

A Semi-Supervised Two-Stage Approach to Learning from Noisy Labels

The recent success of deep neural networks is powered in part by large-s...

Augmentation Strategies for Learning with Noisy Labels

Imperfect labels are ubiquitous in real-world datasets. Several recent s...

Sample Prior Guided Robust Model Learning to Suppress Noisy Labels

Imperfect labels are ubiquitous in real-world datasets and seriously har...

Confidence Adaptive Regularization for Deep Learning with Noisy Labels

Recent studies on the memorization effects of deep neural networks on no...

ChoiceNet: Robust Learning by Revealing Output Correlations

In this paper, we focus on the supervised learning problem with corrupte...

No Regret Sample Selection with Noisy Labels

Deep Neural Network (DNN) suffers from noisy labeled data because of the...

Please sign up or login with your details

Forgot password? Click here to reset