Meta Soft Label Generation for Noisy Labels

by   Görkem Algan, et al.
Middle East Technical University

The existence of noisy labels in the dataset causes significant performance degradation for deep neural networks (DNNs). To address this problem, we propose a Meta Soft Label Generation algorithm called MSLG, which can jointly generate soft labels using meta-learning techniques and learn DNN parameters in an end-to-end fashion. Our approach adapts the meta-learning paradigm to estimate optimal label distribution by checking gradient directions on both noisy training data and noise-free meta-data. In order to iteratively update soft labels, meta-gradient descent step is performed on estimated labels, which would minimize the loss of noise-free meta samples. In each iteration, the base classifier is trained on estimated meta labels. MSLG is model-agnostic and can be added on top of any existing model at hand with ease. We performed extensive experiments on CIFAR10, Clothing1M and Food101N datasets. Results show that our approach outperforms other state-of-the-art methods by a large margin.


page 1

page 2

page 3

page 4


MetaLabelNet: Learning to Generate Soft-Labels from Noisy-Labels

Real-world datasets commonly have noisy labels, which negatively affects...

Learning to Purify Noisy Labels via Meta Soft Label Corrector

Recent deep neural networks (DNNs) can easily overfit to biased training...

Learning Soft Labels via Meta Learning

One-hot labels do not represent soft decision boundaries among concepts,...

A Meta-Learning Approach to the Optimal Power Flow Problem Under Topology Reconfigurations

Recently, there has been a surge of interest in adopting deep neural net...

Deep Learning from Small Amount of Medical Data with Noisy Labels: A Meta-Learning Approach

Computer vision systems recently made a big leap thanks to deep neural n...

Pumpout: A Meta Approach for Robustly Training Deep Neural Networks with Noisy Labels

It is challenging to train deep neural networks robustly on the industri...

Robust Meta-learning with Sampling Noise and Label Noise via Eigen-Reptile

Recent years have seen a surge of interest in meta-learning techniques f...

Please sign up or login with your details

Forgot password? Click here to reset