Meta Soft Label Generation for Noisy Labels


Algan G., ULUSOY İ.

25th International Conference on Pattern Recognition (ICPR), ELECTR NETWORK, 10 - 15 January 2021, pp.7142-7148 identifier identifier

  • Publication Type: Conference Paper / Full Text
  • Volume:
  • Doi Number: 10.1109/icpr48806.2021.9412490
  • Country: ELECTR NETWORK
  • Page Numbers: pp.7142-7148
  • Keywords: deep learning, label noise, noise robust, noise cleansing, meta-learning

Abstract

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. Our code is available at https://github.com/gorkemalgan/MSLG_noisy_label.