IEICE Trans. Information and Systemsに論文が採録されました

当研究室の論文がIEICE Trans. Information and Systemsに採録されました．

R. Higashimoto, T. Horihata, S. Yoshida, M. Muneyasu: Unbiased Pseudo-Labeling for Learning with Noisy Labels

概要

Noisy labels in training data can significantly harm the performance of deep neural networks (DNNs). Recent research on learning with noisy labels uses a property of DNNs called the memorization effect to divide the training data into a set of data with reliable labels and a set of data with unreliable labels. Methods introducing semi-supervised learning strategies discard the unreliable labels and assign pseudo-labels generated from the confident predictions of the model. So far, this semi-supervised strategy has yielded the best results in this field. However, we observe that even when models are trained on balanced data, the distribution of pseudo-labels can still exhibit imbalance, driven by similarity among data. Additionally, a data bias is seen, originating from the division of training data using the semi-supervised method. If we address these biases that arises from pseudo-labels, we can avoid the decrease in generalization performance caused by biased noisy pseudo-labels. We propose a learning method with noisy labels that introduces unbiased pseudo-labeling based on causal inference. The proposed method achieves significant accuracy gains in experiments at high noise rates on the standard benchmarks CIFAR-10 and CIFAR-100.