[2Win5] Poster session 2

[2Win5-01] Adaptive Stopping of Relabeling for Learning with Noisy Label

〇Kazuki Uematsu¹, Hideyuki Nakagawa¹, Takahiro Takimoto¹ (1.Toshiba Corporation)

Keywords:Noisy Label

Supervised learning is applied in various domains. However, human instructional errors are inevitable especially when large amount of expert instruction is required. Standard supervised learning with noisy labels suffers from overfitting, which degrades generalization performance of the model. In this study, we analyze the learning process of deep learning models under label noise and investigate how to correct (relabel) erroneous labels for learning with noisy labels. We find that it is important to perform relabeling at a relatively high learning rate for appropriate number of iterations. By incorporating these properties, we demonstrated that classification accuracy can be maintained under label noise.