Noise is the fatal poison: A Noise-aware Network for noisy dataset classification

Xiaotian Yu, Shengxuming Zhang, Lingxiang Jia, Yuexuan Wang, Mingli Song, Zunlei Feng

Abstract: Highlights•The first to clarify the influence extent of noisy and hard samples for training.•Noise-aware Network with separate groups of kernels is proposed for handling noise.•A new loss function is proposed to make the training robust to the noise.