Noise-Robust Bidirectional Learning with Dynamic Sample Reweighting
This addresses label noise in deep learning, which is a common issue in real-world datasets, but the approach appears incremental as it builds on existing negative learning methods.
The paper tackles the problem of deep neural networks memorizing noisy labels by proposing a bidirectional learning scheme that combines positive learning for convergence speed and negative learning for noise robustness, along with dynamic sample reweighting and self-distillation, achieving improved performance on benchmark datasets.
Deep neural networks trained with standard cross-entropy loss are more prone to memorize noisy labels, which degrades their performance. Negative learning using complementary labels is more robust when noisy labels intervene but with an extremely slow model convergence speed. In this paper, we first introduce a bidirectional learning scheme, where positive learning ensures convergence speed while negative learning robustly copes with label noise. Further, a dynamic sample reweighting strategy is proposed to globally weaken the effect of noise-labeled samples by exploiting the excellent discriminatory ability of negative learning on the sample probability distribution. In addition, we combine self-distillation to further improve the model performance. The code is available at \url{https://github.com/chenchenzong/BLDR}.