A Simple yet Effective Baseline for Robust Deep Learning with Noisy Labels
This addresses the issue of noisy labels in deep learning, which can degrade model performance, but it is an incremental improvement over existing methods.
The paper tackles the problem of deep neural networks memorizing noisy labels, which harms generalization, by introducing a variance regularization method that penalizes the Jacobian norm to prevent overfitting. The approach achieves state-of-the-art performance with high tolerance to severe noise on synthetic and realistic datasets.
Recently deep neural networks have shown their capacity to memorize training data, even with noisy labels, which hurts generalization performance. To mitigate this issue, we provide a simple but effective baseline method that is robust to noisy labels, even with severe noise. Our objective involves a variance regularization term that implicitly penalizes the Jacobian norm of the neural network on the whole training set (including the noisy-labeled data), which encourages generalization and prevents overfitting to the corrupted labels. Experiments on both synthetically generated incorrect labels and realistic large-scale noisy datasets demonstrate that our approach achieves state-of-the-art performance with a high tolerance to severe noise.