Meta Soft Label Generation for Noisy Labels
This addresses the issue of noisy labels in datasets for machine learning practitioners, offering a model-agnostic solution that is incremental in improving label correction methods.
The paper tackles the problem of noisy labels degrading deep neural network performance by proposing the Meta Soft Label Generation (MSLG) algorithm, which uses meta-learning to generate soft labels and jointly learn parameters, achieving state-of-the-art results on datasets like CIFAR10, Clothing1M, and Food101N with significant performance margins.
The existence of noisy labels in the dataset causes significant performance degradation for deep neural networks (DNNs). To address this problem, we propose a Meta Soft Label Generation algorithm called MSLG, which can jointly generate soft labels using meta-learning techniques and learn DNN parameters in an end-to-end fashion. Our approach adapts the meta-learning paradigm to estimate optimal label distribution by checking gradient directions on both noisy training data and noise-free meta-data. In order to iteratively update soft labels, meta-gradient descent step is performed on estimated labels, which would minimize the loss of noise-free meta samples. In each iteration, the base classifier is trained on estimated meta labels. MSLG is model-agnostic and can be added on top of any existing model at hand with ease. We performed extensive experiments on CIFAR10, Clothing1M and Food101N datasets. Results show that our approach outperforms other state-of-the-art methods by a large margin.