论文标题
嘈杂标签的元软标签生成
Meta Soft Label Generation for Noisy Labels
论文作者
论文摘要
数据集中的嘈杂标签的存在会导致深层神经网络（DNNS）的显着性能降解。为了解决这个问题，我们提出了一种称为MSLG的元软标签生成算法，该算法可以使用元学习技术共同生成软标签，并以端到端的方式学习DNN参数。我们的方法通过检查嘈杂训练数据和无噪声元数据的梯度方向来适应元学习范式来估计最佳标签分布。为了迭代更新软标签，对估计标签进行元梯度下降步骤，这将最大程度地减少无噪声元样本的损失。在每次迭代中，基本分类器都经过估计的元标签培训。 MSLG是模型不平衡的，可以轻松地将其添加到任何现有的模型之上。我们在CIFAR10，服装1M和Food101N数据集上进行了广泛的实验。结果表明，我们的方法以大幅度优于其他最先进的方法。
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.
