论文标题
建立神经网络可靠地标记噪声
Establishment of Neural Networks Robust to Label Noise
论文作者
论文摘要
标签噪声是深度学习模型培训的重要障碍。它可能对图像分类模型的性能，尤其是深神经网络的性能产生相当大的影响，这些模型特别容易受到影响，因为它们具有记忆嘈杂标签的强烈倾向。在本文中，我们研究了相关标签噪声方法的基本概念。已经创建了一个过渡矩阵估计器，并且已经证明了其针对实际过渡矩阵的有效性。此外，我们研究了使用LENET和ALEXNET设计的两个卷积神经网络分类器的标签噪声稳健性。两个时尚主义者数据集揭示了这两种模型的鲁棒性。由于时间和计算资源约束，我们无法正确调整复杂的卷积神经网络模型，因此无法有效地证明过渡矩阵噪声校正对鲁棒性增强的影响。需要额外的努力来微调神经网络模型，并探索未来研究中估计的过渡模型的精确度。
Label noise is a significant obstacle in deep learning model training. It can have a considerable impact on the performance of image classification models, particularly deep neural networks, which are especially susceptible because they have a strong propensity to memorise noisy labels. In this paper, we have examined the fundamental concept underlying related label noise approaches. A transition matrix estimator has been created, and its effectiveness against the actual transition matrix has been demonstrated. In addition, we examined the label noise robustness of two convolutional neural network classifiers with LeNet and AlexNet designs. The two FashionMINIST datasets have revealed the robustness of both models. We are not efficiently able to demonstrate the influence of the transition matrix noise correction on robustness enhancements due to our inability to correctly tune the complex convolutional neural network model due to time and computing resource constraints. There is a need for additional effort to fine-tune the neural network model and explore the precision of the estimated transition model in future research.
