Unknown Class Label Cleaning For Learning With Open-Set Noisy Labels
Unknown Class Label Cleaning For Learning With Open-Set Noisy Labels
复制标题
DOI：
10.1109/icip40778.2020.9190652
复制
发表时间：
2020-10
期刊：
影响因子：
--
通讯作者：
Qing Yu;K. Aizawa
中科院分区：
文献类型：
--
作者：
Qing Yu;K. Aizawa
在大规模注释数据集上训练的深度神经网络（DNN）在图像分类领域取得了令人印象深刻的结果。许多大规模的数据集都是从网站上收集的;然而，这些数据不可避免地被噪声破坏了。在这项研究中，我们研究了开集噪声标签问题，其中一些离群值包含在数据集中并通过噪声标签进行注释，但不属于任何类别的训练数据。为了解决这个问题，我们提出了一种新的未知类标签清洗框架，用于训练具有开集噪声标签的DNN。除了一般的图像分类，我们还通过为所有数据分配一个伪未知标签来估计输入来自未知类的概率，并通过交替更新网络参数和标签来纠正这些标签。在嘈杂的CIFAR-10数据集上进行的实验结果表明，我们的方法可以鲁棒地训练具有高比例嘈杂标签的DNN。
Deep neural networks (DNNs) trained on large-scale annotated datasets have achieved impressive results in the area of image classification. Many large-scale datasets have been collected from websites; however, such data are inevitably corrupted with noise. In this study, we researched the open-set noisy label problem, where some outliers are contained in a dataset and annotated through a noisy label but do not belong to any class of training data. To address this problem, we propose a novel unknown class label cleaning framework for the training of DNNs with open-set noisy labels. In addition to general image classification, we also estimate the probability of an input being from an unknown class by assigning a pseudo unknown label to all of the data and correct these labels through an alternating update of the network parameters and labels. The results of experiments conducted on the noisy CIFAR-10 datasets demonstrate that our approach can robustly train DNNs with a high proportion of noisy labels.