论文标题
一个用于图像分类的卷积神经网络委员会以及特征噪声的同时存在
A Committee of Convolutional Neural Networks for Image Classication in the Concurrent Presence of Feature and Label Noise
论文作者
论文摘要
图像分类已成为无处不在的任务。经过高质量数据培训的模型达到了精确度，在某些应用程序域中，该模型已经高于人级的性能。不幸的是，现实世界中的数据经常被功能和/或标签中存在的噪声退化。有很多论文分别解决了特征或标签噪声的问题。但是，据我们所知，这项研究是解决两种噪声同时出现问题的首次尝试。在MNIST，CIFAR-10和CIFAR-100数据集上，我们在实验上证明，无论是属性还是标签的破坏，委员会击败单个模型随着噪声水平的增加的差异。因此，它使集团合法地应用于带有嘈杂标签的嘈杂图像。上述委员会比单个模型的优势也与数据集难度级别呈正相关。我们提出了三种委员会选择算法，这些算法的表现优于强大的基线算法，该算法依赖于个人（非相关）最佳模型的合奏。
Image classification has become a ubiquitous task. Models trained on good quality data achieve accuracy which in some application domains is already above human-level performance. Unfortunately, real-world data are quite often degenerated by the noise existing in features and/or labels. There are quite many papers that handle the problem of either feature or label noise, separately. However, to the best of our knowledge, this piece of research is the first attempt to address the problem of concurrent occurrence of both types of noise. Basing on the MNIST, CIFAR-10 and CIFAR-100 datasets, we experimentally proved that the difference by which committees beat single models increases along with noise level, no matter it is an attribute or label disruption. Thus, it makes ensembles legitimate to be applied to noisy images with noisy labels. The aforementioned committees' advantage over single models is positively correlated with dataset difficulty level as well. We propose three committee selection algorithms that outperform a strong baseline algorithm which relies on an ensemble of individual (nonassociated) best models.
