用于同时存在特征和标号噪声的图像分类的卷积神经网络委员会
A Committee of Convolutional Neural Networks for Image Classication in the Concurrent Presence of Feature and Label Noise
摘要：
图像分类已成为一项普遍存在的任务。在高质量数据上训练的模型达到了在某些应用领域已经超过人类水平的准确性。不幸的是，真实世界的数据往往是退化的噪声存在于功能和/或标签。有相当多的论文分别处理特征噪声或标签噪声的问题。然而，据我们所知，这项研究是第一次尝试解决这两种类型的噪音同时发生的问题。基于MNIST、CIFAR-10和CIFAR-100数据集，我们通过实验证明了委员会击败单个模型的差异随着噪声水平的增加而增加，无论是属性还是标签中断。因此，它使合奏合法地被应用于噪声图像与噪声标签。上述委员会相对于单一模型的优势也与数据集难度水平呈正相关。我们提出了三个委员会的选择算法，优于一个强大的基线算法，依赖于一个合奏的个人（nonassociated）的最佳模型。
英文摘要：
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.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
