论文标题
通过分布数据进行学习的学习，以进行音频分类
Learning with Out-of-Distribution Data for Audio Classification
论文作者
论文摘要
在监督的机器学习中，并不总是满足正确标记培训数据的假设。在本文中，我们调查了一个标记错误的标记错误的实例，其中分类任务被数据集损坏的情况（OOD）实例损坏：不属于任何目标类的数据，但被标记为此类。我们表明，检测和重新定制某些OOD实例而不是丢弃它们，可以对学习产生积极影响。所提出的方法使用辅助分类器，该分类器对已知分布的数据进行了培训，用于检测和重新布置。证明这所需的数据量很小。实验是在FSDNOISY18K音频数据集上进行的，其中OOD实例非常普遍。提出的方法显示出可显着的边缘提高卷积神经网络的性能。与其他噪声动力技术的比较同样令人鼓舞。
In supervised machine learning, the assumption that training data is labelled correctly is not always satisfied. In this paper, we investigate an instance of labelling error for classification tasks in which the dataset is corrupted with out-of-distribution (OOD) instances: data that does not belong to any of the target classes, but is labelled as such. We show that detecting and relabelling certain OOD instances, rather than discarding them, can have a positive effect on learning. The proposed method uses an auxiliary classifier, trained on data that is known to be in-distribution, for detection and relabelling. The amount of data required for this is shown to be small. Experiments are carried out on the FSDnoisy18k audio dataset, where OOD instances are very prevalent. The proposed method is shown to improve the performance of convolutional neural networks by a significant margin. Comparisons with other noise-robust techniques are similarly encouraging.
