论文标题
通过对预训练的CNN特征进行线性判别分析来降低维度的降低。
Supervised dimensionality reduction by a Linear Discriminant Analysis on pre-trained CNN features
论文作者
论文摘要
我们探讨了线性判别分析（LDA）在不同鉴定的深卷积神经网络（CNN）中获得的特征。与其他技术相比，LDA的优势在降低维度方面的优势在于，它在保留数据的全局结构的同时降低了尺寸，因此发现的低维结构的距离是有意义的。应用于CNN功能的LDA发现，与对应于不同数据相对应的类，与相似数据相对应的类的质心更接近。我们将方法应用于MNIST数据集的修改，其中有十个其他类，每个新类，其中一半来自标准的十个类之一。该方法找到了接近我们采用的数据表格的新类。我们还将该方法应用于蝴蝶图像的数据集，以发现发现相关的亚种是接近的。对于这两个数据集，我们都会找到类似于最新方法的性能。
We explore the application of linear discriminant analysis (LDA) to the features obtained in different layers of pretrained deep convolutional neural networks (CNNs). The advantage of LDA compared to other techniques in dimensionality reduction is that it reduces dimensions while preserving the global structure of data, so distances in the low-dimensional structure found are meaningful. The LDA applied to the CNN features finds that the centroids of classes corresponding to the similar data lay closer than classes corresponding to different data. We applied the method to a modification of the MNIST dataset with ten additional classes, each new class with half of the images from one of the standard ten classes. The method finds the new classes close to the corresponding standard classes we took the data form. We also applied the method to a dataset of images of butterflies to find that related subspecies are found to be close. For both datasets, we find a performance similar to state-of-the-art methods.
