PixelHop:一种连续子空间学习(SSL)的目标分类方法
PixelHop: A Successive Subspace Learning (SSL) Method for Object Classification
摘要:
一种新的机器学习方法,称为连续子空间学习(SSL),介绍了这项工作。SSL包含四个关键成分:1)连续的近到远邻域扩展; 2)通过子空间近似的无监督降维; 3)通过标签辅助回归(LAG)的监督降维;以及4)特征拼接和决策。提出了一种基于图像的对象分类方法PixelHop来说明SSL设计。实验结果表明,在MNIST、Fashion MNIST和CIFAR-10三个基准数据集上,PixelHop方法的性能优于相似模型复杂度的经典CNN模型.虽然SSL和深度学习(DL)有一些共同的高级概念,但它们在模型制定,训练过程和训练复杂性方面有着根本的不同。对SSL和DL的比较进行了广泛的讨论,以进一步了解SSL的潜力。
英文摘要:
A new machine learning methodology, called successive subspace learning (SSL), is introduced in this work. SSL contains four key ingredients: 1) successive near-to-far neighborhood expansion; 2) unsupervised dimension reduction via subspace approximation; 3) supervised dimension reduction via label-assisted regression (LAG); and 4) feature concatenation and decision making. An image-based object classification method, called PixelHop, is proposed to illustrate the SSL design. It is shown by experimental results that the PixelHop method outperforms the classic CNN model of similar model complexity in three benchmarking datasets (MNIST, Fashion MNIST and CIFAR-10). Although SSL and deep learning (DL) have some high-level concept in common, they are fundamentally different in model formulation, the training process and training complexity. Extensive discussion on the comparison of SSL and DL is made to provide further insights into the potential of SSL.
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。