arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1702.05538stat.MLcs.LG
收藏

特征空间中的数据集扩充

Dataset Augmentation in Feature Space

University of Guelph(圭尔夫大学)

Terrance DeVries, Graham W. Taylor

摘要:

数据集增强是应用广泛的特定领域转换来综合扩展训练集的实践,是监督学习中的标准工具。虽然在视觉识别等任务中很有效,但必须为每个新领域仔细设计、实现和测试转换集,这限制了其重用和通用性。在本文中,我们采用了一种更简单的、与领域无关的方法来增强数据集。我们从现有的数据点开始,并应用简单的转换,例如添加噪声,插值或在它们之间外推。我们的主要见解是不在输入空间中执行转换,而是在学习的特征空间中执行转换。人们对无监督表示学习的兴趣重新燃起,使得这种技术变得及时和有效。这是一个简单的建议,但迄今为止还没有经过经验检验。在序列到序列模型生成的上下文向量空间中工作,我们展示了一种对静态和顺序数据都有效的技术。

英文摘要:

Dataset augmentation, the practice of applying a wide array of domain-specific transformations to synthetically expand a training set, is a standard tool in supervised learning. While effective in tasks such as visual recognition, the set of transformations must be carefully designed, implemented, and tested for every new domain, limiting its re-use and generality. In this paper, we adopt a simpler, domain-agnostic approach to dataset augmentation. We start with existing data points and apply simple transformations such as adding noise, interpolating, or extrapolating between them. Our main insight is to perform the transformation not in input space, but in a learned feature space. A re-kindling of interest in unsupervised representation learning makes this technique timely and more effective. It is a simple proposal, but to-date one that has not been tested empirically. Working in the space of context vectors generated by sequence-to-sequence models, we demonstrate a technique that is effective for both static and sequential data.

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。

↑