论文标题
监督域的适应：图形嵌入透视图和整流的实验协议
Supervised Domain Adaptation: A Graph Embedding Perspective and a Rectified Experimental Protocol
论文作者
论文摘要
域的适应性是减轻来自不同域数据之间分布差距的过程。在本文中，我们表明，使用源和目标域数据之间的成对关系的域适应方法可以作为图形嵌入，其中将域标签纳入了内在和惩罚图的结构中。具体而言，我们分析了三种现有的最新监督域适应方法的损失函数，并证明它们执行图形嵌入。此外，我们重点介绍了与通常用于证明这些方法的少量学习能力的实验设置相关的一些概括和可重复性问题。为了准确评估和比较监督的域适应方法，我们提出了一个纠正的评估协议，并在标准数据集Office31（Amazon，DSLR和网络摄像头），Digits（MNIST，USPS，USPS，SVHN和MNIST和MNIST和MNIST-M）和VISDA（SYNTHETIC，SYNTHETIC，REAL）上报告了更新的基准。
Domain Adaptation is the process of alleviating distribution gaps between data from different domains. In this paper, we show that Domain Adaptation methods using pair-wise relationships between source and target domain data can be formulated as a Graph Embedding in which the domain labels are incorporated into the structure of the intrinsic and penalty graphs. Specifically, we analyse the loss functions of three existing state-of-the-art Supervised Domain Adaptation methods and demonstrate that they perform Graph Embedding. Moreover, we highlight some generalisation and reproducibility issues related to the experimental setup commonly used to demonstrate the few-shot learning capabilities of these methods. To assess and compare Supervised Domain Adaptation methods accurately, we propose a rectified evaluation protocol, and report updated benchmarks on the standard datasets Office31 (Amazon, DSLR, and Webcam), Digits (MNIST, USPS, SVHN, and MNIST-M) and VisDA (Synthetic, Real).
