BriefGPT.xyz
Mar, 2019
非对称松弛分布对齐的域自适应
Domain Adaptation with Asymmetrically-Relaxed Distribution Alignment
HTML
PDF
Yifan Wu, Ezra Winston, Divyansh Kaushik, Zachary Lipton
TL;DR
本文提出了一种非对称松弛分布对齐的方法来解决领域适应中标签分布偏移问题，并找到了合理的理论假设条件来支撑该方法，证明了该方法在合成和真实数据集上的实际效果。
Abstract
domain adaptation
addresses the common problem when the
target distribution
generating our test data drifts from the source (training) distribution. While absent assumptions,
→