BriefGPT.xyz
Apr, 2019
解缠表示的领域无关学习
Domain Agnostic Learning with Disentangled Representations
HTML
PDF
Xingchao Peng, Zijun Huang, Ximeng Sun, Kate Saenko
TL;DR
本文提出了领域无关学习(DAL)任务,旨在解决如何将来自标记源域的知识转移到任意目标域的未标记数据的问题。通过开发一种能够从类别标识中分离出特定于领域的特征的新型深度对抗去耦自编码器(DADA),我们实验性地证明在未知目标域标签的情况下,DADA在多个图像分类数据集上实现了最先进的性能。
Abstract
unsupervised model transfer
has the potential to greatly improve the
generalizability
of
deep models
to novel domains. Yet the current lit
→