BriefGPT.xyz
Jun, 2017
非线性嵌入变换在无监督领域自适应中的应用
Nonlinear Embedding Transform for Unsupervised Domain Adaptation
HTML
PDF
Hemanth Venkateswara, Shayok Chakraborty, Sethuraman Panchanathan
TL;DR
本文提出了一种非线性嵌入变换（NET）算法，它将领域对齐和基于相似度的嵌入结合在一起，在多个视觉数据集上进行全面评估，证明了NET算法在无监督域适应中优于现有竞争的程序。
Abstract
The problem of
domain adaptation
(DA) deals with adapting classifier models trained on one data distribution to different data distributions. In this paper, we introduce the
nonlinear embedding transform
(NET) fo
→