BriefGPT.xyz
Aug, 2019
一种非对抗式方法构建自主金字塔课程以进行跨领域语义分割
Constructing Self-motivated Pyramid Curriculums for Cross-Domain Semantic Segmentation: A Non-Adversarial Approach
HTML
PDF
Qing Lian, Fengmao Lv, Lixin Duan, Boqing Gong
TL;DR
该研究提出了一种名为PyCDA的自我激励金字塔课程域自适应方法,用于将语义分割神经网络从合成源领域适应到真实目标领域中, 并在无监督域适应语义分割中得到了最先进的结果。
Abstract
We propose a new approach, called self-motivated pyramid
curriculum domain adaptation
(
pycda
), to facilitate the adaptation of
semantic segmentat
→