BriefGPT.xyz
Mar, 2021
几何无监督域自适应语义分割
Geometric Unsupervised Domain Adaptation for Semantic Segmentation
HTML
PDF
Vitor Guizilini, Jie Li, Rares Ambrus, Adrien Gaidon
TL;DR
该论文提出了使用自监督单目深度估计作为代理任务来解决模拟数据和真实数据之间的差异，以提高半监督领域自适应的性能，结果表明这种方法在语义分割领域的无监督域自适应上具有较好的性能。
Abstract
simulators
can efficiently generate large amounts of labeled
synthetic data
with perfect supervision for hard-to-label tasks like
semantic segmen
→