BriefGPT.xyz
Apr, 2020
FDA: 用于语义分割的傅里叶域自适应
FDA: Fourier Domain Adaptation for Semantic Segmentation
HTML
PDF
Yanchao Yang, Stefano Soatto
TL;DR
本论文描述了一种简单的无监督领域适应方法，通过交换低频谱来减少源和目标分布之间的差异，该方法在语义分割中实现了最新的性能，并且不需要对离散领域选择变量进行不变的神经网络背骨的敌对优化。
Abstract
We describe a simple method for
unsupervised domain adaptation
, whereby the discrepancy between the source and target distributions is reduced by swapping the
low-frequency spectrum
of one with the other. We illu
→