BriefGPT.xyz
Mar, 2020
标签驱动的域自适应语义分割重建
Label-Driven Reconstruction for Domain Adaptation in Semantic Segmentation
HTML
PDF
Jinyu Yang, Weizhi An, Sheng Wang, Xinliang Zhu, Chaochao Yan...
TL;DR
该研究提出了一种新的框架来缓解图像翻译偏差问题并将不同领域的特征对齐,该框架通过对目标到源的翻译和从预测标签中重构源和目标图像来实现。实验结果表明,该方法在从合成到真实的城市场景理解中具有良好的效果。
Abstract
unsupervised domain adaptation
enables to alleviate the need for pixel-wise annotation in the
semantic segmentation
. One of the most common strategies is to translate images from the source domain to the target d
→