BriefGPT.xyz
Jul, 2020
类别重要性:一种细粒度对抗方法用于跨域语义分割
Classes Matter: A Fine-grained Adversarial Approach to Cross-domain Semantic Segmentation
HTML
PDF
Haoran Wang, Tong Shen, Wei Zhang, Lingyu Duan, Tao Mei
TL;DR
该研究提出了一种基于精细级别对抗学习的策略,用于解决目标域内的类别级别特征对齐问题,从而提高语义分割模型在实际场景下的性能。
Abstract
Despite great progress in supervised
semantic segmentation
,a large performance drop is usually observed when deploying the model in the wild.
domain adaptation
methods tackle the issue by aligning the source doma
→