BriefGPT.xyz
Oct, 2023
基于图像级标签的弱监督语义分割:从传统模型到基础模型
Weakly-Supervised Semantic Segmentation with Image-Level Labels: from Traditional Models to Foundation Models
HTML
PDF
Zhaozheng Chen, Qianru Sun
TL;DR
基于图像级标签的弱监督语义分割是有效的避免昂贵标注的解决方案。本文首先对传统方法进行全面调研,然后研究了在弱监督语义分割中视觉基础模型(如SAM)的适用性和挑战,为该研究领域的未来发展提供了深入的见解。
Abstract
The rapid development of
deep learning
has driven significant progress in the field of
image semantic segmentation
- a fundamental task in computer vision. Semantic segmentation algorithms often depend on the ava
→