%0 Journal Article
%T 基于深度学习的半监督语义分割算法研究<br>Algorithm Research of Deep Learning in Semi-Supervised Semantic Segmentation
%A 李一彤
%A 张长伦
%J Artificial Intelligence and Robotics Research
%P 328-339
%@ 2326-3423
%D 2023
%I Hans Publishing
%R 10.12677/AIRR.2023.124036
%X 语义分割是计算机视觉中最具挑战性的任务之一。然而，在许多应用中，由于像素级标记的高成本，缺乏标记图像是一个常见的问题。这极大地阻碍了在一些注释大量图像成本高甚至不可行的领域的广泛应用。为了缓解这一问题，半监督语义分割被提出并受到广泛的关注，其中标记图像和未标记图像都被充分利用。本文首先介绍语义分割技术并引入半监督语义分割，然后对深度学习在半监督语义分割中的常用方法分类，随后重点对每种方法及其经典网络结构详细介绍并进行优劣对比，对现有的方法提出了几种可行的改进策略，最后对未来发展进行总结与展望。<br />
Semantic segmentation is one of the most challenging tasks in computer vision. However, lack of marked images is a common problem in many applications due to the high cost of pixel-level marking. This greatly hinders widespread application in some fields where annotating large numbers of images is costly or even unfeasible. In order to alleviate this problem, semi-supervised semantic segmentation has been proposed and received widespread attention, in which both labeled and unlabeled images are fully utilized. This paper first introduces semantic segmentation technology and introduces semi-supervised semantic segmentation, then classifies common methods of deep learning in semi-supervised semantic segmentation, then focuses on each method and its classical network structure in detail and compares its advantages and disadvantages, puts forward several feasible improvement strategies for existing methods, and finally summarizes and looks forward to the future development.
%K 深度学习，语义分割，半监督学习<br>Deep Learning
%K Semantic Segmentation
%K Semi-Supervised Learning
%U http://www.hanspub.org/journal/PaperInformation.aspx?PaperID=75800