Focus+Context Semantic Representation in Scene Segmentation

WU L; ZHANG Xin-yue; TANG Mo; WANG Zi; WANG Yong-an

doi:10.12263/DZXB.20200161

您当前的位置：

首页 >

文章列表页 >

Focus+Context Semantic Representation in Scene Segmentation

更新时间：2025-12-08

- Focus+Context Semantic Representation in Scene Segmentation
- Acta Electronica Sinica Vol. 49, Issue 3, Pages: 596-604(2021)
- 作者机构：
  
  1. 武汉理工大学宽带无线通信与传感器网络湖北省重点实验室,湖北,武汉,430070
  2. 武汉大学资源与环境科学学院,湖北,武汉,430079
  3. 中国人民解放军 95028 部队,湖北,武汉,430070
  4. 中国电子科技集团公司第五十四研究所,河北,石家庄,050081
  5. 武汉理工大学宽带无线通信与传感器网络湖北省重点实验室,湖北,武汉,430070
  6. 武汉大学资源与环境科学学院,湖北,武汉,430079
  7. 中国人民解放军 95028 部队,湖北,武汉,430070
  8. 中国电子科技集团公司第五十四研究所,河北,石家庄,050081
- 作者简介：
- 基金信息：
  
  13th Five-year Plan National Key Research and Development Program of China (No.2017YFB0503500)
- DOI：10.12263/DZXB.20200161
  CLC： TP391.7
- Published Online：25 March 2021，
  
  Published：2021
- 稿件说明：
移动端阅览
WU L, ZHANG Xin-yue, TANG Mo, et al. Focus+Context Semantic Representation in Scene Segmentation[J]. Acta Electronica Sinica, 2021, 49(3): 596-604.
DOI：

WU L, ZHANG Xin-yue, TANG Mo, et al. Focus+Context Semantic Representation in Scene Segmentation[J]. Acta Electronica Sinica, 2021, 49(3): 596-604. DOI： 10.12263/DZXB.20200161.

摘要

场景图像分割一直是机器视觉学习中较为复杂的重难点问题.本文在机器视觉注意力机制学习方法的基础上，融合人类对事物个体的认知，提出场景对象的Focus+Context语义表征，将对象类别信息带入图像底层特征学习中，运用概率统计理论，在抽象层上建模局部区域对象，再联合上下文语义信息推理全局与局部区域对象之间的关系，以实现类内焦点对象（Focus）突出的场景语义分割.实验验证，基于Focus+Context的语义表征和建模能够增加对象的识别率，尤其是在小样本环境下，所提出的方法能极大地简化场景的理解.

Abstract

Scene segmentation has always been a key and complicated problem in machine learning. In order to understand the scene and recognize the objects more accurately

this paper adopts human attention mechanism

takes the category semantic information into consideration and merges it into the image feature learning. The Focus+Context semantic representation is proposed

where the context describes the relationship between the focus and different objects in the scene

and the focus shared among the same category are composed of similar clusters. The probabilistic topic model is used to compute the local features as well as their semantic information. The experimental results show that the Focus+Context method increases the recognition rate of the scene objects

and specially

the proposed method

in a local and global understanding way

can simplify the scene recognition greatly under a small sample size.

关键词

Keywords

references

Views

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

SLDA-TC: A Novel Text Categorization Approach Based on Supervised Topic Model

(Aspect,Rating) Summarization Based on Topic Model

Latent Topic Fusion-Based Cross-Media Image Semantic Annotation

Document Clustering Based on Probabilistic Topic Model

Tr-SLDA: A Transfer Topic Model for Cross-Domains

Related Author

LU Ming-yu

SONG Ying-jie

YU Li-ping

DOU Quan-sheng

TANG Huan-ling

WANG Xing

Uuml

Related Institution

Information Science and Technology College Dalian Maritime University Dalian Liaoning China

Key Laboratory of Intelligent Information Processing in Universities of Shandong(Shandong Technology and Business University) Shandong Yantai China

innovation Center of Shandong Colleges and Universities:Future Intelligent Computing Yantai Shandong China

School of Computer Science and Technology Shandong Technology and Business University Yantai Shandong China

Information Science and Technology College, Dalian Maritime University

⁰