• Home
  • Search
  • A New Semantic Segmentation Model for Supplementing More Spatial Information
  • Cite Icon11
  • https://doi.org/10.1109/access.2019.2915088Copy DOI Icon

A New Semantic Segmentation Model for Supplementing More Spatial Information

Show More
  • Abstract
  • Literature Map
  • References
  • Citations
  • Similar Papers
Abstract

Semantic segmentation, aiming to assign semantic labels to each pixel, is broadly applied into many fields, such as video surveillance, medical image analysis, and autonomous driving. However, there are two challenges in semantic segmentation task: 1) the deficiency of rich contextual information; and 2) the lack of sufficient spatial information, all of which affect segmentation performance seriously. To solve these two challenges, the global feature capturing module (GFCM) and Conv Block are proposed in this paper to build a new model to improve segmentation performance. Specifically, GFCM, made of the global encoding module (GEM) and spatial attention module (SAM), is designed to extract adequate global contextual information and build global spatial dependencies. Composed of three convolution layers, Conv Block is proposed to preserve rich spatial information. Based on GFCM and Conv Block, a new model is designed, where a data-dependent upsampling operator (DUpsampling) is exploited to recover the pixel-wise prediction effectively. The extensive experiments have been made to prove the effectiveness of the design, and the new model achieves 73.69% mIoU on Cityscapes test set and 80.05% mIoU on PASCAL VOC 2012 test set without any post-processing.

Similar Papers
  • Book Chapter
  • Citations44

Chapter 12 - Semantic scene segmentation for robotics

  • Jan 01, 2022
  • Deep Learning for Robot Perception and Cognition
  • Juana Valeria Hurtado +1
  • Conference Article
  • Citations7

Learning Panoptic Segmentation from Instance Contours

  • May 30, 2021
  • Sumanth Chennupati +4
  • Conference Article
  • Citations27

Continual Learning for Class- and Domain-Incremental Semantic Segmentation

  • Jul 11, 2021
  • Tobias Kalb +3
  • Conference Article
  • Citations51

Improved Noise and Attack Robustness for Semantic Segmentation by Using Multi-Task Training with Self-Supervised Depth Estimation

  • Jun 01, 2020
  • Marvin Klingner +2
  • PDF
  • Research Article
  • Citations29

Cervical Cell Segmentation Method Based on Global Dependency and Local Attention

  • Aug 01, 2022
  • Applied Sciences
  • Gang Li +4
  • Research Article

Art Pattern Design Based on Visual Semantic Segmentation and Evolutionary Algorithm Optimization

  • Nov 11, 2024
  • International Journal of High Speed Electronics and Systems
  • Zhao Qing
  • Research Article
  • Citations3

Co-Seg++: Mutual Prompt-Guided Collaborative Learning for Versatile Medical Segmentation.

  • Jan 01, 2025
  • IEEE transactions on medical imaging
  • Qing Xu +3
  • PDF
  • Research Article
  • Citations39

DCAU-Net: dense convolutional attention U-Net for segmentation of intracranial aneurysm images

  • Mar 28, 2022
  • Visual Computing for Industry, Biomedicine, and Art
  • Wenwen Yuan +4
  • Conference Article
  • Citations32

The Effect of Resnet Model as Feature Extractor Network to Performance of DeepLabV3 Model for Semantic Satellite Image Segmentation

  • Dec 07, 2020
  • Yaya Heryadi +5
  • PDF
  • Research Article
  • Citations5

Multi-Pooling Context Network for Image Semantic Segmentation

  • May 28, 2023
  • Remote Sensing
  • Qing Liu +6
  • Conference Article
  • Citations8

Spatial Relational Reasoning in Networks for Improving Semantic Segmentation of Aerial Images

  • Jul 01, 2019
  • Lichao Mou +2
  • Research Article
  • Citations1

Multi-scale medical image segmentation based on pixel encoding and spatial attention mechanism

  • Jun 25, 2024
  • Sheng wu yi xue gong cheng xue za zhi = Journal of biomedical engineering = Shengwu yixue gongchengxue zazhi
  • Yulong Wan +4
  • Research Article
  • Citations117

BAS$^{4}$Net: Boundary-Aware Semi-Supervised Semantic Segmentation Network for Very High Resolution Remote Sensing Images

  • Jan 01, 2020
  • IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
  • Xian Sun +3
  • Research Article
  • Citations41

GCNet: Grid-like context-aware network for RGB-thermal semantic segmentation

  • Jul 22, 2022
  • Neurocomputing
  • Jinfu Liu +4
  • Research Article
  • Citations1

A Lightweight and Multi-Branch Module in Facial Semantic Segmentation Feature Extraction

  • Jan 01, 2024
  • IEEE Access
  • Yuxuan Li +5
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.