• Home
  • Search
  • A top-down manner-based DCNN architecture for semantic image segmentation.
  • Cite Icon6
  • https://doi.org/10.1371/journal.pone.0174508Copy DOI Icon

A top-down manner-based DCNN architecture for semantic image segmentation.

Show More
  • Abstract
  • Highlights & Summary
  • PDF
  • Literature Map
  • References
  • Citations
  • Similar Papers
Abstract

Given their powerful feature representation for recognition, deep convolutional neural networks (DCNNs) have been driving rapid advances in high-level computer vision tasks. However, their performance in semantic image segmentation is still not satisfactory. Based on the analysis of visual mechanism, we conclude that DCNNs in a bottom-up manner are not enough, because semantic image segmentation task requires not only recognition but also visual attention capability. In the study, superpixels containing visual attention information are introduced in a top-down manner, and an extensible architecture is proposed to improve the segmentation results of current DCNN-based methods. We employ the current state-of-the-art fully convolutional network (FCN) and FCN with conditional random field (DeepLab-CRF) as baselines to validate our architecture. Experimental results of the PASCAL VOC segmentation task qualitatively show that coarse edges and error segmentation results are well improved. We also quantitatively obtain about 2%-3% intersection over union (IOU) accuracy improvement on the PASCAL VOC 2011 and 2012 test sets.

Loading PDF

Similar Papers
  • Research Article
  • Citations99

A comparative study of pre-trained convolutional neural networks for semantic segmentation of breast tumors in ultrasound

  • Oct 08, 2020
  • Computers in Biology and Medicine
  • Wilfrido Gómez-Flores +1
  • PDF
  • Research Article
  • Citations46

Parallel Fully Convolutional Network for Semantic Segmentation

  • Dec 30, 2020
  • IEEE Access
  • Jian Ji +5
  • Research Article
  • Citations44

Combining max-pooling and wavelet pooling strategies for semantic image segmentation

  • Jun 12, 2021
  • Expert Systems with Applications
  • André De Souza Brito +4
  • Conference Article
  • Citations2

Semantic segmentation with multi-path refinement and pyramid pooling dilated-resnet

  • Sep 01, 2017
  • Zhipeng Cui +5
  • Book Chapter
  • Citations44

Can Ground Truth Label Propagation from Video Help Semantic Segmentation?

  • Jan 01, 2016
  • Siva Karthik Mustikovela +2
  • Conference Article

Image semantic segmentation optimization by Conditional Random Field integrated with object clique potential

  • Jun 01, 2017
  • Jingwei Li +3
  • Research Article
  • Citations6

Semantic segmentation of remote sensing image based on deep fusion networks and conditional random field

  • Jan 01, 2020
  • National Remote Sensing Bulletin
  • Xiao Chunjiao +3
  • PDF
  • Research Article
  • Citations19

Multi-Scale Feature Map Aggregation and Supervised Domain Adaptation of Fully Convolutional Networks for Urban Building Footprint Extraction

  • Jan 13, 2023
  • Remote Sensing
  • Jagannath Aryal +1
  • Conference Article

Self-supervised multi-task learning for semantic segmentation of urban scenes

  • Sep 12, 2021
  • Jonathan Gonzalez-Santiago +2
  • Research Article
  • Citations2

Artificial Intelligence Based Instance-Aware Semantic Lobe Segmentation on Chest Computed Tomography Images

  • Dec 26, 2022
  • European Journal of Science and Technology
  • Beyza Sayraci +2
  • Book Chapter
  • Citations4

3SP-Net: Semantic Segmentation Network with Stereo Image Pairs for Urban Scene Parsing

  • Jan 01, 2018
  • Lingli Zhou +1
  • Research Article
  • Citations5

PreCM: The Padding-Based Rotation Equivariant Convolution Mode for Semantic Segmentation.

  • Jan 01, 2025
  • IEEE transactions on image processing : a publication of the IEEE Signal Processing Society
  • Xinyu Xu +4
  • PDF
  • Research Article
  • Citations74

Remote Sensing Image Semantic Segmentation Based on Edge Information Guidance

  • May 08, 2020
  • Remote Sensing
  • Chu He +4
  • PDF
  • Research Article
  • Citations47

An Efficient Plant Disease Recognition System Using Hybrid Convolutional Neural Networks (CNNs) and Conditional Random Fields (CRFs) for Smart IoT Applications in Agriculture

  • Aug 16, 2022
  • International Journal of Computational Intelligence Systems
  • Nermeen Gamal Rezk +4
  • Research Article
  • Citations72

High-Resolution Aerial Images Semantic Segmentation Using Deep Fully Convolutional Network With Channel Attention Mechanism

  • Sep 01, 2019
  • IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
  • Haifeng Luo +4
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.