• Home
  • Search
  • Evidential fully convolutional network for semantic segmentation
  • Open Access IconOpen Access
  • Cite Icon53
  • https://doi.org/10.1007/s10489-021-02327-0Copy DOI Icon

Evidential fully convolutional network for semantic segmentation

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

We propose a hybrid architecture composed of a fully convolutional network (FCN) and a Dempster-Shafer layer for image semantic segmentation. In the so-called evidential FCN (E-FCN), an encoder-decoder architecture first extracts pixel-wise feature maps from an input image. A Dempster-Shafer layer then computes mass functions at each pixel location based on distances to prototypes. Finally, a utility layer performs semantic segmentation from mass functions and allows for imprecise classification of ambiguous pixels and outliers. We propose an end-to-end learning strategy for jointly updating the network parameters, which can make use of soft (imprecise) labels. Experiments using three databases (Pascal VOC 2011, MIT-scene Parsing and SIFT Flow) show that the proposed combination improves the accuracy and calibration of semantic segmentation by assigning confusing pixels to multi-class sets.

Similar Papers
  • PDF
  • Research Article
  • Citations46

Parallel Fully Convolutional Network for Semantic Segmentation

  • Dec 30, 2020
  • IEEE Access
  • Jian Ji +5
  • Book Chapter
  • Citations11

Filter-Wise Pruning Approach to FPGA Implementation of Fully Convolutional Network for Semantic Segmentation

  • Jan 01, 2019
  • Masayuki Shimoda +2
  • Research Article
  • Citations134

Multi-scale deep context convolutional neural networks for semantic segmentation

  • Apr 19, 2018
  • World Wide Web
  • Quan Zhou +6
  • Conference Article
  • Citations225

A Relation-Augmented Fully Convolutional Network for Semantic Segmentation in Aerial Scenes

  • Jun 01, 2019
  • Lichao Mou +2
  • Research Article
  • Citations323

Fully Convolutional Networks for Semantic Segmentation of Very High Resolution Remotely Sensed Images Combined With DSM

  • Mar 01, 2018
  • IEEE Geoscience and Remote Sensing Letters
  • Weiwei Sun +1
  • PDF
  • Research Article
  • Citations11

DTS-Net: Depth-to-Space Networks for Fast and Accurate Semantic Object Segmentation

  • Jan 03, 2022
  • Sensors (Basel, Switzerland)
  • Hatem Ibrahem +2
  • Conference Article
  • Citations40716

Fully convolutional networks for semantic segmentation

  • Jun 01, 2015
  • Jonathan Long +2
  • Research Article
  • Citations11804

Fully Convolutional Networks for Semantic Segmentation

  • May 24, 2016
  • IEEE Transactions on Pattern Analysis and Machine Intelligence
  • Evan Shelhamer +2
  • Research Article

HSTNet: An Iterative Optimization Network for Semantic Segmentation of High-Resolution Remote Sensing Images

  • Mar 27, 2024
  • International Journal of Scientific Engineering and Research
  • Tingkai Wang
  • Research Article
  • Citations1

Semantic Segmentation of 3D Point Clouds in Outdoor Environments Based on Local Dual-Enhancement

  • Feb 22, 2024
  • Applied Sciences
  • Kai Zhang +3
  • Conference Article
  • Citations1292

ScribbleSup: Scribble-Supervised Convolutional Networks for Semantic Segmentation

  • Jun 01, 2016
  • Di Lin +4
  • Conference Article
  • Citations1

Spatially bound categorical attention network for semantic segmentation

  • Feb 16, 2022
  • Wei Li +4
  • Conference Article
  • Citations8

CYLINDRICAL TRANSFORM: 3D SEMANTIC SEGMENTATION OF KIDNEYS WITH LIMITED ANNOTATED IMAGES

  • Nov 01, 2018
  • Hojjat Salehinejad +4
  • Conference Article
  • Citations19

Semantic Segmentation using Modified U-Net for Autonomous Driving

  • Jun 01, 2022
  • T Sugirtha +1
  • PDF
  • Research Article
  • Citations2

Memory-Augmented 3D Point Cloud Semantic Segmentation Network for Intelligent Mining Shovels

  • Jul 05, 2024
  • Sensors (Basel, Switzerland)
  • Yunhao Cui +6
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.