• Home
  • Search
  • The Effect of Input Size in Deep Learning Semantic Segmentation
  • Cite Icon1
  • https://doi.org/10.1109/etcm56276.2022.9935713Copy DOI Icon

The Effect of Input Size in Deep Learning Semantic Segmentation

  • Oct 11, 2022
  • Esther Parra-Mora +2 more
Show More
  • Abstract
  • Literature Map
  • References
  • Citations
  • Similar Papers
Abstract

Over the last few years, fully convolutional networks (FCN) methods have been broadly applied to image and video semantic segmentation tasks becoming the state of the art. In the medical area, FCNs have been evaluated for lesion and structures localization and segmentation. With the improvement of acquisition devices, the resolution and size of the images have increased. Usually, deep and large architectures produce the best results but requires large amount of computation for the training process. Amount of memory required to load large images can be a restriction. In this study, we investigated the impact of resizing images for training procedure. Generally, better results are obtained when the FCNs are trained with the original image size, however, our experiments showed that the same performance can be achieved by training the models with smaller images and increasing the size of the predicted mask, instead of inferring the mask by feeding larger images to the network.

Similar Papers
  • Research Article
  • Citations6

Advancements in UAV image semantic segmentation: A comprehensive literature review

  • Mar 11, 2024
  • Multidisciplinary Reviews
  • Shouket A Ahmed +8
  • Conference Article
  • Citations9

Deep Semantic Segmentation Neural Networks of Railway Scene

  • Jul 01, 2018
  • Zhengwei He +4
  • Research Article
  • Citations7

Research on defect pattern recognition of Light Guide Plate based on Deep Learning semantic Segmentation

  • Apr 01, 2021
  • Journal of Physics: Conference Series
  • Linlin Liu +2
  • PDF
  • Research Article
  • Citations25

FCN-Based Carrier Signal Detection in Broadband Power Spectrum

  • Jan 01, 2020
  • IEEE Access
  • Hao Huang +3
  • PDF
  • Research Article
  • Citations32

A Semantic Segmentation Algorithm Using FCN with Combination of BSLIC

  • Mar 26, 2018
  • Applied Sciences
  • Wei Zhao +4
  • Preprint Article
  • Citations116

Deep learning and its application to medical image segmentation

  • Mar 23, 2018
  • Holger R Roth +6
  • Book Chapter
  • Citations10

GAN and DCN Based Multi-step Supervised Learning for Image Semantic Segmentation

  • Jan 01, 2018
  • Jie Fang +1
  • Conference Article
  • Citations8

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

  • Jul 01, 2019
  • Lichao Mou +2
  • Research Article
  • Citations30

Enhancing Green Fraction Estimation in Rice and Wheat Crops: A Self-Supervised Deep Learning Semantic Segmentation Approach.

  • Jan 01, 2023
  • Plant Phenomics
  • Yangmingrui Gao +8
  • Research Article
  • Citations17

License plate detection based on fully convolutional networks

  • Oct 27, 2017
  • Journal of Electronic Imaging
  • Han Xiang +3
  • Conference Article
  • Citations7

Organ segmentation from full-size CT images using memory-efficient FCN

  • Mar 16, 2020
  • Medical Imaging 2020: Computer-Aided Diagnosis
  • Chenglong Wang +2
  • Research Article
  • Citations3

Self-supervised semantic segmentation of retinal pigment epithelium cells in flatmount fluorescent microscopy images

  • Apr 03, 2023
  • Bioinformatics
  • Hanyi Yu +6
  • Abstract
  • Citations1

Robust Prediction of Isodose Distribution with a Fully Convolutional Networks (FCN)-Based Deep Learning Model

  • Oct 20, 2018
  • International Journal of Radiation Oncology*Biology*Physics
  • P Dong +1
  • PDF
  • Research Article
  • Citations42

Comparing Fully Deep Convolutional Neural Networks for Land Cover Classification with High-Spatial-Resolution Gaofen-2 Images

  • Jul 30, 2020
  • ISPRS International Journal of Geo-Information
  • Zemin Han +7
  • Research Article
  • Citations107

Mapping horizontal and vertical urban densification in Denmark with Landsat time-series from 1985 to 2018: A semantic segmentation solution

  • Sep 21, 2020
  • Remote Sensing of Environment
  • Tzu-Hsin Karen Chen +5
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.