• Home
  • Search
  • Synthesizing Training Images for Semantic Segmentation
  • Cite Icon3
  • https://doi.org/10.1007/978-981-13-1702-6_22Copy DOI Icon

Synthesizing Training Images for Semantic Segmentation

  • Jan 1, 2018
  • Yunhui Zhang +3 more
Show More
  • Abstract
  • Literature Map
  • References
  • Citations
  • Similar Papers
Abstract

Semantic segmentation is one of the key problems in the computer vision area. Recently, Convolutional Neural Networks (CNNs) have yielded a significant performance for the semantic segmentation task. However, CNNs require a sufficient amount of annotated training images, which is challenging since massive human labour is needed. In this paper, we propose to use 3D models to automatically generate synthetic images with pixel-level annotations. We take advantage of 3D models to generate synthetic images of high diversity in object appearance and background clutterness, by randomly sampling rendering parameters and adding random background patterns. Then, we use the synthetic images to augment training samples for semantic segmentation by combining with publicly available real-world images. Experimental results demonstrate that CNNs trained with our synthetic images improve performance on the semantic segmentation task in the PASCAL VOC 2012 dataset.

Similar Papers
  • PDF
  • Research Article
  • Citations10

Co-Training for Unsupervised Domain Adaptation of Semantic Segmentation Models

  • Jan 05, 2023
  • Sensors (Basel, Switzerland)
  • Jose L Gómez +2
  • Conference Article
  • Citations7

Learning Panoptic Segmentation from Instance Contours

  • May 30, 2021
  • Sumanth Chennupati +4
  • Conference Article
  • Citations8

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

  • Jul 01, 2019
  • Lichao Mou +2
  • Research Article
  • Citations5

Leveraging CAM Algorithms for Explaining Medical Semantic Segmentation

  • Oct 01, 2024
  • Machine Learning for Biomedical Imaging
  • Tillmann Rheude +3
  • Research Article
  • Citations31

HAFormer: Unleashing the Power of Hierarchy-Aware Features for Lightweight Semantic Segmentation.

  • Jan 01, 2024
  • IEEE transactions on image processing : a publication of the IEEE Signal Processing Society
  • Guoan Xu +4
  • Conference Article
  • Citations8

Airplane Recognition from Remote Sensing Images with Deep Convolutional Neural Network

  • Sep 26, 2020
  • Fen Chen +3
  • Research Article
  • Citations15

Nonlocal regularized CNN for image segmentation

  • Jan 01, 2020
  • Inverse Problems & Imaging
  • Fan Jia +2
  • Book Chapter
  • Citations44

Chapter 12 - Semantic scene segmentation for robotics

  • Jan 01, 2022
  • Deep Learning for Robot Perception and Cognition
  • Juana Valeria Hurtado +1
  • PDF
  • Research Article
  • Citations1

Point Cloud Convolution Network Based on Spatial Location Correspondence

  • Nov 25, 2022
  • ISPRS International Journal of Geo-Information
  • Jiabin Xv +2
  • PDF
  • Research Article
  • Citations13

A Road Crack Segmentation Method Based on Transformer and Multi-Scale Feature Fusion

  • Jun 08, 2024
  • Electronics
  • Yang Xu +4
  • Research Article
  • Citations2

Geodl: An R package for geospatial deep learning semantic segmentation using torch and terra.

  • Dec 05, 2024
  • PloS one
  • Aaron E Maxwell +3
  • Conference Article
  • Citations27

Continual Learning for Class- and Domain-Incremental Semantic Segmentation

  • Jul 11, 2021
  • Tobias Kalb +3
  • Research Article
  • Citations6

Advancements in UAV image semantic segmentation: A comprehensive literature review

  • Mar 11, 2024
  • Multidisciplinary Reviews
  • Shouket A Ahmed +8
  • Book Chapter
  • Citations51

When CNN Meet with ViT: Towards Semi-supervised Learning for Multi-class Medical Image Semantic Segmentation

  • Jan 01, 2023
  • Ziyang Wang +3
  • Supplementary Content

WITHDRAWN: Instance Segmentation of Burn Areas Using Position-Sensitive Convolutional Networks

  • Aug 28, 2025
  • Research Square
  • Neha Patel +3
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.