• Home
  • Search
  • A unified deep learning framework for segmentation in remote sensing imagery
  • https://doi.org/10.1007/s10791-025-09774-0Copy DOI Icon

A unified deep learning framework for segmentation in remote sensing imagery

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

Deep learning-based segmentation models have gained significant focus in various computer vision applications, including remote sensing and medical imaging. There exist deep learning architectures for semantic and instance segmentation separately, with limitations prevailing like imprecise boundary delineation, poor spatial consistency, improper fine-grained object separation, and inaccurate instance segmentation, particularly while handling intricate object structures in remote sensing images. To mitigate the aforementioned issues, in the present work, we propose a unified deep framework that integrates both semantic and instance segmentation within a single architecture tailored for high-resolution RSIs. Our framework combines an Improved Attention Residual MobileNetV2 U-Net (IARUMV2) for pixel-level semantic segmentation and Dynamic Mask R-CNN for instance-level segmentation. To further refine spatial coherence and boundary delineation, we incorporate the post-processing technique like Conditional Random Fields (CRF) on the output segmentation map of enhanced U-Net to improve spatial consistency and edge sharpness. This refined semantic mask serves as input to the Dynamic Mask R-CNN model for instance segmentation, where the Graph-based Refinement Module (GRM) is employed to improve boundary accuracy by leveraging graph-based smoothing techniques. Our approach ensures improved object delineation, increases the segmentation accuracy, and decreases false positives compared to conventional deep learning architectures. Evaluation outcomes on standard datasets illustrate that the proposed approach attains superior performance, highlighting its effectiveness in both semantic and instance segmentation tasks. The results validate the effectiveness of jointly modeling semantic and instance-level information, providing a more comprehensive understanding of complex remote sensing scenes.

Similar Papers
  • Research Article

A Unified Deep Architecture for Segmentation in Remote Sensing Images

  • Jan 01, 2025
  • Applied Computational Intelligence and Soft Computing
  • Nagamani Gonthina +1
  • Conference Article
  • Citations7

Learning Panoptic Segmentation from Instance Contours

  • May 30, 2021
  • Sumanth Chennupati +4
  • Research Article
  • Citations9

HCFS3D: Hierarchical coupled feature selection network for 3D semantic and instance segmentation

  • Mar 03, 2021
  • Image and Vision Computing
  • Jingang Tan +5
  • Research Article
  • Citations66

PST: Plant segmentation transformer for 3D point clouds of rapeseed plants at the podding stage

  • Dec 19, 2022
  • ISPRS Journal of Photogrammetry and Remote Sensing
  • Ruiming Du +4
  • Research Article
  • Citations6

Learning panoptic segmentation through feature discriminability

  • Aug 18, 2021
  • Pattern Recognition
  • Tao Chu +2
  • Research Article
  • Citations85

CLoDSA: a tool for augmentation in classification, localization, detection, semantic segmentation and instance segmentation tasks

  • Jun 13, 2019
  • BMC Bioinformatics
  • Ángela Casado-García +6
  • Book Chapter
  • Citations80

3D Bird’s-Eye-View Instance Segmentation

  • Jan 01, 2019
  • Cathrin Elich +3
  • Book Chapter
  • Citations3

Low-Complexity Scene Understanding Network

  • Jan 01, 2019
  • Livia Iordache +5
  • Research Article
  • Citations9

Detection of karst depression in Brazil comparing different semantic and instance segmentations and global digital elevation models

  • Apr 22, 2024
  • Geomorphology
  • Heitor Da Rocha Nunes De Castro +4
  • Research Article
  • Citations1

CTFS: A consolidated transformer framework for instance and semantic segmentation tasks.

  • Nov 01, 2025
  • Neural networks : the official journal of the International Neural Network Society
  • Kun Dai +7
  • Research Article

Deep learning-based 3D morphological segmentation and quantitative growth analysis of field-grown cabbage across the full cycle.

  • Jun 01, 2026
  • Plant phenomics (Washington, D.C.)
  • Hongda Li +4
  • Research Article

高层语义分析中的模型蒸馏方法综述

  • Jan 01, 2023
  • Journal of Image and Graphics
  • Sun Ruoyu +1
  • Conference Article
  • Citations42

CF-SIS: Semantic-Instance Segmentation of 3D Point Clouds by Context Fusion with Self-Attention

  • Oct 12, 2020
  • Xin Wen +3
  • Conference Article

Joint Point Clouds Semantic and Instance Segmentation by Local Aggregation and Clustering

  • May 19, 2023
  • Yun Bai +4
  • Book Chapter
  • Citations2

Fast Single Shot Instance Segmentation

  • Jan 01, 2019
  • Zuoxin Li +2
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.