• Home
  • Search
  • Self-Supervised Pretraining With Monocular Height Estimation for Semantic Segmentation
  • Cite Icon7
  • https://doi.org/10.1109/tgrs.2024.3412629Copy DOI Icon

Self-Supervised Pretraining With Monocular Height Estimation for Semantic Segmentation

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

Monocular height estimation (MHE) is key for generating 3-D city models, essential for swift disaster response. Moving beyond the traditional focus on performance enhancement, our study breaks new ground by probing the interpretability of MHE networks. We have pioneeringly discovered that neurons within MHE models demonstrate selectivity for both height and semantic classes. This insight sheds light on the complex inner workings of MHE models and inspires innovative strategies for leveraging elevation data more effectively. Informed by this insight, we propose a pioneering framework that employs MHE as a self-supervised pretraining method for remote sensing (RS) imagery. This approach significantly enhances the performance of semantic segmentation tasks. Furthermore, we develop a disentangled latent transformer (DLT) module that leverages explainable deep representations from pretrained MHE networks for unsupervised semantic segmentation. Our method demonstrates the significant potential of MHE tasks in developing foundation models for sophisticated pixel-level semantic analyses. Additionally, we present a new dataset designed to benchmark the performance of both semantic segmentation and height estimation tasks. The dataset and code will be publicly available at <uri xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">https://github.com/zhu-xlab/DLT-MHE.pytorch</uri> .

Similar Papers
  • Research Article
  • Citations22

Comprehensive visual information acquisition for tomato picking robot based on multitask convolutional neural network

  • Jan 06, 2024
  • Biosystems Engineering
  • Xiaoqiang Du +6
  • Conference Article
  • Citations141

Multi-Scale Multi-Task FCN for Semantic Page Segmentation and Table Detection

  • Nov 01, 2017
  • Dafang He +4
  • Research Article

MPSS: A Model Pruning Method for Semantic Image Segmentation Networks

  • Jan 01, 2026
  • IEEE Transactions on Multimedia
  • Yeqiang Qian +3
  • Conference Article
  • Citations57

Learning to Relate Depth and Semantics for Unsupervised Domain Adaptation

  • Jun 01, 2021
  • Suman Saha +6
  • Book Chapter
  • Citations46

Chapter 12 - Semantic scene segmentation for robotics

  • Jan 01, 2022
  • Deep Learning for Robot Perception and Cognition
  • Juana Valeria Hurtado +1
  • PDF
  • Research Article
  • Citations37

A Dynamic Effective Class Balanced Approach for Remote Sensing Imagery Semantic Segmentation of Imbalanced Data

  • Mar 25, 2023
  • Remote Sensing
  • Zheng Zhou +6
  • Research Article
  • Citations10

A Novel Semantic Segmentation Algorithm for RGB-D Images Based on Non-Symmetry and Anti-Packing Pattern Representation Model

  • Jan 01, 2023
  • IEEE Access
  • Yunping Zheng +5
  • 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
  • PDF
  • Research Article
  • Citations15

MFTSC: A Semantically Constrained Method for Urban Building Height Estimation Using Multiple Source Images

  • Nov 29, 2023
  • Remote Sensing
  • Yuhan Chen +2
  • Research Article
  • Citations16

A Semantic Change Detection Network Based on Boundary Detection and Task Interaction for High-Resolution Remote Sensing Images.

  • Sep 01, 2025
  • IEEE transactions on neural networks and learning systems
  • Yingjie Tang +5
  • Research Article
  • Citations4

A Unified Architecture of Semantic Segmentation and Hierarchical Generative Adversarial Networks for Expression Manipulation

  • Jan 01, 2022
  • SSRN Electronic Journal
  • Rumeysa Bodur +2
  • PDF
  • Research Article
  • Citations6

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

  • Mar 24, 2017
  • PLOS ONE
  • Kai Qiao +4
  • PDF
  • Research Article
  • Citations5

Multi-Resolution Learning and Semantic Edge Enhancement for Super-Resolution Semantic Segmentation of Urban Scene Images.

  • Jul 12, 2024
  • Sensors (Basel, Switzerland)
  • Ruijun Shu +1
  • Research Article
  • Citations44

Background-Aware 3-D Point Cloud Segmentation With Dynamic Point Feature Aggregation

  • Jan 01, 2022
  • IEEE Transactions on Geoscience and Remote Sensing
  • Jiajing Chen +2
  • Research Article
  • Citations2

TSINet: A Semantic and Instance Segmentation Network for 3D Tomato Plant Point Clouds

  • Jul 29, 2025
  • Applied Sciences
  • Shanshan Ma +2
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.