• Home
  • Search
  • GraSS: Contrastive Learning With Gradient-Guided Sampling Strategy for Remote Sensing Image Semantic Segmentation
  • Open Access IconOpen Access
  • Cite Icon21
  • https://doi.org/10.1109/tgrs.2023.3336285Copy DOI Icon

GraSS: Contrastive Learning With Gradient-Guided Sampling Strategy for Remote Sensing Image Semantic Segmentation

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

Self-supervised contrastive learning (SSCL) has achieved significant milestones in remote sensing image (RSI) understanding. Its essence lies in designing an unsupervised instance discrimination pretext task to extract image features from a large number of unlabeled images that are beneficial for downstream tasks. However, existing instance discrimination based SSCL suffers from two limitations when applied to the RSI semantic segmentation task: 1) Positive sample confounding issue, SSCL treats different augmentations of the same RSI as positive samples, but the richness, complexity, and imbalance of RSI ground objects lead to the model actually pulling a variety of different ground objects closer while pulling positive samples closer, which confuse the feature of different ground objects. 2) Feature adaptation bias, SSCL treats RSI patches containing various ground objects as individual instances for discrimination and obtains instance-level features, which are not fully adapted to pixel-level or object-level semantic segmentation tasks. To address the above limitations, we consider constructing samples containing single ground objects to alleviate positive sample confounding issue, and make the model obtain object-level features from the contrastive between single ground objects. Meanwhile, we observed that the discrimination information can be mapped to specific regions in RSI through the gradient of unsupervised contrastive loss, these specific regions tend to contain single ground objects. Based on this, we propose contrastive learning with Gradient guided Sampling Strategy (GraSS) for RSI semantic segmentation. GraSS consists of two stages: 1) the instance discrimination warm-up stage to provide initial discrimination information to the contrastive loss gradients, 2) the gradient guided sampling contrastive training stage to adaptively construct samples containing more singular ground objects using the discrimination information. Experimental results on three open datasets demonstrate that GraSS effectively enhances the performance of SSCL in high-resolution RSI semantic segmentation. Compared to eight baseline methods from six different types of SSCL, GraSS achieves an average improvement of 1.57% and a maximum improvement of 3.58% in terms of mean intersection over the union. Additionally, we discovered that the unsupervised contrastive loss gradients contain rich feature information, which inspires us to utilize gradient information more extensively during model training to attain additional model capacity. The source code is available at https://github.com/GeoX-Lab/GraSS.

Similar Papers
  • Research Article
  • Citations27

FALSE: False Negative Samples Aware Contrastive Learning for Semantic Segmentation of High-Resolution Remote Sensing Image

  • Jan 01, 2022
  • IEEE Geoscience and Remote Sensing Letters
  • Zhaoyang Zhang +4
  • Research Article
  • Citations174

Global and Local Contrastive Self-Supervised Learning for Semantic Segmentation of HR Remote Sensing Images

  • Jan 01, 2022
  • IEEE Transactions on Geoscience and Remote Sensing
  • Haifeng Li +6
  • PDF
  • Research Article
  • Citations1

CDEST: Class Distinguishability-Enhanced Self-Training Method for Adopting Pre-Trained Models to Downstream Remote Sensing Image Semantic Segmentation

  • Apr 06, 2024
  • Remote Sensing
  • Ming Zhang +7
  • Research Article

Spatial-Frequency Contrastive Learning for Self-Supervised Semantic Segmentation of Remote Sensing Images

  • Jan 01, 2026
  • IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
  • Yujia Fu +3
  • Research Article
  • Citations59

Fine-Scale Urban Informal Settlements Mapping by Fusing Remote Sensing Images and Building Data via a Transformer-Based Multimodal Fusion Network

  • Jan 01, 2022
  • IEEE Transactions on Geoscience and Remote Sensing
  • Runyu Fan +5
  • PDF
  • Research Article
  • Citations45

Deep Learning Methods for Semantic Segmentation in Remote Sensing with Small Data: A Survey

  • Oct 16, 2023
  • Remote Sensing
  • Anzhu Yu +9
  • PDF
  • Research Article
  • Citations9

Dynamic High-Resolution Network for Semantic Segmentation in Remote-Sensing Images

  • Apr 26, 2023
  • Remote Sensing
  • Shichen Guo +4
  • Research Article

A Unified Deep Architecture for Segmentation in Remote Sensing Images

  • Jan 01, 2025
  • Applied Computational Intelligence and Soft Computing
  • Nagamani Gonthina +1
  • Research Article
  • Citations1

SFANet: A Ground Object Spectral Feature Awareness Network for Multimodal Remote Sensing Image Semantic Segmentation

  • May 21, 2025
  • Remote Sensing
  • Yizhou Lan +6
  • Research Article
  • Citations9

Self-Supervised Edge Perceptual Learning Framework for High-Resolution Remote Sensing Images Classification

  • Jul 01, 2024
  • IEEE Transactions on Circuits and Systems for Video Technology
  • Guangfei Li +5
  • PDF
  • Research Article
  • Citations58

SDFCNv2: An Improved FCN Framework for Remote Sensing Images Semantic Segmentation

  • Dec 03, 2021
  • Remote Sensing
  • Guanzhou Chen +7
  • Research Article
  • Citations5

MDSNet: a multiscale decoupled supervision network for semantic segmentation of remote sensing images

  • Jul 27, 2023
  • International Journal of Digital Earth
  • Jiangfan Feng +4
  • Research Article
  • Citations1

Transferable image synthesis for remote sensing semantic segmentation via joint reference-semantic fusion

  • Mar 01, 2026
  • Information Fusion
  • Runmin Dong +8
  • Research Article
  • Citations13

Semantic Segmentation for Remote Sensing based on RGB Images and Lidar Data using Model-Agnostic Meta-Learning and Partical Swarm Optimization

  • Jan 01, 2020
  • IFAC-PapersOnLine
  • Kai Zhang +4
  • PDF
  • Research Article
  • Citations17

ASPP+-LANet: A Multi-Scale Context Extraction Network for Semantic Segmentation of High-Resolution Remote Sensing Images

  • Mar 14, 2024
  • Remote Sensing
  • Lei Hu +3
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.