• Home
  • Search
  • FALSE: False Negative Samples Aware Contrastive Learning for Semantic Segmentation of High-Resolution Remote Sensing Image
  • Cite Icon27
  • https://doi.org/10.1109/lgrs.2022.3222836Copy DOI Icon

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

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

Self-supervised contrastive learning (SSCL) is a potential learning paradigm for learning remote sensing image (RSI)-invariant features through the label-free method. The existing SSCL of RSI is built based on constructing positive and negative sample pairs. However, due to the richness of RSI ground objects and the complexity of the RSI contextual semantics, the same RSI patches have the coexistence and imbalance of positive and negative samples, which causing the SSCL pushing negative samples far away while pushing positive samples far away, and vice versa. We call this the sample confounding issue (SCI). To solve this problem, we propose a False negAtive sampLes aware contraStive lEarning model (FALSE) for the semantic segmentation of high-resolution RSIs. Since the SSCL pretraining is unsupervised, the lack of definable criteria for false negative sample (FNS) leads to theoretical undecidability, we designed two steps to implement the FNS approximation determination: coarse determination of FNS and precise calibration of FNS. We achieve coarse determination of FNS by the FNS self-determination (FNSD) strategy and achieve calibration of FNS by the FNS confidence calibration (FNCC) loss function. Experimental results on three RSI semantic segmentation datasets demonstrated that the FALSE effectively improves the accuracy of the downstream RSI semantic segmentation task compared with the current three models, which represent three different types of SSCL models. The mean Intersection-over-Union on ISPRS Potsdam dataset is improved by 0.7% on average; on CVPR DGLC dataset is improved by 12.28% on average; and on Xiangtan dataset this is improved by 1.17% on average. This indicates that the SSCL model has the ability to self-differentiate FNS and that the FALSE effectively mitigates the SCI in self-supervised contrastive learning.

Similar Papers
  • Research Article
  • Citations1

Contrastive Masked Feature Modeling for Self-Supervised Representation Learning of High-Resolution Remote Sensing Images

  • Feb 17, 2026
  • Remote Sensing
  • Shiyan Pang +4
  • PDF
  • Research Article
  • Citations3

HAVANA: Hard Negative Sample-Aware Self-Supervised Contrastive Learning for Airborne Laser Scanning Point Cloud Semantic Segmentation

  • Jan 26, 2024
  • Remote Sensing
  • Yunsheng Zhang +5
  • PDF
  • Research Article

Research on positive and negative sample sampling strategies in contrastive learning

  • Nov 08, 2024
  • Applied and Computational Engineering
  • Wenyi Liu
  • Research Article
  • Citations21

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

  • Jan 01, 2023
  • IEEE Transactions on Geoscience and Remote Sensing
  • Zhaoyang Zhang +5
  • Research Article

VGCL-DNSO: a graph contrastive learning method for identifying hidden faults under strong noise interference

  • Feb 18, 2026
  • Structural Health Monitoring
  • Haiyang Pan +5
  • 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
  • Research Article
  • Citations12

Self-supervised dual-head attentional bootstrap learning network for prostate cancer screening in transrectal ultrasound images

  • Aug 12, 2023
  • Computers in Biology and Medicine
  • Xu Lu +6
  • PDF
  • Research Article
  • Citations74

Self-Supervised Learning for Scene Classification in Remote Sensing: Current State of the Art and Perspectives

  • Aug 17, 2022
  • Remote Sensing
  • Paul Berg +2
  • Conference Article
  • Citations63

Solving Inefficiency of Self-supervised Representation Learning

  • Oct 01, 2021
  • Guangrun Wang +4
  • Research Article
  • Citations94

CMID: A Unified Self-Supervised Learning Framework for Remote Sensing Image Understanding

  • Jan 01, 2023
  • IEEE Transactions on Geoscience and Remote Sensing
  • Dilxat Muhtar +4
  • Book Chapter
  • Citations5

Improving Self-supervised Lightweight Model Learning via Hard-Aware Metric Distillation

  • Jan 01, 2022
  • Hao Liu +1
  • PDF
  • Research Article

Advancements in Self-Supervised Learning for Remote Sensing Scene Classification: Present Innovations and Future Outlooks

  • Apr 23, 2024
  • Journal of Artificial Intelligence General science (JAIGS) ISSN 3006-4023
  • José Gabriel Carrasco Ramírez
  • PDF
  • Research Article
  • Citations1

Advancements in Self-Supervised Learning for Remote Sensing Scene Classification: Present Innovations and Future Outlooks

  • Apr 23, 2024
  • Journal of Artificial Intelligence General science (JAIGS) ISSN 3006-4023
  • José Gabriel Carrasco Ramírez
  • Research Article
  • Citations3

Frequency-Masked Embedding Inference: A Non-Contrastive Approach for Time Series Representation Learning

  • Apr 11, 2025
  • Proceedings of the AAAI Conference on Artificial Intelligence
  • En Fu +1
  • Book Chapter

A Regularization-Based Positive and Unlabeled Learning Algorithm for One-Class Classification of Remote Sensing Data

  • Jan 01, 2021
  • Yan Zhang +2
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.