• Home
  • Search
  • Intra- and Inter-Image Causal Intervention for Robust Semantic Segmentation in Remote-Sensing Images
  • Cite Icon1
  • https://doi.org/10.1109/lgrs.2024.3383457Copy DOI Icon

Intra- and Inter-Image Causal Intervention for Robust Semantic Segmentation in Remote-Sensing Images

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

Semantic segmentation in remote-sensing (RS) images is a critical component for advanced RS scene understanding. Traditional methods learn to segment using direct supervision of paired data, yet fall short by not fully addressing the non-causal biases behind RS images. These include intra-image biases like varying background and object appearance, and inter-image biases such as inconsistent geographical environments and class distributions, which can mislead models to infer by relying on these biases. Given the high cost and effort needed for pixel-wise annotation, the limited volume of RS images exacerbates this problem. In this paper, we propose a novel intra- and inter-image causal intervention (I <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">3</sup> -CI) learning paradigm, designed specifically to mitigate the influence of both biases on RS semantic segmentation. Specifically, to reduce the intra-image biases, our I <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">3</sup> -CI utilizes intra-image contrastive learning to promote closer alignment of features from the same category and distancing those of disparate categories in the same image. Consequently, the compact feature space is more robust to the varying appearance. As for eliminating the inter-image level biases, our I <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">3</sup> -CI further explores the inter-image contrastive learning of all pixels within the entire dataset. To overcome the difficulty of learning from all pixels of the dataset simultaneously, our I <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">3</sup> -CI introduces a set of proxy prototype features to keep track of the global centroids for the features of different categories. We substantiate the I <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">3</sup> -CI paradigm’s efficacy through rigorous testing on the LoveDA, Vaihingen, and Potsdam datasets with an average improvement of 0.55% on the mIoU metric, proving the value of causal interventions in achieving robust and accurate semantic segmentation.

Similar Papers
  • PDF
  • Research Article
  • Citations34

Learnable Gated Convolutional Neural Network for Semantic Segmentation in Remote-Sensing Images

  • Aug 17, 2019
  • Remote Sensing
  • Shichen Guo +5
  • Research Article
  • Citations122

Deep-Learning-Based Semantic Segmentation of Remote Sensing Images: A Survey

  • Jan 01, 2024
  • IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
  • Liwei Huang +4
  • Research Article
  • Citations87

Rethinking Transformers for Semantic Segmentation of Remote Sensing Images

  • Jan 01, 2023
  • IEEE Transactions on Geoscience and Remote Sensing
  • Yuheng Liu +3
  • PDF
  • Research Article
  • Citations9

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

  • Apr 26, 2023
  • Remote Sensing
  • Shichen Guo +4
  • PDF
  • Research Article
  • Citations29

Mask2Former with Improved Query for Semantic Segmentation in Remote-Sensing Images

  • Mar 04, 2024
  • Mathematics
  • Shichen Guo +4
  • Research Article

CLIP2RS: Leveraging Pretrained Vision-Language Model for Semantic Segmentation of Remote Sensing Images

  • Jan 01, 2025
  • IEEE Transactions on Geoscience and Remote Sensing
  • Yinghui Xing +5
  • Research Article

Local-Contextual Feature Fusion Network Based on Nonlinear Spiking Neural Model for Semantic Segmentation of Remote Sensing Images.

  • Mar 24, 2026
  • International journal of neural systems
  • Junhao Du +3
  • PDF
  • Research Article
  • Citations3

Active Bidirectional Self-Training Network for Cross-Domain Segmentation in Remote-Sensing Images

  • Jul 08, 2024
  • Remote Sensing
  • Zhujun Yang +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
  • Citations39

SSCNet: A Spectrum-Space Collaborative Network for Semantic Segmentation of Remote Sensing Images

  • Dec 03, 2023
  • Remote Sensing
  • Xin Li +8
  • Research Article
  • Citations3

Semantic Labeling of High-Resolution Images Combining a Self-Cascaded Multimodal Fully Convolution Neural Network with Fully Conditional Random Field

  • Sep 05, 2024
  • Remote Sensing
  • Qiongqiong Hu +3
  • Research Article
  • Citations15

CTMU-Net: An Improved U-Net for Semantic Segmentation of Remote-Sensing Images Based on the Combined Attention Mechanism

  • Jan 01, 2023
  • IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
  • Yuanjun Li +6
  • PDF
  • Research Article
  • Citations13

BiTSRS: A Bi-Decoder Transformer Segmentor for High-Spatial-Resolution Remote Sensing Images

  • Feb 02, 2023
  • Remote Sensing
  • Yuheng Liu +3
  • Research Article
  • Citations4

Onet: Twin U-Net Architecture for Unsupervised Binary Semantic Segmentation in Radar and Remote Sensing Images.

  • Jan 01, 2025
  • IEEE transactions on image processing : a publication of the IEEE Signal Processing Society
  • Yi Zhou +3
  • PDF
  • Research Article
  • Citations5

Semantic Segmentation Network of Remote Sensing Images With Dynamic Loss Fusion Strategy

  • Jan 01, 2021
  • IEEE Access
  • Wenjie Liu +4
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.