Remote Sensing Image Change Detection with Transformers

Abstract

Modern change detection (CD) has achieved remarkable success by the powerful discriminative ability of deep convolutions. However, high-resolution remote sensing CD remains challenging due to the complexity of objects in the scene. Objects with the same semantic concept may show distinct spectral characteristics at different times and spatial locations. Most recent CD pipelines using pure convolutions are still struggling to relate long-range concepts in space-time. Non-local self-attention approaches show promising performance via modeling dense relations among pixels, yet are computationally inefficient. Here, we propose a bitemporal image transformer (BIT) to efficiently and effectively model contexts within the spatial-temporal domain. Our intuition is that the high-level concepts of the change of interest can be represented by a few visual words, i.e., semantic tokens. To achieve this, we express the bitemporal image into a few tokens, and use a transformer encoder to model contexts in the compact token-based space-time. The learned context-rich tokens are then feedback to the pixel-space for refining the original features via a transformer decoder. We incorporate BIT in a deep feature differencing-based CD framework. Extensive experiments on three CD datasets demonstrate the effectiveness and efficiency of the proposed method. Notably, our BIT-based model significantly outperforms the purely convolutional baseline using only 3 times lower computational costs and model parameters. Based on a naive backbone (ResNet18) without sophisticated structures (e.g., FPN, UNet), our model surpasses several state-of-the-art CD methods, including better than four recent attention-based methods in terms of efficiency and accuracy. Our code is available at https://github.com/justchenhao/BIT\_CD.

arXiv comment14 pages, 8 figures. Accepted article by IEEE TGRS

References in corpus (2)

• DASNet: Dual attentive fully convolutional siamese networks for change detection of high resolution satellite images
• From W-Net to CDGAN: Bi-temporal Change Detection via Deep Learning Techniques

Cited by in corpus (39)

• Changer: Feature Interaction is What You Need for Change Detection
• HANet: A Hierarchical Attention Network for Change Detection With Bitemporal Very-High-Resolution Remote Sensing Images
• Building extraction with vision transformer
• S2Looking: A Satellite Side-Looking Dataset for Building Change Detection
• An Empirical Study of Remote Sensing Pretraining
• Adapting Segment Anything Model for Change Detection in HR Remote Sensing Images
• Change Guiding Network: Incorporating Change Prior to Guide Change Detection in Remote Sensing Imagery
• Looking Outside the Window: Wide-Context Transformer for the Semantic Segmentation of High-Resolution Remote Sensing Images
• Joint Spatio-Temporal Modeling for the Semantic Change Detection in Remote Sensing Images
• CMID: A Unified Self-Supervised Learning Framework for Remote Sensing Image Understanding
• Adjacent-Level Feature Cross-Fusion With 3-D CNN for Remote Sensing Image Change Detection
• Exchanging Dual Encoder-Decoder: A New Strategy for Change Detection with Semantic Guidance and Spatial Localization
• C2F-SemiCD: A Coarse-to-Fine Semi-Supervised Change Detection Method Based on Consistency Regularization in High-Resolution Remote Sensing Images
• Change-Agent: Towards Interactive Comprehensive Remote Sensing Change Interpretation and Analysis
• A Survey of Sample-Efficient Deep Learning for Change Detection in Remote Sensing: Tasks, Strategies, and Challenges
• Semantic-aware Dense Representation Learning for Remote Sensing Image Change Detection
• Diffusion Models Meet Remote Sensing: Principles, Methods, and Perspectives
• SAAN: Similarity-aware attention flow network for change detection with VHR remote sensing images
• Continuous Cross-resolution Remote Sensing Image Change Detection
• ObjFormer: Learning Land-Cover Changes From Paired OSM Data and Optical High-Resolution Imagery via Object-Guided Transformer
• EHCTNet: Enhanced Hybrid of CNN and Transformer Network for Remote Sensing Image Change Detection
• Remote Sensing SpatioTemporal Vision-Language Models: A Comprehensive Survey
• Semantic Labeling of High Resolution Images Using EfficientUNets and Transformers
• SRC-Net: Bi-Temporal Spatial Relationship Concerned Network for Change Detection
• Vision-Language Modeling Meets Remote Sensing: Models, Datasets and Perspectives
• MCTNet: A Multi-Scale CNN-Transformer Network for Change Detection in Optical Remote Sensing Images
• Fusion of Satellite Images and Weather Data with Transformer Networks for Downy Mildew Disease Detection
• Bridging the Domain Gap: A Simple Domain Matching Method for Reference-based Image Super-Resolution in Remote Sensing
• Single-Temporal Supervised Learning for Universal Remote Sensing Change Detection
• EfficientCD: A New Strategy For Change Detection Based With Bi-temporal Layers Exchanged
• Implicit Ray-Transformers for Multi-view Remote Sensing Image Segmentation
• AdaSemiCD: An Adaptive Semi-Supervised Change Detection Method Based on Pseudo-Label Evaluation
• Be the Change You Want to See: Revisiting Remote Sensing Change Detection Practices
• NN-Copula-CD: A Copula-Guided Interpretable Neural Network for Change Detection in Heterogeneous Remote Sensing Images
• Toward distortion-aware change detection in realistic scenarios
• BD-MSA: Body decouple VHR Remote Sensing Image Change Detection method guided by multi-scale feature information aggregation
• HA2F: Dual-module Collaboration-Guided Hierarchical Adaptive Aggregation Framework for Remote Sensing Change Detection
• MGCR-Net:Multimodal Graph-Conditioned Vision-Language Reconstruction Network for Remote Sensing Change Detection
• Learning Woody Clearing With Loss Alignment for Zero-Shot Regrowth and Woody Segmentation