# SAAN: Similarity-aware attention flow network for change detection with VHR remote sensing images

arXiv: https://arxiv.org/abs/2308.14570 · HTML: https://mlsanity.com/paper/2308.14570/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- Builds on 28 of its 78 references that are in the map.
- First posted on arXiv 28 Aug 2023.

## Builds on (most cited first, 28 of 28)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization](https://mlsanity.com/paper/1610.02391/) (2016)
- [EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks](https://mlsanity.com/paper/1905.11946/) (2019)
- [Squeeze-and-Excitation Networks](https://mlsanity.com/paper/1709.01507/) (2017)
- [FaceNet: A Unified Embedding for Face Recognition and Clustering](https://mlsanity.com/paper/1503.03832/) (2015)
- [CBAM: Convolutional Block Attention Module](https://mlsanity.com/paper/1807.06521/) (2018)
- [CosFace: Large Margin Cosine Loss for Deep Face Recognition](https://mlsanity.com/paper/1801.09414/) (2018)
- [AdaFace: Quality Adaptive Margin for Face Recognition](https://mlsanity.com/paper/2204.00964/) (2022)
- [Fully Convolutional Siamese Networks for Change Detection](https://mlsanity.com/paper/1810.08462/) (2018)
- [Remote Sensing Image Change Detection with Transformers](https://mlsanity.com/paper/2103.00208/) (2021)
- [A Transformer-Based Siamese Network for Change Detection](https://mlsanity.com/paper/2201.01293/) (2022)
- [Unified Contrastive Learning in Image-Text-Label Space](https://mlsanity.com/paper/2204.03610/) (2022)
- [xBD: A Dataset for Assessing Building Damage from Satellite Imagery](https://mlsanity.com/paper/1911.09296/) (2019)
- [Urban Change Detection for Multispectral Earth Observation Using Convolutional Neural Networks](https://mlsanity.com/paper/1810.08468/) (2018)
- [Superpixel Sampling Networks](https://mlsanity.com/paper/1807.10174/) (2018)
- [Towards Universal Representation Learning for Deep Face Recognition](https://mlsanity.com/paper/2002.11841/) (2020)
- [DASNet: Dual attentive fully convolutional siamese networks for change detection of high resolution satellite images](https://mlsanity.com/paper/2003.03608/) (2020)
- [Deep Learning for Instance Retrieval: A Survey](https://mlsanity.com/paper/2101.11282/) (2021)
- [Change is Everywhere: Single-Temporal Supervised Object Change Detection in Remote Sensing Imagery](https://mlsanity.com/paper/2108.07002/) (2021)
- [Few-shot Object Counting with Similarity-Aware Feature Enhancement](https://mlsanity.com/paper/2201.08959/) (2022)
- [Unsupervised Deep Slow Feature Analysis for Change Detection in Multi-Temporal Remote Sensing Images](https://mlsanity.com/paper/1812.00645/) (2018)
- [Semantic Change Detection with Asymmetric Siamese Networks](https://mlsanity.com/paper/2010.05687/) (2020)
- [FCCDN: Feature Constraint Network for VHR Image Change Detection](https://mlsanity.com/paper/2105.10860/) (2021)
- [Unsupervised Change Detection in Multi-temporal VHR Images Based on Deep Kernel PCA Convolutional Mapping Network](https://mlsanity.com/paper/1912.08628/) (2019)
- [Dual-Tasks Siamese Transformer Framework for Building Damage Assessment](https://mlsanity.com/paper/2201.10953/) (2022)

## Built on by (most cited first, 12 of 12)

- [MTP: Advancing Remote Sensing Foundation Model via Multi-Task Pretraining](https://mlsanity.com/paper/2403.13430/) (2024)
- [Frequency-Assisted Mamba for Remote Sensing Image Super-Resolution](https://mlsanity.com/paper/2405.04964/) (2024)
- [BRIGHT: A globally distributed multimodal building damage assessment dataset with very-high-resolution for all-weather disaster response](https://mlsanity.com/paper/2501.06019/) (2025)
- [Visual Instruction Pretraining for Domain-Specific Foundation Models](https://mlsanity.com/paper/2509.17562/) (2025)
- [UniChange: Unifying Change Detection with Multimodal Large Language Model](https://mlsanity.com/paper/2511.02607/) (2025)
- [LaVIDE: Language-Prompted Satellite Change Detection via Map-Image Alignment](https://mlsanity.com/paper/2411.19758/) (2024)
- [Wavelet-Guided Dual-Frequency Encoding for Remote Sensing Change Detection](https://mlsanity.com/paper/2508.05271/) (2025)
- [Riemannian Complex Hermit Positive Definite Convolution Network for Polarimetric SAR Image Classification](https://mlsanity.com/paper/2502.08137/) (2025)
- [Generalization-aware Remote Sensing Change Detection via Domain-agnostic Learning](https://mlsanity.com/paper/2504.00543/) (2025)
- [Transformer-Guided Content-Adaptive Graph Learning for Hyperspectral Unmixing](https://mlsanity.com/paper/2509.03376/) (2025)
- [Multi-Modal Building Change Detection for Large-Scale Small Changes: Benchmark and Baseline](https://mlsanity.com/paper/2603.19077/) (2026)
- [FootprintNet: State-Transition-Guided Dynamic Footprint Learning for Multi-temporal Remote Sensing Change Detection](https://mlsanity.com/paper/2607.27969/) (2026)

## Abstract (arXiv)

Change detection (CD) is a fundamental and important task for monitoring the land surface dynamics in the earth observation field. Existing deep learning-based CD methods typically extract bi-temporal image features using a weight-sharing Siamese encoder network and identify change regions using a decoder network. These CD methods, however, still perform far from satisfactorily as we observe that 1) deep encoder layers focus on irrelevant background regions and 2) the models' confidence in the change regions is inconsistent at different decoder stages. The first problem is because deep encoder layers cannot effectively learn from imbalanced change categories using the sole output supervision, while the second problem is attributed to the lack of explicit semantic consistency preservation. To address these issues, we design a novel similarity-aware attention flow network (SAAN). SAAN incorporates a similarity-guided attention flow module with deeply supervised similarity optimization to achieve effective change detection. Specifically, we counter the first issue by explicitly guiding deep encoder layers to discover semantic relations from bi-temporal input images using deeply supervised similarity optimization. The extracted features are optimized to be semantically similar in the unchanged regions and dissimilar in the changing regions. The second drawback can be alleviated by the proposed similarity-guided attention flow module, which incorporates similarity-guided attention modules and attention flow mechanisms to guide the model to focus on discriminative channels and regions. We evaluated the effectiveness and generalization ability of the proposed method by conducting experiments on a wide range of CD tasks. The experimental results demonstrate that our method achieves excellent performance on several CD tasks, with discriminative features and semantic consistency preserved.