UniRSCD: A Unified Novel Architectural Paradigm for Remote Sensing Change Detection

The Identification of changes within two different images from satellites or other sources of remote sensing is a basic issue in earth observation that seeks to recognize any semantically significant distinctions between two images. Methods using supervised learning approaches provide good performance on RSCD tasks, however, they suffer from generalization issues. In this paper, we present UniRSCD, a unified architectural paradigm for semantic change detection that integrates class-prior color statistics, dual-branch feature fusion, and lightweight decoder design into a single end-to-end trainable framework.
UniRSCD leverages an encoder network that is built on ResNet34 and executes simultaneously over the image pairs while using a special color signal stream to combine several difference features at different scales, along with an attention mechanism based on RGB statistics prototypes. Our extensive evaluations on the benchmark dataset SECOND show that the average class IoU of our approach reaches 38.7% and its F1 score is 53.5%, outperforming the previous SOTA open-vocabulary change detection method OmniOVCD by +11.6 IoU and +11.7 F1. In particular, the IoU scores of buildings and playgrounds are 61.3% (+16.1) and 64.4% (+37.4) compared to OmniOVCD, respectively, showing the effectiveness of prior-aware class disambiguation in spectral land-cover categories.

Remote sensing, change detection, semantic segmentation

1. X. Zhang et al., "OmniOVCD: Streamlining Open-Vocabulary Change Detection with SAM 3," arXiv:2601.13895, 2026. [Online]. Available: https://arxiv.org/abs/2601.13895 [Google Scholar] [Crossref]

2. K. Li et al., "DynamicEarth: How Far are We from Open-Vocabulary Change Detection?" arXiv:2501.12931, 2025. [Online]. Available: https://arxiv.org/abs/2501.12931 [Google Scholar] [Crossref]

3. N. Carion et al., "SAM 3: Segment Anything with Concepts," arXiv:2511.16719, 2025. [Online]. Available: https://arxiv.org/abs/2511.16719 [Google Scholar] [Crossref]

4. Kirillov et al., "Segment Anything," in Proc. IEEE/CVF Int. Conf. Comput. Vis. (ICCV), Paris, France, 2023, pp. 4015–4026. [Online]. Available: https://arxiv.org/abs/2304.02643 [Google Scholar] [Crossref]

5. N. Ravi et al., "SAM 2: Segment Anything in Images and Videos," arXiv:2408.00714, 2024. [Online]. Available: https://arxiv.org/abs/2408.00714 [Google Scholar] [Crossref]

6. Radford et al., "Learning Transferable Visual Models From Natural Language Supervision," in Proc. Int. Conf. Mach. Learn. (ICML), vol. 139, 2021, pp. 8748–8763. [Online]. Available: https://arxiv.org/abs/2103.00020 [Google Scholar] [Crossref]

7. M. Oquab et al., "DINOv2: Learning Robust Visual Features without Supervision," arXiv:2304.07193, 2023. [Online]. Available: https://arxiv.org/abs/2304.07193 [Google Scholar] [Crossref]

8. M. Caron et al., "Emerging Properties in Self-Supervised Vision Transformers," in Proc. IEEE/CVF Int. Conf. Comput. Vis. (ICCV), Montreal, Canada, 2021, pp. 9650–9660. [Online]. Available: https://arxiv.org/abs/2104.14294 [Google Scholar] [Crossref]

9. M. Lan et al., "ProxyCLIP: Proxy Attention Improves CLIP for Open-Vocabulary Segmentation," in Proc. Eur. Conf. Comput. Vis. (ECCV), Milan, Italy, 2024, pp. 70–88. [Online]. Available: https://arxiv.org/abs/2408.04883 [Google Scholar] [Crossref]

10. K. Li et al., "SegEarth-OV: Towards Training-Free Open-Vocabulary Segmentation for Remote Sensing Images," in Proc. IEEE/CVF Conf. Comput. Vis. Pattern Recognit. (CVPR), Nashville, USA, 2025, pp. 10545–10556. [Online]. Available: https://arxiv.org/abs/2410.01768 [Google Scholar] [Crossref]

11. K. Li et al., "SegEarth-OV3: Exploring SAM 3 for Open-Vocabulary Semantic Segmentation in Remote Sensing Images," arXiv:2512.08730, 2025. [Online]. Available: https://arxiv.org/abs/2512.08730 [Google Scholar] [Crossref]

12. Z. Zheng et al., "Segment Any Change," in Adv. Neural Inf. Process. Syst. (NeurIPS), New Orleans, USA, 2024. [Online]. Available: https://arxiv.org/abs/2402.01188 [Google Scholar] [Crossref]

13. X. Tan et al., "Segment Change Model (SCM) for Unsupervised Change Detection in VHR Remote Sensing Images," in Proc. IEEE Int. Geosci. Remote Sens. Symp. (IGARSS), Athens, Greece, 2024, pp. 8577–8580. [Online]. Available: https://ieeexplore.ieee.org/document/10641528 [Google Scholar] [Crossref]

14. H. Chen et al., "ChangeMamba: Remote Sensing Change Detection with Spatio-Temporal State Space Model," arXiv:2404.03425, 2024. [Online]. Available: https://arxiv.org/abs/2404.03425 [Google Scholar] [Crossref]

15. J. Chen and W. Shi, "Spatial-Temporal Transformer for Large-Scale Remote Sensing Image Change Detection," IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens., vol. 15, pp. 2517–2527, 2022. [Online]. Available: https://ieeexplore.ieee.org/document/9627707 [Google Scholar] [Crossref]

16. S. Yang et al., "SECOND: A Dataset for Semantic Change Detection," IEEE Trans. Geosci. Remote Sens., vol. 60, pp. 1–16, 2022. [Online]. Available: https://ieeexplore.ieee.org/document/9555824 [Google Scholar] [Crossref]

17. H. Chen and Z. Shi, "A Spatial-Temporal Attention-Based Method and a New Dataset for Remote Sensing Image Change Detection," Remote Sens., vol. 12, no. 10, p. 1662, 2020. [Online]. Available: https://www.mdpi.com/2072-4292/12/10/1662 [Google Scholar] [Crossref]

18. S. Ji et al., "Fully Convolutional Networks for Multisource Building Extraction From an Open Aerial and Satellite Imagery Data Set," IEEE Trans. Geosci. Remote Sens., vol. 57, no. 1, pp. 574–586, 2019. [Online]. Available: https://ieeexplore.ieee.org/document/8444434 [Google Scholar] [Crossref]

19. P. Shen et al., "S2Looking: A Satellite Side-Looking Dataset for Building Change Detection," Remote Sens., vol. 13, no. 24, p. 5094, 2021. [Online]. Available: https://www.mdpi.com/2072-4292/13/24/5094 [Google Scholar] [Crossref]

20. L. Mei et al., "SCD-SAM: Adapting Segment Anything Model for Semantic Change Detection in Remote Sensing Imagery," IEEE Trans. Geosci. Remote Sens., vol. 62, pp. 1–14, 2024. [Online].Available: https://ieeexplore.ieee.org/document/10443352 [Google Scholar] [Crossref]

21. T. Celik, "Unsupervised Change Detection in Satellite Images Using Principal Component Analysis and K-Means Clustering," IEEE Geosci. Remote Sens. Lett., vol. 6, no. 4, pp. 772–776, 2009. [Online]. Available: https://ieeexplore.ieee.org/document/5196726 [Google Scholar] [Crossref]

22. M. A. El Amin et al., "Convolutional Neural Network Features Based Change Detection in Satellite Images," Proc. SPIE, vol. 10011, 2016. [Online]. Available: https://www.spiedigitallibrary.org/conference-proceedings-of-spie/10011/1001152/Convolutional-neural-network-features-based-change-detection-in-satellite images/10.1117/12.2243039.short [Google Scholar] [Crossref]

23. Du et al., "Unsupervised Deep Slow Feature Analysis for Change Detection in Multi-Temporal Remote Sensing Images," IEEE Trans. Geosci. Remote Sens., vol. 57, no. 12, pp. 9976–9992, 2019. [Online]. Available: https://ieeexplore.ieee.org/document/8824216 [Google Scholar] [Crossref]

24. S. Saha et al., "Unsupervised Deep Change Vector Analysis for Multiple-Change Detection in VHR Images," IEEE Trans. Geosci. Remote Sens., vol. 57, no. 6, pp. 3677–3693, 2019. [Online]. Available: https://ieeexplore.ieee.org/document/8608001 [Google Scholar] [Crossref]

25. X. Tang et al., "An Unsupervised Remote Sensing Change Detection Method Based on Multiscale Graph Convolutional Network and Metric Learning," IEEE Trans. Geosci. Remote Sens., vol. 60, pp. 1–15, 2021. [Online]. Available: https://ieeexplore.ieee.org/document/9627698 [Google Scholar] [Crossref]

26. Bovolo and L. Bruzzone, "A Theoretical Framework for Unsupervised Change Detection Based on Change Vector Analysis in the Polar Domain," IEEE Trans. Geosci. Remote Sens., vol. 45, no. 1, pp. 218–236, 2007. [Online]. Available: https://ieeexplore.ieee.org/document/4069199 [Google Scholar] [Crossref]

27. Z. Wang et al., "SCLIP: Rethinking Self-Attention for Dense Vision-Language Inference," arXiv:2312.01597, 2024. [Online]. Available: https://arxiv.org/abs/2312.01597 [Google Scholar] [Crossref]

28. K. Li et al., "A New Learning Paradigm for Foundation Model-Based Remote-Sensing Change Detection," IEEE Trans. Geosci. Remote Sens., vol. 62, pp. 1–12, 2024. [Online]. Available: https://ieeexplore.ieee.org/document/10438490 [Google Scholar] [Crossref]

29. Y. Zhu et al., "Semantic-CD: Remote Sensing Image Semantic Change Detection towards Open-Vocabulary Setting," arXiv:2501.06808, 2025. [Online]. Available: https://arxiv.org/abs/2501.06808 [Google Scholar] [Crossref]

• What the Desert Fathers Teach Data Scientists: Ancient Ascetic Principles for Ethical Machine-Learning Practice
• Comparative Analysis of Some Machine Learning Algorithms for the Classification of Ransomware
• Comparative Performance Analysis of Some Priority Queue Variants in Dijkstra’s Algorithm
• Transfer Learning in Detecting E-Assessment Malpractice from a Proctored Video Recordings.
• Dual-Modal Detection of Parkinson’s Disease: A Clinical Framework and Deep Learning Approach Using NeuroParkNet