درحال بارگذاري...
MaskChanger: A Transformer-Based Model Tailoring Change Detection with Mask Classification
0 مرتبه مشاهده شده

MaskChanger: A Transformer-Based Model Tailoring Change Detection with Mask Classification

Ebrahimzadeh, M.

  1. DOI:10.1109/MVIP62238.2024.10491166
  2. Main Entry: Ebrahimzadeh, M.
  3. Title:MaskChanger: A Transformer-Based Model Tailoring Change Detection with Mask Classification.
  4. Publisher:2024.
  5. Abstract:Change detection in multi-temporal remote sensing data enables crucial urban analysis and environmental monitoring applications. However, complex factors like illumination variance and occlusion make robust automated change interpretation challenging. We propose MaskChanger - a novel deep learning paradigm tailored for satellite image change detection. Our method adapts the segmentation-specialized Mask2Former architecture by incorporating Siamese networks to extract features separately from bi-temporal images, while retaining the original mask transformer decoder. To our knowledge, this is the first study in which change detection is converted from the existing per-pixel classification approach into a mask classification approach. Evaluated on the LEVIR-CD benchmark of over 600 very high-resolution image pairs exhibiting real-world rural and urban changes, MaskChanger achieves Fl-Score of 91.96%, outperforming prior transformer-based change detection approaches. © 2024 IEEE
  6. Notes:Sharif Repository
  7. Subject:Transformer.
  8. Subject:Deep learning.
  9. Subject:Image classification.
  10. Subject:Image segmentation.
  11. Subject:Remote sensing.
  12. Subject:Classification approach.
  13. Subject:Complex factors.
  14. Subject:Environmental Monitoring.
  15. Subject:Monitoring applications.
  16. Subject:Multi-temporal remote sensing.
  17. Subject:Remote sensing data.
  18. Subject:Remote sensing images.
  19. Subject:Urban analysis.
  20. Subject:Change detection.
  21. Added Entry:Manzuri, M. T.
  22. Added Entry:Sharif University of Technology.
  23. Source: Iranian Conference on Machine Vision and Image Processing, MVIP ; 2024 ; 21666776 (ISSN); 979-835035049-4 (ISBN)
  24. Web Site:https://ieeexplore.ieee.org/document/10491166

 فهرست نقدها