Performance Evaluation of Segment Anything Model with Variational Prompting for Application to Non-Visible Spectrum Imagery

Gaus, Y. F. A.; Bhowmik, N.; Isaac-Medina, B. K. S.; Breckon, T. P.

Performance Evaluation of Segment Anything Model with Variational Prompting for Application to Non-Visible Spectrum Imagery

Gaus, Y. F. A.; Bhowmik, N.; Isaac-Medina, B. K. S.; Breckon, T. P.

Authors

Yona Binti Abd Gaus yona.f.binti-abd-gaus@durham.ac.uk
Post Doctoral Research Associate

Dr Neelanjan Bhowmik neelanjan.bhowmik@durham.ac.uk
Post Doctoral Research Associate

Brian Isaac Medina brian.k.isaac-medina@durham.ac.uk
Postdoctoral Research Associate

Professor Toby Breckon toby.breckon@durham.ac.uk
Professor

Citation

Gaus, Y. F. A., Bhowmik, N., Isaac-Medina, B. K. S., & Breckon, T. P. (in press). Performance Evaluation of Segment Anything Model with Variational Prompting for Application to Non-Visible Spectrum Imagery.

Conference Name	2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)
Conference Location	Seattle, WA
Start Date	Jun 17, 2024
End Date	Jun 21, 2024
Acceptance Date	Apr 1, 2024
Deposit Date	Apr 23, 2024
Keywords	x-ray, thermal, infrared, foundational model, SAM, segmentation, semantic segmentation, instance segmantation
Public URL	https://durham-repository.worktribe.com/output/2393936
Publisher URL	https://ieeexplore.ieee.org/xpl/conhome/1001809/all-proceedings
Related Public URLs	https://breckon.org/tob...apers/gaus24segment.pdf