Hybrid spectral denoising transformer with guided attention

Z Lai, C Yan, Y Fu - Proceedings of the IEEE/CVF …, 2023 - openaccess.thecvf.com
In this paper, we present a Hybrid Spectral Denoising Transformer (HSDT) for hyperspectral
image denoising. Challenges in adapting transformer for HSI arise from the capabilities to …

[HTML][HTML] A novel detection method for warhead fragment targets in optical images under dynamic strong interference environments

G Zhang, H Zhang, Z Shen, D Kong, C Ning, F Shang… - Defence …, 2024 - Elsevier
A measurement system for the scattering characteristics of warhead fragments based on
high-speed imaging systems offers advantages such as simple deployment, flexible …

Denoiser-based projections for 2D super-resolution MRA

J Shani, T Tirer, R Giryes… - IEEE Open Journal of …, 2024 - ieeexplore.ieee.org
We study the 2D super-resolution multi-reference alignment (SR-MRA) problem: estimating
an image from its down-sampled, circularly translated, and noisy copies. The SR-MRA …

Single-Shot Plug-and-Play Methods for Inverse Problems

Y Cheng, L Zhang, Z Shen, S Wang, L Yu… - arXiv preprint arXiv …, 2023 - arxiv.org
The utilisation of Plug-and-Play (PnP) priors in inverse problems has become increasingly
prominent in recent years. This preference is based on the mathematical equivalence …

Theory Embedded Learning

C Chi - 2023 - tspace.library.utoronto.ca
Theory Embedded Learning (TEL) combines theoretical principles with machine learning to
solve Engineering problems. It offers a middle ground between principle-driven and learning …

Theory Embedded Learning A Universal Framework for Combining Theory With Learning

C Chi - 2023 - search.proquest.com
Abstract Theory Embedded Learning (TEL) combines theoretical principles with machine
learning to solve Engineering problems. It offers a middle ground between principle-driven …