2025-01-14-wang25b.md

title	Multi-Scale Dual-Attention Unfolding Network for Compressed Sensing Image Reconstruction
booktitle	Proceedings of the 16th Asian Conference on Machine Learning
year	2025
volume	260
series	Proceedings of Machine Learning Research
month	0
publisher	PMLR
pdf	https://raw.githubusercontent.com/mlresearch/v260/main/assets/wang25b/wang25b.pdf
url	https://proceedings.mlr.press/v260/wang25b.html
openreview	ny6N9etKUn
abstract	Deep Unfolding Networks have emerged as a prominent strategy in compressed sensing image reconstruction, effectively merging optimization techniques with deep learning through end-to-end training of truncated inferences. Despite their advantages, these algorithms generally require extensive iterations and parameters, potentially limited by storage capacity. Additionally, the image-level transmission at each iterative step does not optimally harness the inter-scale feature information available. To address these issues, we introduce a novel approach in this paper: the $\textbf{M}$ulti-$\textbf{S}$cale $\textbf{D}$ual-$\textbf{A}$ttention $\textbf{U}$nfolding $\textbf{N}$etwork ($\textbf{MSDAUN}$) for compressed sensing image reconstruction. We propose a cross-stage multi-scale deep reconstruction module $\textbf{D}$ as an iterative process, which is composed of multiple attention sub-modules. These include Cross Attention Transformer($\textbf{CAT}$) Modules that enhance the reconstruction with multi-channel inertia, thereby facilitating feature-level transmission and robust information exchange. Concurrently, Texture Attention Transformer($\textbf{TAT}$) Modules are designed to meticulously extract salient reconstruction information, subsequently channeling it into the texture path to effectuate the precise prediction of textural regions, thereby contributing to the meticulous restoration of textural details. Our comprehensive experimental evaluation across diverse datasets confirms that MSDAUN surpasses existing state-of-the-art methods. This work presents significant potential for further advancements and applications in inverse imaging problems and optimization models.
layout	inproceedings
issn	2640-3498
id	wang25b
tex_title	Multi-Scale Dual-Attention Unfolding Network for Compressed Sensing Image Reconstruction
firstpage	207
lastpage	222
page	207-222
order	207
cycles	false
bibtex_editor	Nguyen, Vu and Lin, Hsuan-Tien
editor	given family Vu Nguyen given family Hsuan-Tien Lin
bibtex_author	Wang, Liangjun and Wang, Meixin
author	given family Liangjun Wang given family Meixin Wang
date	2025-01-14
address
container-title	Proceedings of the 16th Asian Conference on Machine Learning
genre	inproceedings
issued	date-parts 2025 1 14
extras