Publication Details
Overview
 
 
 

2023 IEEE International Conference on Acoustics, Speech and Signal Processing

Contribution To Book Anthology

Abstract 

Deep unfolding models are designed by unrolling an optimization algorithm into a deep learning network. These models have shown faster convergence and higher performance compared to the original optimization algorithms. Additionally, by incorporating domain knowledge from the optimization algorithm, they need much less training data to learn efficient representations. Current deep unfolding networks for sequential sparse recovery consist of recurrent neural networks (RNNs), which leverage the similarity between consecutive signals. We redesign the optimization problem to use correlations across the whole sequence, which unfolds into a Transformer architecture. Our model is used for the task of video frame reconstruction from low-dimensional measurements and is shown to outperform state-of-the-art deep unfolding RNN and Transformer models, as well as a traditional Vision Transformer on several video datasets.

Reference 
 
 
DOI scopus VUB