Connections Between Deep Equilibrium and Sparse Representation Models With Application to Hyperspectral Image Denoising
- 22 February 2023
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Image Processing
- Vol. 32 (10577149) , 1513-1528
Abstract
In this study, the problem of computing a sparse representation of multi-dimensional visual data is considered. In general, such data e.g., hyperspectral images, color images or video data consists of signals that exhibit strong local dependencies. A new computationally efficient sparse coding optimization problem is derived by employing regularization terms that are adapted to the properties of the signals of interest. Exploiting the merits of the learnable regularization techniques, a neural network is employed to act as structure prior and reveal the underlying signal dependencies. To solve the optimization problem Deep unrolling and Deep equilibrium based algorithms are developed, forming highly interpretable and concise deep-learning-based architectures, that process the input dataset in a block-by-block fashion. Extensive simulation results, in the context of hyperspectral image denoising, are provided, which demonstrate that the proposed algorithms outperform significantly other sparse coding approaches and exhibit superior performance against recent state-of-the-art deep-learning-based denoising models. In a wider perspective, our work provides a unique bridge between a classic approach, that is the sparse representation theory, and modern representation tools that are based on deep learning modeling.Keywords
All Related Versions
Funding Information
- University of Patras and the Research Promotion Foundation (RPF), Cyprus, through IRIDA (INFRASTRUCTURES/ 1216/0017)
- Research Council of the University of Patras
This publication has 67 references indexed in Scilit:
- Hyperspectral Image Restoration Using Low-Rank Matrix RecoveryIEEE Transactions on Geoscience and Remote Sensing, 2013
- Sparse Representation Classifier Steered Discriminative Projection With Applications to Face RecognitionIEEE Transactions on Neural Networks and Learning Systems, 2013
- Anderson Acceleration for Fixed-Point IterationsSIAM Journal on Numerical Analysis, 2011
- Seismic moment tensor inversion using a 3-D structural model: applications for the Australian regionGeophysical Journal International, 2010
- CoSaMP: Iterative signal recovery from incomplete and inaccurate samplesApplied and Computational Harmonic Analysis, 2009
- Image quality assessment: from error visibility to structural similarityIEEE Transactions on Image Processing, 2004
- Affine Invariant Flows in the Beltrami FrameworkJournal of Mathematical Imaging and Vision, 2004
- Atomic Decomposition by Basis PursuitSIAM Journal on Scientific Computing, 1998
- Nonlinear image recovery with half-quadratic regularizationIEEE Transactions on Image Processing, 1995
- The spectral image processing system (SIPS)—interactive visualization and analysis of imaging spectrometer dataRemote Sensing of Environment, 1993