Representation Learning via Cauchy Convolutional Sparse Coding
arXiv:2008.03473 · doi:10.1109/ACCESS.2021.3096643
Abstract
In representation learning, Convolutional Sparse Coding (CSC) enables unsupervised learning of features by jointly optimising both an \(\ell_2\)-norm fidelity term and a sparsity enforcing penalty. This work investigates using a regularisation term derived from an assumed Cauchy prior for the coefficients of the feature maps of a CSC generative model. The sparsity penalty term resulting from this prior is solved via its proximal operator, which is then applied iteratively, element-wise, on the coefficients of the feature maps to optimise the CSC cost function. The performance of the proposed Iterative Cauchy Thresholding (ICT) algorithm in reconstructing natural images is compared against the common choice of \(\ell_1\)-norm optimised via soft and hard thresholding. ICT outperforms IHT and IST in most of these reconstruction experiments across various datasets, with an average PSNR of up to 11.30 and 7.04 above ISTA and IHT respectively.
19 pages, 9 figures, journal draft
References in corpus (5)
- Shift-Invariance Sparse Coding for Audio Classification
- Learning Convolutional Sparse Coding on Complex Domain for Interferometric Phase Restoration
- On Solving SAR Imaging Inverse Problems Using Non-Convex Regularization with a Cauchy-based Penalty
- Convergence Guarantees for Non-Convex Optimisation with Cauchy-Based Penalties
- Detection of Line Artefacts in Lung Ultrasound Images of COVID-19 Patients via Non-Convex Regularization