Representation Learning via Cauchy Convolutional Sparse Coding

08/08/2020
by   Perla Mayo, et al.
0

In representation learning, Convolutional Sparse Coding (CSC) enables unsupervised learning of features by jointly optimising both an ℓ_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 ℓ_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.

READ FULL TEXT

Please sign up or login with your details

Forgot password? Click here to reset