تقرير
Representation Learning via Cauchy Convolutional Sparse Coding
العنوان: | Representation Learning via Cauchy Convolutional Sparse Coding |
---|---|
المؤلفون: | Mayo, Perla, Karakuş, Oktay, Holmes, Robin, Achim, Alin |
سنة النشر: | 2020 |
المجموعة: | Computer Science |
مصطلحات موضوعية: | Electrical Engineering and Systems Science - Image and Video Processing, Computer Science - Computer Vision and Pattern Recognition, Computer Science - Machine Learning |
الوصف: | 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. Comment: 19 pages, 9 figures, journal draft |
نوع الوثيقة: | Working Paper |
DOI: | 10.1109/ACCESS.2021.3096643 |
URL الوصول: | http://arxiv.org/abs/2008.03473 |
رقم الأكسشن: | edsarx.2008.03473 |
قاعدة البيانات: | arXiv |
DOI: | 10.1109/ACCESS.2021.3096643 |
---|