Learning ${\ell }_1$-based analysis and synthesis sparsity priors using bi-level optimization

Abstract

We consider the analysis operator and synthesis dictionary learning problems based on the the ${\ell }_1$ regularized sparse representation model. We reveal the internal relations between the ${\ell }_1$-based analysis model and synthesis model. We then introduce an approach to learn both analysis operator and synthesis dictionary simultaneously by using a unified framework of bi-level optimization. Our aim is to learn a meaningful operator (dictionary) such that the minimum energy solution of the analysis (synthesis)-prior based model is as close as possible to the ground-truth. We solve the bi-level optimization problem using the implicit differentiation technique. Moreover, we demonstrate the effectiveness of our leaning approach by applying the learned analysis operator (dictionary) to the image denoising task and comparing its performance with state-of-the-art methods. Under this unified framework, we can compare the performance of the two types of priors.

5 pages, 1 figure, appear at the Workshop on Analysis Operator Learning vs. Dictionary Learning, NIPS 2012

Cited by in corpus (6)

• Insights into analysis operator learning: From patch-based sparse models to higher-order MRFs
• The structure of optimal parameters for image restoration problems
• Learning Filter Bank Sparsifying Transforms
• Learning Co-Sparse Analysis Operators with Separable Structures
• Supervised Learning of Sparsity-Promoting Regularizers for Denoising
• Explorations on anisotropic regularisation of dynamic inverse problems by bilevel optimisation