Details

Autor(en) / Beteiligte

• Wangmeng Zuo
• Deyu Meng
• Lei Zhang
• Xiangchu Feng
• Zhang, David

Titel

A Generalized Iterated Shrinkage Algorithm for Non-convex Sparse Coding

Ist Teil von

• 2013 IEEE International Conference on Computer Vision, 2013, p.217-224

Ort / Verlag

IEEE

Erscheinungsjahr

2013

Quelle

IEEE Electronic Library (IEL)

Beschreibungen/Notizen

• In many sparse coding based image restoration and image classification problems, using non-convex I p -norm minimization (0 ≤ p <; 1) can often obtain better results than the convex l 1 -norm minimization. A number of algorithms, e.g., iteratively reweighted least squares (IRLS), iteratively thresholding method (ITM-I p ), and look-up table (LUT), have been proposed for non-convex I p -norm sparse coding, while some analytic solutions have been suggested for some specific values of p. In this paper, by extending the popular soft-thresholding operator, we propose a generalized iterated shrinkage algorithm (GISA) for I p -norm non-convex sparse coding. Unlike the analytic solutions, the proposed GISA algorithm is easy to implement, and can be adopted for solving non-convex sparse coding problems with arbitrary p values. Compared with LUT, GISA is more general and does not need to compute and store the look-up tables. Compared with IRLS and ITM-I p , GISA is theoretically more solid and can achieve more accurate solutions. Experiments on image restoration and sparse coding based face recognition are conducted to validate the performance of GISA.