Insights Into Analysis Operator Learning: From Patch-Based Sparse Models to Higher Order MRFs
作者： Thomas Pock , Rene Ranftl , Yunjin Chen
关键词: Image restoration 、 Field (computer science) 、 Penalty method 、 Artificial intelligence 、 Function (mathematics) 、 Computer science 、 Order (exchange) 、 Operator (computer programming) 、 Filter (signal processing) 、 Machine learning 、 Factor (programming language)
摘要: This paper addresses a new learning algorithm for the recently introduced co-sparse analysis model. First, we give new insights into the co-sparse analysis model by establishing connections to filter-based MRF models, such as the field of experts model of Roth and Black. For training, we introduce a technique called bi-level optimization to learn the analysis operators. Compared with existing analysis operator learning approaches, our training procedure has the advantage that it is unconstrained with respect to the analysis …
elsevier.com
harvard.edu
arxiv.org
sci-hub.st 参考文章(39)
Jeremy Jancsary, Sebastian Nowozin, Carsten Rother, Loss-Specific Training of Non-Parametric Image Restoration Models: A New State of the Art Computer Vision – ECCV 2012. pp. 112- 125 ,(2012) , 10.1007/978-3-642-33786-4_9
Energy-based models for sparse overcomplete representations Journal of Machine Learning Research. ,vol. 4, pp. 1235- 1260 ,(2003) , 10.1162/JMLR.2003.4.7-8.1235
Yunjin Chen, Thomas Pock, René Ranftl, Horst Bischof, Revisiting Loss-Specific Training of Filter-Based MRFs for Image Restoration german conference on pattern recognition. pp. 271- 281 ,(2013) , 10.1007/978-3-642-40602-7_30
Karl Kunisch, Thomas Pock, A Bilevel Optimization Approach for Parameter Learning in Variational Models Siam Journal on Imaging Sciences. ,vol. 6, pp. 938- 983 ,(2013) , 10.1137/120882706
Le LI, Yu-Jin ZHANG, SENSC: a Stable and Efficient Algorithm for Nonnegative Sparse Coding: SENSC: a Stable and Efficient Algorithm for Nonnegative Sparse Coding Acta Automatica Sinica. ,vol. 35, pp. 1257- 1271 ,(2009) , 10.3724/SP.J.1004.2009.01257
Ron Rubinstein, Tomer Peleg, Michael Elad, Analysis K-SVD: A Dictionary-Learning Algorithm for the Analysis Sparse Model IEEE Transactions on Signal Processing. ,vol. 61, pp. 661- 677 ,(2013) , 10.1109/TSP.2012.2226445
Julien Mairal, Francis Bach, Jean Ponce, Guillermo Sapiro, Online dictionary learning for sparse coding Proceedings of the 26th Annual International Conference on Machine Learning - ICML '09. pp. 689- 696 ,(2009) , 10.1145/1553374.1553463
Dong C. Liu, Jorge Nocedal, On the limited memory BFGS method for large scale optimization Mathematical Programming. ,vol. 45, pp. 503- 528 ,(1989) , 10.1007/BF01589116
Karen Egiazarian, Kostadin Dabov, Alessandro Foi, Vladimir Katkovnik, Image Denoising by Sparse 3-D Transform-Domain Collaborative Filtering IEEE Transactions on Image Processing. ,vol. 16, pp. 2080- 2095 ,(2007) , 10.1109/TIP.2007.901238
Uwe Schmidt, Qi Gao, Stefan Roth, A generative perspective on MRFs in low-level vision computer vision and pattern recognition. pp. 1751- 1758 ,(2010) , 10.1109/CVPR.2010.5539844