TY - GEN
T1 - Fast and Flexible Convolutional Sparse Coding
AU - Heide, Felix
AU - Heidrich, Wolfgang
AU - Wetzstein, Gordon
N1 - KAUST Repository Item: Exported on 2021-02-10
PY - 2015/10/15
Y1 - 2015/10/15
N2 - Convolutional sparse coding (CSC) has become an increasingly important tool in machine learning and computer vision. Image features can be learned and subsequently used for classification and reconstruction tasks. As opposed to patch-based methods, convolutional sparse coding operates on whole images, thereby seamlessly capturing the correlation between local neighborhoods. In this paper, we propose a new approach to solving CSC problems and show that our method converges significantly faster and also finds better solutions than the state of the art. In addition, the proposed method is the first efficient approach to allow for proper boundary conditions to be imposed and it also supports feature learning from incomplete data as well as general reconstruction problems.
AB - Convolutional sparse coding (CSC) has become an increasingly important tool in machine learning and computer vision. Image features can be learned and subsequently used for classification and reconstruction tasks. As opposed to patch-based methods, convolutional sparse coding operates on whole images, thereby seamlessly capturing the correlation between local neighborhoods. In this paper, we propose a new approach to solving CSC problems and show that our method converges significantly faster and also finds better solutions than the state of the art. In addition, the proposed method is the first efficient approach to allow for proper boundary conditions to be imposed and it also supports feature learning from incomplete data as well as general reconstruction problems.
UR - http://hdl.handle.net/10754/556538
UR - http://www.cv-foundation.org/openaccess/content_cvpr_2015/app/3B_075_ext.pdf
UR - http://www.scopus.com/inward/record.url?scp=84959235606&partnerID=8YFLogxK
U2 - 10.1109/CVPR.2015.7299149
DO - 10.1109/CVPR.2015.7299149
M3 - Conference contribution
AN - SCOPUS:84959235606
SN - 9781467369640
SP - 5135
EP - 5143
BT - Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition
PB - Institute of Electrical and Electronics Engineers (IEEE)
ER -