Learned Convolutional Sparse Coding

We propose a convolutional recurrent sparse auto-encoder model. The model consists of a sparse encoder, which is a convolutional extension of the learned ISTA (LISTA) method, and a linear convolutional decoder. Our strategy offers a simple strategy for learning a task-driven sparse convolutional dic...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) s. 2191 - 2195
Hlavní autoři: Sreter, Hillel, Giryes, Raja
Médium: Konferenční příspěvek
Jazyk:angličtina
Vydáno: IEEE 01.04.2018
Témata:
Computational modeling
Convolution
Convolutional codes
Convolutional Sparse Coding
Dictionaries
Encoding
ISTA
LISTA
Neural networks
Noise reduction
Sparse Coding
Task analysis
ISSN:2379-190X
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Popis
Shrnutí:We propose a convolutional recurrent sparse auto-encoder model. The model consists of a sparse encoder, which is a convolutional extension of the learned ISTA (LISTA) method, and a linear convolutional decoder. Our strategy offers a simple strategy for learning a task-driven sparse convolutional dictionary (CD), and producing an approximate convolutional sparse code (CSC) over the learned dictionary. We trained the model to minimize reconstruction loss via gradient decent with back-propagation and have achieved competitve results to KSVD image denoising and to leading CSC methods in image inpainting requiring only a small fraction of their runtime.
ISSN:2379-190X
DOI:10.1109/ICASSP.2018.8462313