Confirmnet: Convolutional Firmnet and Application to Image Denoising and Inpainting

We address the problem of efficient convolutional sparse coding (CSC) and develop a non-convex-penalty-regularized CSC formulation, namely, minimax-concave CSC (MC 2 SC). MC 2 SC leads to an optimal sparse representation than the standard ℓ 1 -penalty based approach. In addition, suitable convergenc...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:Proceedings of the ... IEEE International Conference on Acoustics, Speech and Signal Processing (1998) s. 8663 - 8667
Hlavní autoři: Pokala, Praveen Kumar, Kumar Uttam, Prakash, Seelamantula, Chandra Sekhar
Médium: Konferenční příspěvek
Jazyk:angličtina
Vydáno: IEEE 01.05.2020
Témata:
Convolution
Convolutional codes
convolutional IFTA
Convolutional sparse coding
deep unfolding
FirmNet
Image denoising
Iterative algorithms
LISTA
Signal processing algorithms
Testing
Training
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 address the problem of efficient convolutional sparse coding (CSC) and develop a non-convex-penalty-regularized CSC formulation, namely, minimax-concave CSC (MC 2 SC). MC 2 SC leads to an optimal sparse representation than the standard ℓ 1 -penalty based approach. In addition, suitable convergence guarantees can also be provided for MC 2 SC. We propose a convolutional iterative firm-thresholding algorithm (CIFTA) building on our previously proposed IFTA, and its deep-unfolded version, namely, convolutional-FirmNet (ConFirmNet). As an application, we develop the ConFirmNet based sparse autoencoder (ConFirmNet-SAE) for learning an application-specific convolutional dictionary, the applications being image denoising and inpainting. Further, we also show that training ConFirmNet-SAE with the Huber loss imparts robustness to outliers. It also turns out that ConFirmNet-SAE is robust to mismatch between training and test noise conditions than convolutional learned iterative soft-thresholding algorithm (LISTA).
ISSN:2379-190X
DOI:10.1109/ICASSP40776.2020.9053538