Confirmnet: Convolutional Firmnet and Application to Image Denoising and Inpainting

Pokala, PK and Kumar Uttam, P and Seelamantula, CS (2020) Confirmnet: Convolutional Firmnet and Application to Image Denoising and Inpainting. In: 2020 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2020, 4-8, May 2020, Barcelona, Spain, pp. 8663-8667.

PDF iee_int_con_aco_spe_sig_pro_8663-8667_2020.pdf - Published Version Restricted to Registered users only Download (1MB) | Request a copy

Abstract

We address the problem of efficient convolutional sparse coding (CSC) and develop a non-convex-penalty-regularized CSC formulation, namely, minimax-concave CSC (MC2SC). MC2SC leads to an optimal sparse representation than the standard �1-penalty based approach. In addition, suitable convergence guarantees can also be provided for MC2SC. 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). © 2020 IEEE.

Item Type:	Conference Paper
Publication:	ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings
Publisher:	Institute of Electrical and Electronics Engineers Inc.
Additional Information:	The copyright of this article belongs to Institute of Electrical and Electronics Engineers Inc.
Department/Centre:	Division of Electrical Sciences > Electrical Engineering
Date Deposited:	26 Aug 2020 07:28
Last Modified:	26 Aug 2020 07:28
URI:	http://eprints.iisc.ac.in/id/eprint/66385

Actions (login required)

View Item