LIPSCHITZ-CONSTRAINED CONVOLUTIONAL LAYERS USING CONVEX PROJECTION

Kumar, B and Chaudhury, KN (2024) LIPSCHITZ-CONSTRAINED CONVOLUTIONAL LAYERS USING CONVEX PROJECTION. In: IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2024, 14 -19 April 2024, Seoul, pp. 6450-6454.

PDF iee_int_con_aco_spe_sig_pro_pro_2024...pdf - Published Version Restricted to Registered users only Download (2MB) | Request a copy

Abstract

The problem of training a convolutional neural network (CNN) with a stipulated Lipschitz bound comes up in applications such as adversarial robustness, stability of closed-loop controllers, and image reconstruction. The present work was motivated by Plug-and-Play (PnP) and Regularization-by-Denoising (RED) which use CNN denoisers for image reconstruction. It has been shown that the convergence of these iterative algorithms can be guaranteed by constraining the Lipschitz bound of the denoiser. We make the case that using a contractive CNN denoiser is a straightforward means to certify convergence. In particular, we show how a contractive CNN denoiser can be trained using convex projections within the paradigm of gradient-based learning and how the projection problem can be reduced to a tractable convex program. Apart from the theoretical guarantee, the regularization capacity of the trained denoiser is shown to be competitive with BM3D and DnCNN. © 2024 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 for this article belongs to Institute of Electrical and Electronics Engineers Inc.
Department/Centre:	Division of Electrical Sciences > Electrical Engineering
Date Deposited:	19 Aug 2024 13:28
Last Modified:	19 Aug 2024 13:28
URI:	http://eprints.iisc.ac.in/id/eprint/85479

Actions (login required)

View Item