Quantized Proximal Averaging Networks for Compressed Image Recovery

Reddy, NKK and Bulusu, MM and Pokala, PK and Seelamantula, CS (2023) Quantized Proximal Averaging Networks for Compressed Image Recovery. In: 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2023, 18 - 22 June 2023, Vancouver, BC, Canada, pp. 4633-4643.

PDF IEEE-CVF_CVPRW2023_2023_4633-4643_2023.pdf - Published Version Restricted to Registered users only Download (10MB) | Request a copy

Abstract

We solve the analysis sparse coding problem considering a combination of convex and non-convex sparsity promoting penalties. The multi-penalty formulation results in an iterative algorithm involving proximal-averaging. We then unfold the iterative algorithm into a trainable network that facilitates learning the sparsity prior. We also consider quantization of the network weights. Quantization makes neural networks efficient both in terms of memory and computation during inference, and also renders them compatible for low-precision hardware deployment. Our learning algorithm is based on a variant of the ADAM optimizer in which the quantizer is part of the forward pass and the gradients of the loss function are evaluated corresponding to the quantized weights while doing a book-keeping of the high-precision weights. We demonstrate applications to compressed image recovery and magnetic resonance image reconstruction. The proposed approach offers superior reconstruction accuracy and quality than state-of-the-art unfolding techniques and the performance degradation is minimal even when the weights are subjected to extreme quantization. © 2023 IEEE.

Item Type:	Conference Paper
Publication:	IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops
Publisher:	IEEE Computer Society
Additional Information:	The copyright for this article belongs to the IEEE Computer Society.
Keywords:	Image compression; Iterative methods; Learning algorithms; Magnetic resonance imaging, Coding problems; Compressed images; Image recovery; Iterative algorithm; Network weights; Neural-networks; Penalty formulation; Quantisation; Sparse coding; Sparsity priors, Image reconstruction
Department/Centre:	Division of Electrical Sciences > Electrical Engineering
Date Deposited:	24 Nov 2023 10:10
Last Modified:	24 Nov 2023 10:10
URI:	https://eprints.iisc.ac.in/id/eprint/83212

Actions (login required)

View Item