Quantized Proximal Averaging Network for Analysis Sparse Coding

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.


page 1

page 5

page 8


Adaptive Loss-aware Quantization for Multi-bit Networks

We investigate the compression of deep neural networks by quantizing the...

Approximate search with quantized sparse representations

This paper tackles the task of storing a large collection of vectors, su...

NuSPAN: A Proximal Average Network for Nonuniform Sparse Model – Application to Seismic Reflectivity Inversion

We solve the problem of sparse signal deconvolution in the context of se...

Sparsity Promoting Reconstruction of Delta Modulated Voice Samples by Sequential Adaptive Thresholds

In this paper, we propose the family of Iterative Methods with Adaptive ...

A Low Memory Footprint Quantized Neural Network for Depth Completion of Very Sparse Time-of-Flight Depth Maps

Sparse active illumination enables precise time-of-flight depth sensing ...

Please sign up or login with your details

Forgot password? Click here to reset