Compressed Classification from Learned Measurements

Abstract

This work proposes a deep compressed learning framework inferring classification directly from the compressive measurements. While classical approaches separately sense, reconstruct signals, and apply classification on these reconstructions, we jointly learn the sensing and classification schemes utilizing a deep neural network with a novel loss function. Our approach employs a data-driven reconstruction network within the compressed learning framework utilizing a weighted loss that combines both in-network reconstruction and classification losses. The proposed network structure also learns the optimal measurement matrices for the goal of enhancing classification performance. Quantitative results demonstrated on CIFAR-10 image dataset show that the proposed framework provides better classification performance and robustness to noise compared to the tested state of the art deep compressed learning approaches.