Feasible Architecture for Quantum Fully Convolutional Networks

TL;DR

This paper proposes a feasible pure quantum architecture for fully convolutional networks that can operate on noisy intermediate-scale quantum devices, enabling quantum semantic segmentation with potential advantages over hybrid solutions.

Contribution

It introduces a novel quantum fully convolutional network architecture with convolutional, pooling, and upsampling layers suitable for noisy quantum hardware.

Findings

Successful training of a quantum fully convolutional network in simulations

The architecture can be implemented on various physical platforms

Advantages over hybrid quantum-classical solutions are discussed

Abstract

Fully convolutional networks are robust in performing semantic segmentation, with many applications from signal processing to computer vision. From the fundamental principles of variational quantum algorithms, we propose a feasible pure quantum architecture that can be operated on noisy intermediate-scale quantum devices. In this work, a parameterized quantum circuit consisting of three layers, convolutional, pooling, and upsampling, is characterized by generative one-qubit and two-qubit gates and driven by a classical optimizer. This architecture supplies a solution for realizing the dynamical programming on a one-way quantum computer and maximally taking advantage of quantum computing throughout the calculation. Moreover, our algorithm works on many physical platforms, and particularly the upsampling layer can use either conventional qubits or multiple-level systems. Through numerical simulations, our study represents the successful training of a pure quantum fully convolutional network and discusses advantages by comparing it with the hybrid solution.