Feasible Architecture for Quantum Fully Convolutional Networks
This work addresses the problem of enabling quantum computing for semantic segmentation tasks, offering a novel approach that could impact quantum machine learning, though it appears incremental as it builds on existing variational quantum algorithms.
The authors tackled the challenge of implementing fully convolutional networks on quantum hardware by proposing a pure quantum architecture that operates on noisy intermediate-scale quantum devices, achieving successful training through numerical simulations and demonstrating advantages over hybrid solutions.
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.