Qubit-Efficient Hybrid CNN-Quantum Network for Scalable Multi-Class Image Classification
TL;DR
This work proposes a new Hybrid CNN-Quantum framework that dramatically reduces the required quantum resources, and uses an amplitude-encoding-inspired technique and a new activation function that together allow it to infer the final classification using only ⌈log2 (number of classes)⌉ readout qubits.
Abstract
Hybrid classical-quantum machine learning is a promising approach for image classification, but current methods often require too many qubits (quantum resources), creating a bottleneck for practical use. Current methodologies either constrain classification to basic binary decisions due to intricate quantum circuit design or depend on a Convolutional Neural Network (CNN) feature extractor that interfaces with a quantum layer necessitating a substantial quantity of qubits, frequently equivalent to the number of extracted features. To solve this, we propose a new Hybrid CNN-Quantum framework that dramatically reduces the required quantum resources. Our key innovation is an amplitude-encoding-inspired technique and a new activation function that together allow us to infer the final classification using only ⌈log2 (number of classes)⌉ readout qubits. We validated our framework on MNIST, Fashion-MNIST, and KMNIST, achieving accuracies of 0.9697, 0.8515, and 0.9258, respectively, using just 8 qubits. This matches or surpasses prior results that used over 1500 qubits, highlighting our method's competitive accuracy with drastically reduced quantum hardware requirements.