Quantum-Classical Hybrid Machine Learning for Image Classification (ICCAD Special Session Paper)

TL;DR

This paper reviews quantum-classical hybrid machine learning models for image classification, focusing on Quanvolutional Neural Networks and classical feature extraction with QNNs, discussing design choices, opportunities, and providing a Python framework.

Contribution

It introduces and analyzes two hybrid QML models for image classification, emphasizing trainable filters and feature extraction techniques, and provides a Python framework for exploration.

Findings

Quantum models can extract rich features and create complex decision boundaries.

Hybrid models offer promising avenues for quantum advantage in image classification.

The paper discusses design trade-offs and potential benefits of quantum-classical integration.

Abstract

Image classification is a major application domain for conventional deep learning (DL). Quantum machine learning (QML) has the potential to revolutionize image classification. In any typical DL-based image classification, we use convolutional neural network (CNN) to extract features from the image and multi-layer perceptron network (MLP) to create the actual decision boundaries. On one hand, QML models can be useful in both of these tasks. Convolution with parameterized quantum circuits (Quanvolution) can extract rich features from the images. On the other hand, quantum neural network (QNN) models can create complex decision boundaries. Therefore, Quanvolution and QNN can be used to create an end-to-end QML model for image classification. Alternatively, we can extract image features separately using classical dimension reduction techniques such as, Principal Components Analysis (PCA) or Convolutional Autoencoder (CAE) and use the extracted features to train a QNN. We review two proposals on quantum-classical hybrid ML models for image classification namely, Quanvolutional Neural Network and dimension reduction using a classical algorithm followed by QNN. Particularly, we make a case for trainable filters in Quanvolution and CAE-based feature extraction for image datasets (instead of dimension reduction using linear transformations such as, PCA). We discuss various design choices, potential opportunities, and drawbacks of these models. We also release a Python-based framework to create and explore these hybrid models with a variety of design choices.