Efficient Quantum Feature Extraction for CNN-based Learning
This work addresses the challenge of improving machine learning model performance for image classification tasks, but it is incremental as it builds on existing quantum and classical methods without a paradigm shift.
The authors tackled the problem of enhancing classical CNN discriminability by integrating parametrized quantum circuits (PQCs) as feature extractors, resulting in a hybrid quantum-classical model that achieved lower cost and higher accuracy on MNIST classification compared to other settings.
Recent work has begun to explore the potential of parametrized quantum circuits (PQCs) as general function approximators. In this work, we propose a quantum-classical deep network structure to enhance classical CNN model discriminability. The convolutional layer uses linear filters to scan the input data. Moreover, we build PQC, which is a more potent function approximator, with more complex structures to capture the features within the receptive field. The feature maps are obtained by sliding the PQCs over the input in a similar way as CNN. We also give a training algorithm for the proposed model. The hybrid models used in our design are validated by numerical simulation. We demonstrate the reasonable classification performances on MNIST and we compare the performances with models in different settings. The results disclose that the model with ansatz in high expressibility achieves lower cost and higher accuracy.