Hybrid Quantum Neural Network Structures for Image Multi-classification

TL;DR

This paper evaluates hybrid quantum neural networks for multi-class image classification, comparing PCA and angle encoding methods, and explores transfer learning to enhance performance amid current quantum limitations.

Contribution

It introduces an optimized hybrid quantum neural network architecture and analyzes the effectiveness of PCA and angle encoding methods for multi-class image classification.

Findings

PCA-based quantum algorithms face barren plateau issues with increasing categories.

Hybrid CNN-QNN models partially address multi-class training challenges.

Quantum neural networks show potential but need further optimization.

Abstract

Image classification is a fundamental computer vision problem, and neural networks offer efficient solutions. With advancing quantum technology, quantum neural networks have gained attention. However, they work only for low-dimensional data and demand dimensionality reduction and quantum encoding. Two recent image classification methods have emerged: one employs PCA dimensionality reduction and angle encoding, the other integrates QNNs into CNNs to boost performance. Despite numerous algorithms, comparing PCA reduction with angle encoding against the latter remains unclear. This study explores these algorithms' performance in multi-class image classification and proposes an optimized hybrid quantum neural network suitable for the current environment. Investigating PCA-based quantum algorithms unveils a barren plateau issue for QNNs as categories increase, unsuitable for multi-class in the hybrid setup. Simultaneously, the combined CNN-QNN model partly overcomes QNN's multi-class training challenges but lags in accuracy to superior traditional CNN models. Additionally, this work explores transfer learning in the hybrid quantum neural network model. In conclusion, quantum neural networks show promise but require further research and optimization, facing challenges ahead.