Image classification is a crucial task in machine learning. In recent years, this field has witnessed rapid development, with a series of image classification models being proposed and achieving state-of-the-art (SOTA) results. Parallelly, with the advancement of quantum technologies, quantum machine learning has attracted a lot of interest. In particular, a class of algorithms known as variational quantum algorithms (VQAs) has been extensively studied to improve the performance of classical machine learning. In this paper, we propose a novel image classification framework using VQAs. The major advantage of our framework is the elimination of the need for the global pooling operation typically performed at the end of classical image classification models. While global pooling can help to reduce computational complexity, it often results in a significant loss of information. By removing the global pooling module before the output layer, our approach allows for effectively capturing more discriminative features and fine-grained details in images, leading to improved classification performance. Moreover, employing VQAs enables our framework to have fewer parameters compared to the classical framework, even in the absence of global pooling, which makes it more advantageous in preventing overfitting. We apply our method to different SOTA image classification models and demonstrate the superiority of the proposed quantum architecture over its classical counterpart through a series of experiments on public datasets.

翻译：图像分类是机器学习中的一项关键任务。近年来，该领域发展迅速，一系列图像分类模型相继被提出并取得了最先进（SOTA）的结果。与此同时，随着量子技术的发展，量子机器学习引起了广泛关注。特别是，一类称为变分量子算法（VQAs）的算法被广泛研究，以提升经典机器学习的性能。在本文中，我们提出了一种使用VQAs的新型图像分类框架。该框架的主要优势在于消除了经典图像分类模型末尾通常执行的全局池化操作。虽然全局池化有助于降低计算复杂度，但它常常导致显著的信息损失。通过移除输出层前的全局池化模块，我们的方法能够有效捕获图像中更具判别性的特征和细粒度细节，从而提升分类性能。此外，即使在没有全局池化的情况下，使用VQAs也能使我们的框架相比经典框架具有更少的参数，这使其在防止过拟合方面更具优势。我们将该方法应用于不同的SOTA图像分类模型，并通过在公开数据集上的一系列实验，证明了所提出的量子架构相对于经典对应架构的优越性。