WiMi Lays Out Scalable Quantum Convolutional Neural Network to Enhance Image Classification Accuracy and Efficiency
BEIJING, Sept. 15, 2025 /PRNewswire/ -- WiMi Hologram Cloud Inc. (NASDAQ: WiMi) ("WiMi" or the "Company"), a leading global Hologram Augmented Reality ("AR") Technology provider, today announced that they are actively exploring Scalable Quantum Convolutional Neural Networks (SQCNN) technology. Compared to existing quantum neural network models, the scalable quantum convolutional neural network model developed by WiMi demonstrates superior performance, significantly improving classification accuracy.
Traditional quantum neural network models, when handling complex image classification tasks, often suffer from biases in classification results due to incomplete or inaccurate feature extraction. In contrast, the scalable quantum convolutional neural network model, through optimized utilization of qubits and a unique network architecture design, can more accurately extract key features from images, thereby significantly improving classification accuracy. Additionally, in terms of model generalization, the scalable quantum convolutional neural network model can better adapt to the characteristics of different datasets, enabling accurate classification even when faced with new data. This advantage makes it more stable and reliable in practical applications, preventing significant performance degradation due to minor data variations. In terms of training efficiency, the scalable quantum convolutional neural network model greatly reduces the time required for training through optimization of quantum algorithms. By leveraging advanced algorithms and efficient quantum computing architectures, the scalable quantum convolutional neural network model significantly enhances application efficiency.
In traditional convolutional neural networks, the convolutional layer performs convolution operations on the image through a sliding convolution kernel to extract local features of the image. In the quantum circuit of the scalable quantum convolutional neural network, similar functionality is achieved by relying on the superposition and entanglement properties of quantum gates. The superposition of quantum gates allows qubits to exist in multiple states simultaneously, which is equivalent to processing multiple features at the same time, significantly improving processing efficiency. The entanglement between qubits establishes more complex correlations, enabling the quantum circuit to learn subtler and deeper features in the image. This unique design allows the quantum circuit of the scalable quantum convolutional neural network to better learn features, providing a solid foundation for subsequent classification tasks.
In particular, in the scalable quantum convolutional neural network system, multiple independent quantum devices can extract features in parallel, a design that is highly innovative and practical. In traditional machine learning tasks, feature extraction is often performed sequentially, which limits processing speed and efficiency. In contrast, the parallel design in the scalable quantum convolutional neural network system allows different quantum devices to simultaneously extract features from different parts of an image or different types of features, akin to multiple workers operating simultaneously in different areas, significantly accelerating the speed of feature extraction. Moreover, this design allows for the flexible use of quantum devices of varying sizes. When facing machine learning tasks of different scales and complexities, quantum devices of appropriate sizes can be selected and combined based on actual needs. For simple, small-scale tasks, smaller quantum devices can be used to reduce costs and computational complexity; for complex, large-scale tasks, multiple larger-scale quantum devices can be combined to meet the computational demands of the task, thereby enabling larger-scale machine learning tasks.
The scalable quantum convolutional neural network explored by WiMi not only achieves parallelization and multidimensionality in feature extraction but also breaks the conflict between computational resources and task complexity through its ability to dynamically adapt to the scale of quantum devices. This innovation not only significantly enhances the accuracy and efficiency of image classification but also strikes a balance between generalization capability and training costs, providing technical support for high-real-time, high-complexity scenarios such as autonomous driving and medical image analysis. With the continuous development of quantum technology, it will propel artificial intelligence toward a higher-dimensional computational paradigm.
About WiMi Hologram Cloud
WiMi Hologram Cloud, Inc. (NASDAQ:WiMi) is a holographic cloud comprehensive technical solution provider that focuses on professional areas including holographic AR automotive HUD software, 3D holographic pulse LiDAR, head-mounted light field holographic equipment, holographic semiconductor, holographic cloud software, holographic car navigation and others. Its services and holographic AR technologies include holographic AR automotive application, 3D holographic pulse LiDAR technology, holographic vision semiconductor technology, holographic software development, holographic AR advertising technology, holographic AR entertainment technology, holographic ARSDK payment, interactive holographic communication and other holographic AR technologies.
AI
