Challenges
Datasets
Workspaces
Papers
Discussions
Leaderboard
Log inSign up
Challenges
Datasets
Workspaces
Papers
Discussions
Leaderboard
Blog
Job Board
Q3AS

© 2026 Aqora Quantum S.A.S.

TermsPrivacyLegal Notice

IEEE Transactions on Mobile Computing

Fast Quantum Convolutional Neural Networks for Low-Complexity Object Detection in Autonomous Driving Applications

Emily Jimin Roh, Hankyul Baek, Donghyeon Kim, Joongheon Kim

Published Sep 27, 2024• 35 citations
Publisher

Abstract

Object detection applications, especially in autonomous driving, have drawn attention due to the advancements in deep learning. Additionally, with continuous improvements in classical convolutional neural networks (CNNs), there has been a notable enhancement in both the efficiency and speed of these applications, making autonomous driving more reliable and effective. However, due to the exponentially rapid growth in the complexity and scale of visual signals used in object detection, there are limitations regarding computation speeds while conducting object detection solely with classical computing. Motivated by this, this paper proposes the quantum object detection engine (QODE), which implements a quantum version of CNN, named QCNN, in object detection. Furthermore, this paper proposes a novel fast quantum convolution algorithm that processes the multi-channel of visual signals based on a small number of qubits and constructs the output channel data, thereby achieving relieved computational complexity. Our QODE, equipped with fast quantum convolution, demonstrates feasibility in object detection with multi-channel data, addressing a limitation of current QCNNs due to the scarcity of qubits in the current era of quantum computing. Moreover, this paper introduces a heterogeneous knowledge distillation training algorithm that enhances the performance of our QODE.

DOI
10.1109/tmc.2024.3470328

Related papers

Fast Quantum Convolutional Neural Networks for Low-Complexity Object Detection in Autonomous Driving Applications

Hankyul Baek, Donghyeon Kim, Joongheon Kim

Spurred by consistent advances and innovation in deep learning, object detection applications have become prevalent, particularly in autonomous driving that leverages various visual data. As convolutional neural networks (CNNs) are being optimized, the performances and computation speeds of object detection in autonomous driving have been significantly improved. However, due to the exponentially rapid growth in the complexity and scale of data used in object detection, there are limitations in terms of computation speeds while conducting object detection solely with classical computing. Motivated by this, quantum convolution-based object detection (QCOD) is proposed to adopt quantum computing to perform object detection at high speed. The QCOD utilizes our proposed fast quantum convolution that uploads input channel information and re-constructs output channels for achieving reduced computational complexity and thus improving performances. Lastly, the extensive experiments with KITTI autonomous driving object detection dataset verify that the proposed fast quantum convolution and QCOD are successfully operated in real object detection applications.

arXiv:2401.01370•Dec 28, 2023•2 citations

Quantum-Eyes: Scalable Quantum Convolutional Neural Networks for Low-Overhead Object Detection [Research Frontier]

Joongheon Kim, Emily Jimin Roh, Chaemoon Im +1 more

Quantum neural networks (QNNs) are gaining attention as a promising foundation for next-generation machine learning. However, the practical deployment of QNNs, particularly in vision tasks, remains limited due to hardware constraints such as qubit scarcity. To address this challenge, this paper proposes a quantum convolutional neural network (QCNN)-based object detection framework designed for the noisy intermediate scale quantum (NISQ) era. The proposed method introduces four key components, patch processing, channel uploading, hybrid channel construction, and heterogeneous knowledge distillation, to enable efficient multi-channel object detection with a limited number of qubits. Furthermore, the knowledge distillation strategy facilitates the transfer of knowledge from a classical region proposal network (RPN) to its quantum counterpart, thereby enhancing detection accuracy despite the limitations of early-stage quantum machine learning. The evaluation results demonstrate the feasibility and efficiency of the proposed quantum object detection model, which can be effectively applied to complex vision tasks within existing quantum hardware limitations.

IEEE Computational Intelligence Magazine•Jul 14, 2025•2 citations

Computation-efficient quantum convolutional neural networks for autonomous driving applications

Emily Jimin Roh, Chaemoon Im, Wonjun Jeong +1 more

This paper proposes a computation-efficient quantum convolutional neural network (CE-QCNN) architecture designed for autonomous driving applications. A key contribution of this work lies in the formulation of a tri-value qubit encoding (TQE) scheme, which compactly embeds three-channel RGB image data into single-qubit states via a sequence of quantum rotations. This strategy enables significant qubit resource reduction while preserving the representational richness of multi-channel visual inputs. The encoded quantum states are subsequently processed through parameterized quantum circuits for convolutional feature extraction, forming the core of the proposed CE-QCNN framework. To further improve learning stability and early-stage performance, a knowledge distillation (KD) strategy is employed, transferring supervision from a pretrained classical CNN model to the quantum network. The proposed model is evaluated on the KITTI dataset, a standard benchmark for autonomous driving, where it demonstrates both competitive detection accuracy and reduced computational complexity. These results substantiate the scalability and practical applicability of CE-QCNNs for future quantum-enhanced perception systems in real-time autonomous driving scenarios.

The Journal of Supercomputing•Jun 14, 2025•5 citations

Research on Object Detection Model Based on Quantum Convolutional Neural Network

Hui Gao

In recent years, object detection technology has undergone substantial evolution within the realms of deep learning and computer vision, particularly owing to the extensive utilization of traditional convolutional neural networks (CNNs). These technologies perform well in a variety of applications, such as autonomous driving, security monitoring, and medical image analysis. However, traditional CNNS face many challenges when dealing with complex scenes and small target detection, such as background interference, target scale change and occlusion. In this paper, a novel Hybrid model, Hybrid Quantum-Cascade FPN, is proposed, which cleverly combines the advantages of Quantum convolutional neural network (QCNN) and classical CNN. The design of Hybrid quantum-Cascade FPN model is divided into three key stages: first, the Quantum coarse screening stage, which quickly extracts low-level features through quantum feature coding; Next is the quantum-classical feature fusion stage, which uses the parallelism of quantum computing and the structural advantages of classical networks to carry out multi-scale feature fusion. The last is the classical fine-tuning stage, which further optimizes the model to improve the high-level semantic analysis ability. Experiments on multiple data sets show that the model performs well in both detection accuracy and inference speed, especially in complex background and small target detection tasks.

IEEE International Conference on Power, Intelligent Computing and Systems (ICPICS)•Aug 29, 2025•0 citations

Quantum Convolutional Neural Networks (QCNN) Using Deep Learning for Computer Vision Applications

Varadi Rajesh, Umesh Parameshwar Naik, Mohana

Deep learning algorithms and models have made an impact in the area of AI and machine learning, one among them is CNN. CNN is extensively used in the area of image recognition and object detection for classification purposes. CNN is composed of several layers of filters to get feature maps of input data, yet foremost and crucial one is convolutional layer, hence the name Convolutional neural networks. However, the growth of quantum computing and quantum neural network in deep learning is limited. Three main obstacles that limit the growth of these are, first is due to the lack of real-time quantum computers to experiment with. Second is the improper training algorithms and at last, non-linearity nature of the neural networks. This paper introduces a novel approach to begin one's journey in quantum computing, along with solutions and developments. This work provides a detailed description of architectures, frameworks and algorithms used for implementing a QCNN model. The research was made regarding image recognition and object detection using QCNN and found that QCNN can increase the computational speeds with better performance metrics compared to classical computational methods. This paper also debates about applications of QCNN in computer vision, signal and image processing, Pharmaceuticals, Cryptography and various other fields. This study also explains Key players and future work in developing quantum computers, quantum computing algorithms, software and hardware support to implement QCNN in various applications.

International Conference on Recent Trends on Electronics, Information, Communication & Technology (RTEICT)•Aug 1, 2021•77 citations

Quantum Convolutional Neural Network for Resource-Efficient Image Classification: A Quantum Random Access Memory (QRAM) Approach

Seunghyeok Oh, Jaeho Choi, Jong‐Kook Kim +1 more

Convolutional Neural Network (CNN) is a breakthrough learning model that shows outstanding performance in computer vision and deep learning applications. However, it is a relatively burdened model in terms of learning speed and resource usage compared to other learning models when the learning scale becomes large. Quantum Convolutional Neural Network (QCNN) is a novel model as a potential solution using quantum computers to handle this problem. Quantum computers with a limited number of usable qubits needs a resource-efficient method to process large-scale data at once. In addition, Quantum Random Access Memory (QRAM) can store the large data to qubits logarithmically using superposition and entanglement. The QRAM algorithm can design a new QCNN model that can efficiently process in massive data. This paper proposes a more resource and depth efficient model for larger-sized input data and the number of output channels using the QRAM algorithm and efficiently extracting features.

International Conference on Information Networking•Jan 13, 2021•30 citations
Object detection applications, especially in autonomous driving, have drawn attention due to the advancements in deep learning. Additionally, with continuous improvements in classical convolutional neural networks (CNNs), there has been a notable enhancement in both the efficiency and speed of these applications, making autonomous driving more reliable and effective. However, due to the exponentially rapid growth in the complexity and scale of visual signals used in object detection, there are limitations regarding computation speeds while conducting object detection solely with classical computing. Motivated by this, this paper proposes the quantum object detection engine (QODE), which implements a quantum version of CNN, named QCNN, in object detection. Furthermore, this paper proposes a novel fast quantum convolution algorithm that processes the multi-channel of visual signals based on a small number of qubits and constructs the output channel data, thereby achieving relieved computational complexity. Our QODE, equipped with fast quantum convolution, demonstrates feasibility in object detection with multi-channel data, addressing a limitation of current QCNNs due to the scarcity of qubits in the current era of quantum computing. Moreover, this paper introduces a heterogeneous knowledge distillation training algorithm that enhances the performance of our QODE.
Spurred by consistent advances and innovation in deep learning, object detection applications have become prevalent, particularly in autonomous driving that leverages various visual data. As convolutional neural networks (CNNs) are being optimized, the performances and computation speeds of object detection in autonomous driving have been significantly improved. However, due to the exponentially rapid growth in the complexity and scale of data used in object detection, there are limitations in terms of computation speeds while conducting object detection solely with classical computing. Motivated by this, quantum convolution-based object detection (QCOD) is proposed to adopt quantum computing to perform object detection at high speed. The QCOD utilizes our proposed fast quantum convolution that uploads input channel information and re-constructs output channels for achieving reduced computational complexity and thus improving performances. Lastly, the extensive experiments with KITTI autonomous driving object detection dataset verify that the proposed fast quantum convolution and QCOD are successfully operated in real object detection applications.
Quantum neural networks (QNNs) are gaining attention as a promising foundation for next-generation machine learning. However, the practical deployment of QNNs, particularly in vision tasks, remains limited due to hardware constraints such as qubit scarcity. To address this challenge, this paper proposes a quantum convolutional neural network (QCNN)-based object detection framework designed for the noisy intermediate scale quantum (NISQ) era. The proposed method introduces four key components, patch processing, channel uploading, hybrid channel construction, and heterogeneous knowledge distillation, to enable efficient multi-channel object detection with a limited number of qubits. Furthermore, the knowledge distillation strategy facilitates the transfer of knowledge from a classical region proposal network (RPN) to its quantum counterpart, thereby enhancing detection accuracy despite the limitations of early-stage quantum machine learning. The evaluation results demonstrate the feasibility and efficiency of the proposed quantum object detection model, which can be effectively applied to complex vision tasks within existing quantum hardware limitations.
This paper proposes a computation-efficient quantum convolutional neural network (CE-QCNN) architecture designed for autonomous driving applications. A key contribution of this work lies in the formulation of a tri-value qubit encoding (TQE) scheme, which compactly embeds three-channel RGB image data into single-qubit states via a sequence of quantum rotations. This strategy enables significant qubit resource reduction while preserving the representational richness of multi-channel visual inputs. The encoded quantum states are subsequently processed through parameterized quantum circuits for convolutional feature extraction, forming the core of the proposed CE-QCNN framework. To further improve learning stability and early-stage performance, a knowledge distillation (KD) strategy is employed, transferring supervision from a pretrained classical CNN model to the quantum network. The proposed model is evaluated on the KITTI dataset, a standard benchmark for autonomous driving, where it demonstrates both competitive detection accuracy and reduced computational complexity. These results substantiate the scalability and practical applicability of CE-QCNNs for future quantum-enhanced perception systems in real-time autonomous driving scenarios.
In recent years, object detection technology has undergone substantial evolution within the realms of deep learning and computer vision, particularly owing to the extensive utilization of traditional convolutional neural networks (CNNs). These technologies perform well in a variety of applications, such as autonomous driving, security monitoring, and medical image analysis. However, traditional CNNS face many challenges when dealing with complex scenes and small target detection, such as background interference, target scale change and occlusion. In this paper, a novel Hybrid model, Hybrid Quantum-Cascade FPN, is proposed, which cleverly combines the advantages of Quantum convolutional neural network (QCNN) and classical CNN. The design of Hybrid quantum-Cascade FPN model is divided into three key stages: first, the Quantum coarse screening stage, which quickly extracts low-level features through quantum feature coding; Next is the quantum-classical feature fusion stage, which uses the parallelism of quantum computing and the structural advantages of classical networks to carry out multi-scale feature fusion. The last is the classical fine-tuning stage, which further optimizes the model to improve the high-level semantic analysis ability. Experiments on multiple data sets show that the model performs well in both detection accuracy and inference speed, especially in complex background and small target detection tasks.
Deep learning algorithms and models have made an impact in the area of AI and machine learning, one among them is CNN. CNN is extensively used in the area of image recognition and object detection for classification purposes. CNN is composed of several layers of filters to get feature maps of input data, yet foremost and crucial one is convolutional layer, hence the name Convolutional neural networks. However, the growth of quantum computing and quantum neural network in deep learning is limited. Three main obstacles that limit the growth of these are, first is due to the lack of real-time quantum computers to experiment with. Second is the improper training algorithms and at last, non-linearity nature of the neural networks. This paper introduces a novel approach to begin one's journey in quantum computing, along with solutions and developments. This work provides a detailed description of architectures, frameworks and algorithms used for implementing a QCNN model. The research was made regarding image recognition and object detection using QCNN and found that QCNN can increase the computational speeds with better performance metrics compared to classical computational methods. This paper also debates about applications of QCNN in computer vision, signal and image processing, Pharmaceuticals, Cryptography and various other fields. This study also explains Key players and future work in developing quantum computers, quantum computing algorithms, software and hardware support to implement QCNN in various applications.
Convolutional Neural Network (CNN) is a breakthrough learning model that shows outstanding performance in computer vision and deep learning applications. However, it is a relatively burdened model in terms of learning speed and resource usage compared to other learning models when the learning scale becomes large. Quantum Convolutional Neural Network (QCNN) is a novel model as a potential solution using quantum computers to handle this problem. Quantum computers with a limited number of usable qubits needs a resource-efficient method to process large-scale data at once. In addition, Quantum Random Access Memory (QRAM) can store the large data to qubits logarithmically using superposition and entanglement. The QRAM algorithm can design a new QCNN model that can efficiently process in massive data. This paper proposes a more resource and depth efficient model for larger-sized input data and the number of output channels using the QRAM algorithm and efficiently extracting features.