Image classification is a core task of intelligent sensing, conventionally follows a sequential imaging then processing pipeline. However, redundant high-dimensional image reconstruction is inherently inefficient, especially in photon limited scenarios. Here we report a photon level image classification method using quantum compressed sensing, which reformulates the classification task as a sparse signal measurement problem directly oriented toward class labels. By exploiting the parallelism of photonic quantum superposition states, a single photon can be encoded the complete spatial information of a high-dimensional image. Through a diffractive deep neural network, we physically construct a dedicated measurement basis aligned with the class space, enabling signal-dependent adaptive compressive measurement. Ideally, our method can extract class information via a single quantum projective measurement, reducing the required number of measurements from the logarithmic scaling O(Klog(N/K)) of classical compressed sensing to the constant-order information-theoretic limit M = K = 1. Experimental results show that a classification accuracy of 69.0% can be achieved by using a single-photon detection event as the decision criterion, while it increases to 95.0% with four-photon detection events. This work demonstrates image classification at the energy efficiency limit and introduces a measurement as decision framework. It provides a foundation for intelligent sensing systems that operate under extreme photon budgets and harsh environments.
Image classification is a core task of intelligent sensing, conventionally follows a sequential imaging then processing pipeline. However, redundant high-dimensional image reconstruction is inherently inefficient, especially in photon limited scenarios. Here we report a photon level image classification method using quantum compressed sensing, which reformulates the classification task as a sparse signal measurement problem directly oriented toward class labels. By exploiting the parallelism of photonic quantum superposition states, a single photon can be encoded the complete spatial information of a high-dimensional image. Through a diffractive deep neural network, we physically construct a dedicated measurement basis aligned with the class space, enabling signal-dependent adaptive compressive measurement. Ideally, our method can extract class information via a single quantum projective measurement, reducing the required number of measurements from the logarithmic scaling O(Klog(N/K)) of classical compressed sensing to the constant-order information-theoretic limit M = K = 1. Experimental results show that a classification accuracy of 69.0% can be achieved by using a single-photon detection event as the decision criterion, while it increases to 95.0% with four-photon detection events. This work demonstrates image classification at the energy efficiency limit and introduces a measurement as decision framework. It provides a foundation for intelligent sensing systems that operate under extreme photon budgets and harsh environments.
The rapid growth of machine learning is increasingly constrained by the energy and bandwidth limits of classical hardware. Optical and quantum technologies offer an alternative route, enabling high-dimensional, parallel information processing directly in the physical layer, particularly suited for imaging tasks. In this context, quantum photonic platforms provide both a natural mechanism for computing inner products and a promising path to energy-efficient inference in photon-limited regimes. Here, we experimentally demonstrate a camera-free quantum-optical images classifier that performs inference directly at the measurement layer using Hong-Ou-Mandel (HOM) interference of spatially programmable single photons. Two-photon coincidences directly report the overlap between an input image mode and a learned template, replacing pixel-resolved acquisition with a single global measurement. We realize both a single-perceptron quantum optical neuron and a two-neuron shallow network, achieving high accuracy on benchmark datasets with strong robustness to experimental noise and minimal hardware complexity. With a fixed measurement budget, performance remains insensitive to input resolution, demonstrating intrinsic robustness to the number of pixels, which would be impossible in a classical framework. This approach paves the way toward neuromorphic quantum photonic processors capable of extracting task-relevant information directly from HOM interference, with promising applications in remote object recognition, low-signal sensing, and photon-starved biological microscopy.
How many measurements are fundamentally required to capture a signal. Shannon's information theory established the bedrock of this question in 1948, the Nyquist Shannon theorem set the first answer, and compressed sensing (CS) rewrote it in 2006 by reducing the required measurement number to M = O(Klog(N/K)) for a K sparse signal. Here, we propose quantum compressed sensing (QCS), a paradigm that reframes signal acquisition as a unitary quantum evolution. By encoding high dimensional signal information into a single quantum probe state, then introducing domain-alignment evolution,a physically realizable unitary transformation that maps the sparse basis directly onto the measurement basis. QCS executes the support-set search at the quantum level without consuming measurement trials. The logarithmic penalty vanishes, compressing the required measurement number from the classical bound to M =O(K) and reducing reconstruction from ill posed optimization to linear estimation. We experimentally validate QCS using frequency and time domain sparse signals, confirming that the measurement number scales linearly with sparsity and decouples entirely from the signal dimension. Our work provides a physical pathway toward ultimate information acquisition efficiency, with broad implications for sensing, imaging, and communication.
Abstract Object identification is central to modern sensing, widely employed in autonomous systems and industrial inspection. However, conventional approaches rely on image formation followed by computational inference, requiring many photons to suppress shot noise and introducing readout and computational latencies. These limitations arise because direct position-basis measurement is not optimized for discriminating object-encoded states. Here, we demonstrate single-photon object identification without imaging by implementing quantum state discrimination in a high-dimensional spatial Hilbert space. By applying a task-optimized unitary transformation prior to wavefunction collapse, we transform spatially overlapping object-encoded wavefields into spatially separated states. Thus, the measurement basis is engineered so that the collapse of the single-photon state directly specifies the object label. Numerically, our method achieves 90.2% identification accuracy for nine objects, surpassing the 31.9% classical limit obtained from maximum-likelihood single-photon intensity imaging. Experimentally, the framework achieves 71.0% conditional identification accuracy under attenuated coherent illumination with camera detection, and is further demonstrated with heralded single photons using only 36 detection channels. Our framework establishes a quantum-measurement approach to information-efficient sensing that connects quantum state discrimination with computational optics, providing a route toward low-photon and ultrafast object identification.
Quantum neural networks (QNNs) integrate the advantages of quantum information with the formidable capabilities of classical neural networks, exhibiting notable potential in image classification tasks. However, the performance of current QNNs in processing multi-class image classification tasks still leaves room for improvement. In this paper, we propose three QNN architectures to enhance the accuracy of multi-class image classification by utilizing techniques of overparameterization, dense pooling, and local feature extraction. These networks are capable of mapping conventional data to the amplitudes of quantum states via amplitude encoding, eschewing the need for traditional dimensionality reduction techniques. Following processing with parameterized quantum circuits (PQCs), we conduct quantum measurements to extract feature information. We validate the proposed architectures using the MNIST dataset for eight-class image classification problems. The experimental results unequivocally demonstrate that the three techniques we employed significantly enhance the accuracy of QNNs in multi-class image classification tasks.
Quantum sensing can enhance imaging performance by reducing measurement noise below the classical limit, thereby improving the signal-to-noise ratio (SNR) of acquired data. In conventional quantum imaging schemes, squeezing is applied independently to each pixel or spatial mode, leading to a quantum resource cost that scales linearly with image dimension. This approach implicitly separates quantum enhancement from classical post-processing, treating them as independent layers. In this work, we demonstrate that integrating quantum resource allocation with the guidance from classical compressive imaging, via co-design between the quantum hardware layer and the classical software layer, substantially reduces the required quantum resources. We employ principal component analysis (PCA) to identify a low-dimensional principal component subspace for measurement and apply squeezing selectively to the most informative spatial modes corresponding to these principal components. Our numerical experiments show that high-accuracy image classification and high-fidelity image reconstruction can be achieved with significantly fewer squeezed modes compared to pixel-wise squeezing. Our results establish a joint quantum classical co-design framework for resource-efficient quantum-enhanced imaging.
Image classification has become a fundamental task in computer vision with applications in areas such as medical imaging, agriculture, environmental monitoring, and automated surveillance. Traditional machine learning techniques have achieved reasonable performance in classification tasks; however, they often struggle when dealing with high-dimensional and complex image datasets. Deep learning models, particularly Convolutional Neural Networks (CNNs), have significantly improved image classification performance by automatically learning hierarchical feature representations. Despite these advancements, classical deep learning models may still face challenges related to computational complexity and large-scale data processing.In recent years, quantum machine learning has emerged as a promising paradigm that combines principles of quantum computing with classical machine learning techniques to enhance computational efficiency and model performance. This study proposes a hybrid quantum–classical framework for image classification that integrates a deep residual network (ResNet-50) with a Quantum Support Vector Machine (QSVM). The ResNet-50 model is employed as a feature extraction mechanism to capture high-level visual representations from image data. The extracted features are then reduced in dimensionality using Principal Component Analysis (PCA) to simplify the feature space and improve computational efficiency.The reduced feature vectors are subsequently classified using a QSVM model that utilizes quantum feature maps to encode classical data into quantum states. Various quantum feature maps are explored to evaluate their impact on classification performance. Experimental results demonstrate that the hybrid quantum–classical approach achieves higher classification accuracy compared to conventional machine learning models such as Support Vector Machines and Random Forest classifiers. The proposed framework highlights the potential of combining classical deep learning architectures with quantum machine learning algorithms to address complex image classification challenges. This hybrid approach provides an efficient and scalable solution for advanced image analysis tasks and demonstrates the growing potential of quantum computing in artificial intelligence applications.