Quantum convolutional neural networks (QCNNs) are widely regarded as a promising model for quantum machine learning (QML). In this work, we analyze the most widely used variants of these models (i.e., tracing out- and measurement-based QCNNs), and we relate their heuristic success to two facts. First, that when randomly initialized, they can only operate on the information encoded in low-bodyness measurements of their input states. And second, that they are commonly benchmarked on “locally easy” datasets whose states are precisely classifiable by the information encoded in these low-bodyness observables subspace. From these insights, we argue that the QCNN’s action on this subspace should be efficiently classically simulable. Indeed, we construct and train a purely classical QCNN surrogate—based on low-bodyness Pauli propagation, tensor networks, and classical shadows—that matches or outperforms standard QCNNs on all benchmark datasets and on up-to 1024 qubits, thereby empirically realizing our simulability claims. Our results can then be understood as highlighting a deeper symptom of QML: Models could only be showing heuristic success because they are benchmarked on simple problems, for which their action can be classically simulated. This insight points to the fact that nontrivial datasets are a truly necessary ingredient for moving forward with QML. To finish, we discuss how our results can be extrapolated to classically simulate other architectures.
Quantum convolutional neural networks (QCNNs) are widely regarded as a promising model for quantum machine learning (QML). In this work, we analyze the most widely used variants of these models (i.e., tracing out- and measurement-based QCNNs), and we relate their heuristic success to two facts. First, that when randomly initialized, they can only operate on the information encoded in low-bodyness measurements of their input states. And second, that they are commonly benchmarked on “locally easy” datasets whose states are precisely classifiable by the information encoded in these low-bodyness observables subspace. From these insights, we argue that the QCNN’s action on this subspace should be efficiently classically simulable. Indeed, we construct and train a purely classical QCNN surrogate—based on low-bodyness Pauli propagation, tensor networks, and classical shadows—that matches or outperforms standard QCNNs on all benchmark datasets and on up-to 1024 qubits, thereby empirically realizing our simulability claims. Our results can then be understood as highlighting a deeper symptom of QML: Models could only be showing heuristic success because they are benchmarked on simple problems, for which their action can be classically simulated. This insight points to the fact that nontrivial datasets are a truly necessary ingredient for moving forward with QML. To finish, we discuss how our results can be extrapolated to classically simulate other architectures.
Quantum Convolutional Neural Networks (QCNNs) have emerged as one of the most promising architectures in Quantum Machine Learning (QML), enabling hierarchical quantum feature extraction and offering potential advantages over classical CNNs in expressivity and scalability. This study presents a Systematic Literature Review (SLR) on QCNN development from 2019 to 2025, covering theoretical foundations, model architectures, noise resilience, benchmark performance, and applications in materials informatics, chemistry, image recognition, quantum phase classification, and cybersecurity. The SLR followed PRISMA guidelines, screening 214 publications and selecting 47 primary studies. The review finds that QCNNs consistently outperform classical baselines in small-data and high-dimensional regimes due to quantum feature maps and entanglement-driven locality. Significant limitations include noise sensitivity, limited qubit availability, and a lack of standardized datasets for benchmarking. The novelty of this work lies in providing the first comprehensive synthesis of QCNN research across theory, simulations, and real-hardware deployment, offering a roadmap for research gaps and future directions. The findings confirm that QCNNs are strong candidates for NISQ-era applications, especially in physics-informed learning.
As image datasets grow in scale and complexity, classical convolutional neural networks (CNNs) increasingly face limitations in computational efficiency, scalability, and generalisation in low-data regimes. Quantum machine learning (QML) offers a promising alternative, with quantum convolutional neural networks (QCNNs) exploiting quantum parallelism and entanglement for feature extraction. This paper introduces the Novel Quantum Convolutional Neural Network (No-QCNN), which differs from recent hybrid QCNN/QCQ-CNN architectures by employing an end-to-end quantum convolution-pooling pipeline without inserting an intermediate classical CNN block. No-QCNN is a hybrid quantum-classical model that employs a variational quantum classifier (VQC) optimised via the COBYLA algorithm and is designed for binary and multiclass classification of low-resolution colour images on near-term quantum devices. A key innovation is a problem-specific quantum feature map that pre-processes each image into a structured three-dimensional block-matrix representation, jointly encoding pixel colour (R, G, B) and spatial position before mapping this information into a hierarchical ZZFeatureMap. This encoding captures spatial-chromatic correlations at shallow circuit depth, making it compatible with noisy intermediate-scale quantum (NISQ) constraints. The model is implemented using IBM-Qiskit on a local quantum simulator and benchmarked against a classical CNN. For a six-class classification task on a 50-image dataset, No-QCNN achieves a validation accuracy of 82.05%, substantially outperforming the classical CNN's 40.00%, indicating improved generalisation and reduced overfitting in low-data, multiclass settings. Conversely, for a simpler binary classification task, the classical CNN achieves perfect validation accuracy of 100%, surpassing the No-QCNN's 89.7%. We further observe that No-QCNN performance declines with increasing dataset size and training time due to limited circuit expressibility, data-encoding overhead, and finite-sampling noise inherent to NISQ models. Overall, these results position No-QCNN as a complementary framework best suited to low-data, correlation-rich classification tasks, defining a realistic niche for quantum-enhanced artificial vision and quantum perception in the NISQ era.
Quantum Machine Learning (QML) has recently emerged as a highly promising research frontier. Within this domain, Quantum Neural Networks (QNNs),characterized by Variational Quantum Circuits (VQCs) at their core and featuring layers of quantum gates optimized by classical algorithms, have garnered significant attention. However, a rigorous and exhaustive evaluation of their practical performance remains largely incomplete. In this study, we conduct a comprehensive comparative analysis of three prominent hybrid classical-quantum architectures: Quantum Convolutional Neural Networks (QCNN), Quantum Recurrent Neural Networks (QRNN), and Quantum Vision Transformers (QViT), focusing on the critical dimensions of generalization, accuracy, and robustness. Our findings provide novel insights that address previous evaluative gaps. Notably, while these models exhibit exceptional performance on low-feature datasets such as MNIST, their learning efficacy degrades significantly when transitioned to high-feature datasets. Furthermore, convolutional-based models like QCNN appear less effective on high-dimensional data than other machine learning architectures. Additionally, while all models are susceptible to adversarial noise, traditional architectures, such as recurrent and convolutional networks, demonstrate superior resilience. Conversely, in the presence of quantum noise, the transformer-based architecture proves its strength by maintaining high robustness against measurement noise, channel noise, and finite-shot effects, whereas other architectures suffer marked performance declines. These results provide a granular perspective on the current state of the field and underscore the critical importance of tailoring model selection to the constraints of contemporary Noisy Intermediate-Scale Quantum (NISQ) environments.
This work presents a study of an implementation of a novel Quantum Convolutional Neural Network (QCNN) for binary classification of images from the Modified National Institute of Standards and Technology (MNIST) dataset. Using a novel architecture inspired by previous QCNN and classical convolutional neural network (CNN) implementations, we use a hierarchical partitioning approach to implement a QCNN circuit that can be approximated and simulated efficiently on a classical machine for a large problem. First, the original image is partitioned such that each process handles a smaller portion of the image, which is encoded into independent states. Then, these partitions merge and combine, resulting in states that contain information from both partitions while halving the number of processes. After repeating this until one process remains, we reduce the dimensionality of the state until a single qubit remains for measurement. Using this approach, we can use multiple processes in parallel to simulate a large QCNN program without the need for exponentially growing hardware requirements as the number of qubits increases. In our work, we use this scheme to train a 128-qubit model, which is impossible to run on any classical supercomputer without the novel architecture. We also explore the impact of this new model architecture on prediction accuracy by training it to perform binary classification on the MNIST dataset with a small number of qubits, and comparing it to a model without partitioning. Our initial findings show that partitioning images into smaller sub-images with this architecture does not degrade the model's performance and sometimes even improves it, likely because it reduces the Barren plateaus issue in the partitioning process.
We benchmark quantum convolutional neural networks (QCNNs) and their classical surrogates for phase differentiation in one-dimensional strongly correlated systems with beyond-nearest-neighbour terms. Using an anisotropic Heisenberg spin chain and an extended t-t′ Fermi-Hubbard model as representative spin and fermionic testbeds, we train QCNN classifiers on labelled ground-state datasets and map out finite-size phase diagrams. In hybrid setups, we employ Pauli backpropagation to express the QCNN measurement as a weighted sum of Pauli-string expectation values to be evaluated directly on input states, and study how truncation parameters control the trade-off between approximation accuracy and the size of the resulting Pauli expansion. Robust convergence is achieved for the Heisenberg model under aggressive truncation, whereas the Fermi-Hubbard model requires substantially looser thresholds, resulting in a sharp growth in retained Pauli strings and evaluation cost. Our results contribute to charting where hybrid quantum-classical training is viable for learning strongly correlated quantum states, and provide practical guidance for choosing truncation regimes in Pauli backpropagation-based surrogates.
Quantum machine learning is a promising paradigm for learning from limited data, a central bottleneck in domains such as medical imaging, clinical trials, and rare diseases. Quantum convolutional neural networks (QCNNs) are particularly attractive in this setting, combining a hierarchical architecture with strong inductive bias and a parameter count that grows only logarithmically with system size. Their appeal rests on the generalization bounds of Caro et al. (2022), which show that the generalization error of a quantum model scales with the number of trainable parameters rather than with the Hilbert-space dimension, placing QCNNs in a potentially sample-efficient regime. We develop a hardware-compatible QCNN with mid-circuit measurement and classical feed-forward, and show on a binary handwritten-digit task that strong test performance is achievable from as few as 10 training samples, with the generalization error decreasing as the training set grows. At a matched 45-parameter budget the QCNN learns where an equally small classical convolutional network stays at chance, although an unconstrained classical baseline with roughly 25,000 parameters remains strongest when data are plentiful. Transpiling amplitude and angle encoded circuits across image resolutions from 2x2 to 512x512 pixels then exposes the dominant scaling bottleneck: amplitude encoding stays qubit-efficient but grows extremely deep, whereas angle encoding stays shallow but becomes qubit-prohibitive. On the medically motivated BreastMNIST benchmark the QCNN does not surpass the unconstrained classical network, yet it learns consistently above chance using orders of magnitude fewer parameters. Our results indicate that for QCNNs, learning from few samples is attainable in practice, whereas scaling to realistic image data is constrained less by optimization than by data encoding and hardware execution.