Hybrid Quantum-Classical Neural Network for LAB Color Space Image Classification

• URL: http://arxiv.org/abs/2406.02229v1
• Date: Tue, 4 Jun 2024 11:46:56 GMT
• Title: Hybrid Quantum-Classical Neural Network for LAB Color Space Image Classification
• Authors: Kwokho Ng, Tingting Song,
• Abstract summary: Quantum convolutional neural networks (QCNNs) are structurally similar to classical convolutional neural networks. We show that two channels consistently exhibit higher classification accuracy in images from different color spaces than the third.
• Score: 1.565361244756411
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Parameterized quantum circuits (PQCs) are essential in many variational quantum algorithms. Quantum convolutional neural networks (QCNNs), which are structurally similar to classical convolutional neural networks, possess the capability to extract informative features and have shown significant effectiveness in image classification tasks. To achieve higher image classification accuracy and reduce the number of training parameters, modifications to the structure of PQCs or hybrid quantum-classical convolutional neural network (HQCCNN) models are typically employed. The image datasets used in these learning models are usually RGB images. We investigate the effects of different color spaces to explore the potential for reducing the resources required for quantum computation. By utilizing a simple HQCCNN model with existing PQCs, we analyze the performance of each channel in various color space images. Experimental results reveal that two channels consistently exhibit higher classification accuracy in images from different color spaces than the third. Specifically, the L channel of LAB color space images achieves superior classification accuracy when employing a more complex PQC. Additionally, PQCs utilizing controlled rotation X-gates outperform those using controlled selection Z-gates in this classification task.

Related papers

• Towards Efficient Quantum Hybrid Diffusion Models [68.43405413443175]
  We propose a new methodology to design quantum hybrid diffusion models. We propose two possible hybridization schemes combining quantum computing's superior generalization with classical networks' modularity.
  arXiv  Detail & Related papers  (2024-02-25T16:57:51Z)
• Studying the Impact of Quantum-Specific Hyperparameters on Hybrid Quantum-Classical Neural Networks [4.951980887762045]
  hybrid quantum-classical neural networks (HQNNs) represent a promising solution that combines the strengths of classical machine learning with quantum computing capabilities. In this paper, we investigate the impact of these variations on different HQNN models for image classification tasks, implemented on the PennyLane framework. We aim to uncover intuitive and counter-intuitive learning patterns of HQNN models within granular levels of controlled quantum perturbations, to form a sound basis for their correlation to accuracy and training time.
  arXiv  Detail & Related papers  (2024-02-16T11:44:25Z)
• Hybrid Quantum Neural Network Structures for Image Multi-classification [0.0]
  Two recent image classification methods have emerged, one employs PCA dimensionality reduction and angle encoding, the other integrates QNNs into CNNs to boost performance. This study explores these algorithms' performance in multi-class image classification and proposes an optimized hybrid quantum neural network suitable for the current environment.
  arXiv  Detail & Related papers  (2023-08-30T12:48:05Z)
• Quantum machine learning for image classification [39.58317527488534]
  This research introduces two quantum machine learning models that leverage the principles of quantum mechanics for effective computations. Our first model, a hybrid quantum neural network with parallel quantum circuits, enables the execution of computations even in the noisy intermediate-scale quantum era. A second model introduces a hybrid quantum neural network with a Quanvolutional layer, reducing image resolution via a convolution process.
  arXiv  Detail & Related papers  (2023-04-18T18:23:20Z)
• Problem-Dependent Power of Quantum Neural Networks on Multi-Class Classification [83.20479832949069]
  Quantum neural networks (QNNs) have become an important tool for understanding the physical world, but their advantages and limitations are not fully understood. Here we investigate the problem-dependent power of QCs on multi-class classification tasks. Our work sheds light on the problem-dependent power of QNNs and offers a practical tool for evaluating their potential merit.
  arXiv  Detail & Related papers  (2022-12-29T10:46:40Z)
• Photonic Quantum Computing For Polymer Classification [62.997667081978825]
  Two polymer classes visual (VIS) and near-infrared (NIR) are defined based on the size of the polymer gaps. We present a hybrid classical-quantum approach to the binary classification of polymer structures.
  arXiv  Detail & Related papers  (2022-11-22T11:59:52Z)
• On Circuit-based Hybrid Quantum Neural Networks for Remote Sensing Imagery Classification [88.31717434938338]
  The hybrid QCNNs enrich the classical architecture of CNNs by introducing a quantum layer within a standard neural network. The novel QCNN proposed in this work is applied to the Land Use and Land Cover (LULC) classification, chosen as an Earth Observation (EO) use case. The results of the multiclass classification prove the effectiveness of the presented approach, by demonstrating that the QCNN performances are higher than the classical counterparts.
  arXiv  Detail & Related papers  (2021-09-20T12:41:50Z)
• RGB Image Classification with Quantum Convolutional Ansaetze [18.379304679643436]
  We propose two types of quantum circuit ansaetze to simulate convolution operations on RGB images. To the best of our knowledge, this is the first work of a quantum convolutional circuit to deal with RGB images effectively. We also investigate the relationship between the size of quantum circuit ansatz and the learnability of the hybrid quantum-classical convolutional neural network.
  arXiv  Detail & Related papers  (2021-07-23T09:38:59Z)
• Toward Trainability of Quantum Neural Networks [87.04438831673063]
  Quantum Neural Networks (QNNs) have been proposed as generalizations of classical neural networks to achieve the quantum speed-up. Serious bottlenecks exist for training QNNs due to the vanishing with gradient rate exponential to the input qubit number. We show that QNNs with tree tensor and step controlled structures for the application of binary classification. Simulations show faster convergent rates and better accuracy compared to QNNs with random structures.
  arXiv  Detail & Related papers  (2020-11-12T08:32:04Z)
• The Heterogeneity Hypothesis: Finding Layer-Wise Differentiated Network Architectures [179.66117325866585]
  We investigate a design space that is usually overlooked, i.e. adjusting the channel configurations of predefined networks. We find that this adjustment can be achieved by shrinking widened baseline networks and leads to superior performance. Experiments are conducted on various networks and datasets for image classification, visual tracking and image restoration.
  arXiv  Detail & Related papers  (2020-06-29T17:59:26Z)
• Recurrent Quantum Neural Networks [7.6146285961466]
  Recurrent neural networks are the foundation of many sequence-to-sequence models in machine learning. We construct a quantum recurrent neural network (QRNN) with demonstrable performance on non-trivial tasks. We evaluate the QRNN on MNIST classification, both by feeding the QRNN each image pixel-by-pixel; and by utilising modern data augmentation as preprocessing step.
  arXiv  Detail & Related papers  (2020-06-25T17:59:44Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.