Corpus ID: 237572283

On Circuit-based Hybrid Quantum Neural Networks for Remote Sensing Imagery Classification

  title={On Circuit-based Hybrid Quantum Neural Networks for Remote Sensing Imagery Classification},
  author={Alessandro Sebastianelli and Daniela A. Zaidenberg and Dario Spiller and B. L. Saux and Silvia Liberata Ullo},
This article aims to investigate how circuit-based hybrid Quantum Convolutional Neural Networks (QCNNs) can be successfully employed as image classifiers in the context of remote sensing. 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, and tested on the EuroSAT dataset used… Expand


A Tutorial on Quantum Convolutional Neural Networks (QCNN)
Whether the QCNN model is capable of efficient learning compared to CNN through training using the MNIST dataset through the TensorFlow Quantum platform is verified. Expand
Hyperspectral Image Classification With CapsNet and Markov Random Fields
A new remote sensing hyperspectral image classification algorithm called Conv-Caps is proposed to make full use of the advantages of both spectral and spatial information and is compared with the latest methods to find the framework can produce competitive classification performance. Expand
Quanvolutional neural networks: powering image recognition with quantum circuits
A new type of transformational layer called a quantum convolution, or quanvolutional layer is introduced, which operates on input data by locally transforming the data using a number of random quantum circuits, in a way that is similar to the transformations performed by random convolutional filter layers. Expand
Methods for accelerating geospatial data processing using quantum computers
A performance improvement over previous quantum efforts in this domain is found and potential refinements that could lead to an eventual quantum advantage are identified: the quanvolutional neural network. Expand
Vision Transformers for Remote Sensing Image Classification
A remote-sensing scene-classification method based on vision transformers that obtains an average classification accuracy of 98.49%, and it is shown experimentally that the network can be compressed by pruning half of the layers while keeping competing classification accuracies. Expand
Approaching Remote Sensing Image Classification with Ensembles of Support Vector Machines on the D-Wave Quantum Annealer
The classification of Remote Sensing (RS) multispectral images with SVMs trained on a QA is discussed and an open code repository is released to facilitate an early entry into the practical application of QA, a new disruptive compute technology. Expand
Introducing Eurosat: A Novel Dataset and Deep Learning Benchmark for Land Use and Land Cover Classification
This paper presents a novel dataset based on Sentinel-2 satellite images covering 13 different spectral bands and consisting of 10 classes with in total 27,000 labeled images, and demonstrates how the classification system can assist in improving geographical maps. Expand
Multi-Spectral Image Classification with Quantum Neural Network
  • P. Gawron, S. Lewinski
  • Computer Science
  • IGARSS 2020 - 2020 IEEE International Geoscience and Remote Sensing Symposium
  • 2020
This work investigates application of quantum circuit based neural network classifiers for multi-spectral data classification aimed at obtaining the land cover information using data acquired from Earth observation satellites. Expand
Quantum-Enhanced Deep Learning-Based Lithology Interpretation From Well Logs
The proposed quantum-enhanced deep-learning (QEDL) model achieves comparable model performance with a clearly improved generalization power for interpreting both thin and thick lithology layers. Expand
Semantic Segmentation of Earth Observation Data Using Multimodal and Multi-scale Deep Networks
This work investigates the use of deep fully convolutional neural networks (DFCNN) for pixel-wise scene labeling of Earth Observation images. Especially, we train a variant of the SegNet architectureExpand