Adversarial learning is of paramount importance in numerous recent computing areas, while quantum entanglement has also revealed its role in efficient computing. This motivated us to bring quantum computing into adversarial learning. Though there are some preliminary theoretical studies of quantum adversarial learning (QAL), there has no demonstration of advanced real-world applications. For the first time, we design and implement a QAL framework, and demonstrate the feasibility of QAL-based hyperspectral image processing for remote sensing. This research line aims to lay the foundation for the QAL in hyperspectral remote sensing, including to solve the limited qubit resources, to mitigate the quantum collapse effect, to design a quantum discriminator with comparable ability, as well as to ensure the quantum expressibility of the generator, to name a few.
Adversarial learning is of paramount importance in numerous recent computing areas, while quantum entanglement has also revealed its role in efficient computing. This motivated us to bring quantum computing into adversarial learning. Though there are some preliminary theoretical studies of quantum adversarial learning (QAL), there has no demonstration of advanced real-world applications. For the first time, we design and implement a QAL framework, and demonstrate the feasibility of QAL-based hyperspectral image processing for remote sensing. This research line aims to lay the foundation for the QAL in hyperspectral remote sensing, including to solve the limited qubit resources, to mitigate the quantum collapse effect, to design a quantum discriminator with comparable ability, as well as to ensure the quantum expressibility of the generator, to name a few.
Considering that there are many NP-hard problems in remote sensing (e.g., Craig simplex computation in hyperspectral un-mixing), it is natural to introduce quantum computing into space remote sensing. However, current quantum computers have some practical limitations, requiring complementary techniques to support quantum computing. Specifically, we are introducing artificial intelligence (AI) to solve the quantum collapse effect and the phenomenon of insufficient quantum bits (qubits). We thereby propose the hyperspectral quantum deep network (HyperQUEEN) for satellite remote sensing. HyperQUEEN is the first quantum technology that successfully outputs a complete hyperspectral image, given the very limited qubit resources. Existing quantum image processing methods can only achieve classification-level tasks or simple geometry transforms, and are far from being applicable to advanced satellite missions like restoration of damaged hyperspectral images, which HyperQUEEN has successfully achieved for the first time. Remarkable computational efficiency and restoration performances achieved by the radically new quantum AI system—HyperQUEEN—will be reported.
In recent years, deep learning algorithms have shown promising results for different image analyzing tasks, particularly in remote sensing image processing. Inspired by the success of remote sensing sensors in geo-located imagery, many studies have been carried out on remote sensing sensors for image processing, which brings a new approach into intelligent remote sensing and photogrammetric computer vision. At the same time, algorithms for quantum processors have been shown to efficiently solve some issues that are intractable on conventional, classical processors. This study summarizes the novel techniques of deep learning and quantum deep learning and its research progress and real-world applications in remote sensing image processing, introduces the current main challenges in processing and its development of geo-located datasets, focuses on the analysis and elaboration of the research status of quantum deep learning in sensing and imaging, and on this basis, summarizes the intelligent remote sensing applications and their application effects in scene understanding.
Quantum science just winning the 2022 Nobel Prize in Physics must lead future development of remote sensing technologies. However, given the very limited number of entangled quantum bits (qubits) even in the most advanced quantum computers, is processing remotely sensed hyperspectral image (featured by its large data volume) using quantum computer technically feasible? Even if the quantum image state can be well processed to the quantum state of the target image (QSTI), it cannot be perfectly retrieved/output as the QSTI will collapse to some eigenstate once it is measured. Owing to these challenges, current quantum image processing technologies can only achieve classification-level applications requiring just a few output qubits. We design a hyperspectral quantum deep network (HyperQUEEN) to encode the hyperspectral information using very few qubits, as well as to learn the mapping from some measuring statistics (associated with the collapsed-QSTI) to the target image (instead of directly retrieving the unobservable QSTI), thereby solving the challenges. HyperQUEEN is the first quantum architecture that makes a breakthrough to blindly reconstruct NASA’s damaged hyperspectral images, which means a lot for the upcoming space era. As the immature quantum facility nowadays does not yet allow us to fully exhibit its high potential, we are not aiming at developing state-of-the-art methods, but are demonstrating the feasibility of quantum hyperspectral remote sensing. Mathematical analysis guiding our design toward the low-rank quantum deep network, together with comprehensive experiments, will also be reported.
Quantum machine intelligence starts showing its impact on satellite remote sensing (SRS). Also, recent literature exhibits that quantum generative intelligences encompass superior potential than their classical counterpart, motivating us to develop quantum generative adversarial networks (GANs) for SRS. However, existing quantum GANs are restricted by the limited quantum bit (qubit) resources of current quantum computers and process merely a small 2 × 2 grayscale image, far from being applicable to SRS. Recently, the novel concept of hybrid quantum-classical GAN, a quantum generator with a classical discriminator, has upgraded the order to 28 × 28 (still grayscale), whereas it is still insufficient for SRS. This motivates us to design a radically new hybrid framework, where both generator and discriminator are hybrid architectures. We demonstrate this feasibility, leading to a breakthrough of processing 128×128 hyperspectral images for SRS. Specifically, we design the quantum part with mathematically provable quantum full expressibility (FE) to address core signal processing tasks, wherein the FE property allows the quantum network to realize any valid quantum operator with appropriate training. The classical part, composed of convolutional layers, treats the read-in (compressing the optical information into limited qubits) and read-out (addressing the quantum collapse effect) procedures. The proposed innovative hybrid quantum GAN, named “Hyperspectral Knot-like IntelligeNt dIscrimiNator and Generator” (HyperKING), where “knot” partly symbolizes the quantum entanglement and partly the compressed quantum domain in the central part of the network architecture. HyperKING significantly surpasses the classical approaches in hyperspectral tensor completion, mixed noise removal (about 3dB improvement), and blind source separation results.
Quantum computing changes the way computational problems can be solved by taking advantage of special qubit features such as superposition and entanglement. Owing to these features, a quantum computer can efficiently search through a large amount of solution space and therefore tackle problems that are otherwise too hard for classical computers. In the field of quantum machine learning (QML), Quantum Generative Adversarial Networks (QGANs) are coming to the forefront as a very productive area. QGANs are based on the experimentally successful classical Generative Adversarial Networks (GANs) and, therefore, utilize an adversarial approach, where a generator competes with a discriminator. The data-synthesizing unit called the generator tries to generate data samples that are statistically similar to the actual data, while the discriminator tries to tell the real data apart from any artificially created data samples. Such layers of adversarial-tuned feedback culminate in the improvement of the generator in making realistic simulated data. Even though a considerable amount of research is already published that substantiates the numerous prospects of quantum computing but still the practical implementation of it seems hypothetical. Even so, QGANs are likely to revolutionize many fields by making it possible to synthesize new and fascinating complex realistic data. This review work aims to serve as a valuable resource for researchers and practitioners interested in understanding the exciting field of QGANs and their potential contributions to the broader landscape of quantum machine learning.
Quantum computing is a research field that aims at developing computational models that leverage quantum phenomena. The growing interest in the field of machine learning as well as the recent development of available quantum hardware has motivated researchers to combine the two research areas, giving rise to the interdisciplinary field of quantum machine learning. This chapter offers an overview of the basic theoretical notions of quantum computing and quantum machine learning as well as how it can be applied in image processing use-cases. Specific attention is given to hybrid quantum-classical models, which combine the capabilities of quantum and classical computing. Some example applications employing both gate-based quantum computing and quantum annealing to real image processing tasks within the field of remote sensing are also illustrated and discussed.