Fidelity Constraints Research Articles

HEAL: High-Frequency Enhanced and Attention-Guided Learning Network for Sparse-View CT Reconstruction.

X-ray computed tomography (CT) imaging technology has become an indispensable diagnostic tool in clinical examination. However, it poses a risk of ionizing radiation, making the reduction of radiation dose one of the current research hotspots in CT imaging. Sparse-view imaging, as one of the main methods for reducing radiation dose, has made significant progress in recent years. In particular, sparse-view reconstruction methods based on deep learning have shown promising results. Nevertheless, efficiently recovering image details under ultra-sparse conditions remains a challenge. To address this challenge, this paper proposes a high-frequency enhanced and attention-guided learning Network (HEAL). HEAL includes three optimization strategies to achieve detail enhancement: Firstly, we introduce a dual-domain progressive enhancement module, which leverages fidelity constraints within each domain and consistency constraints across domains to effectively narrow the solution space. Secondly, we incorporate both channel and spatial attention mechanisms to improve the network's feature-scaling process. Finally, we propose a high-frequency component enhancement regularization term that integrates residual learning with direction-weighted total variation, utilizing directional cues to effectively distinguish between noise and textures. The HEAL network is trained, validated and tested under different ultra-sparse configurations of 60 views and 30 views, demonstrating its advantages in reconstruction accuracy and detail enhancement.

Generating Universal Adversarial Perturbations for Quantum Classifiers

Quantum Machine Learning (QML) has emerged as a promising field of research, aiming to leverage the capabilities of quantum computing to enhance existing machine learning methodologies. Recent studies have revealed that, like their classical counterparts, QML models based on Parametrized Quantum Circuits (PQCs) are also vulnerable to adversarial attacks. Moreover, the existence of Universal Adversarial Perturbations (UAPs) in the quantum domain has been demonstrated theoretically in the context of quantum classifiers. In this work, we introduce QuGAP: a novel framework for generating UAPs for quantum classifiers. We conceptualize the notion of additive UAPs for PQC-based classifiers and theoretically demonstrate their existence. We then utilize generative models (QuGAP-A) to craft additive UAPs and experimentally show that quantum classifiers are susceptible to such attacks. Moreover, we formulate a new method for generating unitary UAPs (QuGAP-U) using quantum generative models and a novel loss function based on fidelity constraints. We evaluate the performance of the proposed framework and show that our method achieves state-of-the-art misclassification rates, while maintaining high fidelity between legitimate and adversarial samples.

Mesh-Based Double-Sided Freeform Lens Optimization

We present a mesh-based method for optimizing double-sided freeform lenses to control their caustic effects. Unlike traditional single-sided approaches, we optimize both sides of the lens simultaneously, using a bijective correspondence between the two sides to control light refraction paths. Our approach balances image fidelity, geometric compatibility, and physical constraints. Results demonstrate the method’s capability to accurately produce intricate light patterns, opening new possibilities in optical applications.

Advanced Pipeline for Designing Multi-Locus TMS Coils With Current Density Constraints

This work aims for a method to design manufacturable windings for transcranial magnetic stimulation (TMS) coils with fine control over the induced electric field (E-field) distributions. Such TMS coils are required for multi-locus TMS (mTMS). We introduce a new mTMS coil design workflow with increased flexibility in target E-field definition and faster computations compared to our previous method. We also incorporate custom current density and E-field fidelity constraints to ensure that the target E-fields are accurately reproduced with feasible winding densities in the resulting coil designs. We validated the method by designing, manufacturing, and characterizing a 2-coil mTMS transducer for focal rat brain stimulation. Applying the constraints reduced the computed maximum surface current densities from 15.4 and 6.6kA/mm to the target value 4.7kA/mm, yielding winding paths suitable for a 1.5-mm-diameter wire with 7-kA maximum currents while still replicating the target E-fields with the predefined 2.8% maximum error in the FOV. The optimization time was reduced by two thirds compared to our previous method. The developed method allowed us to design a manufacturable, focal 2-coil mTMS transducer for rat TMS impossible to attain with our previous design workflow. The presented workflow enables considerably faster design and manufacturing of previously unattainable mTMS transducers with increased control over the induced E-field distribution and winding density, opening new possibilities for brain research and clinical TMS.

Rethinking the necessity of image fusion in high-level vision tasks: A practical infrared and visible image fusion network based on progressive semantic injection and scene fidelity

Image fusion aims to integrate complementary characteristics of source images into a single fused image that better serves human visual observation and machine vision perception. However, most existing image fusion algorithms primarily focus on improving the visual appeal of fused images. Although there are some semantic-driven methods that consider semantic requirements of downstream applications, none of them have demonstrated the potential of image-level fusion compared to feature-level fusion, which fulfills high-level vision tasks directly on multi-modal features rather than on a fused image. To overcome these limitations, this paper presents a practical infrared and visible image fusion network based on progressive semantic injection and scene fidelity constraints, termed PSFusion. First of all, the sparse semantic perception branch extracts sufficient semantic features, which are then progressively integrated into the fusion network using the semantic injection module to fulfill the semantic requirements of high-level vision tasks. The scene fidelity path within the scene restoration branch is devised to ensure that the fusion features contain complete information for reconstructing the source images. Additionally, the contrast mask and salient target mask are employed to construct the fusion loss to maintain impressive visual effects of fusion results. In particular, we provide quantitative and qualitative analyses to demonstrate the potential of image-level fusion compared to feature-level fusion for high-level vision tasks. With the rapid advancement of large-scale models, image-level fusion can expeditiously leverage the advantages of multi-modal data and state-of-the-art (SOTA) unimodal segmentation to achieve superior performance. Furthermore, extensive comparative experiments demonstrate the superiority of our PSFusion over SOTA image-level fusion alternatives in terms of visual appeal and high-level semantics. Even under harsh circumstances, our method offers satisfactory fusion results to serve subsequent high-level vision applications. The source code is available at https://github.com/Linfeng-Tang/PSFusion.

Third Law of Thermodynamics and the Scaling of Quantum Computers.

The third law of thermodynamics, also known as the Nernst unattainability principle, puts a fundamental bound on how close a system, whether classical or quantum, can be cooled to a temperature near to absolute zero. On the other hand, a fundamental assumption of quantum computing is to start each computation from a register of qubits initialized in a pure state, i.e., at zero temperature. These conflicting aspects, at the interface between quantum computing and thermodynamics, are often overlooked or, at best, addressed only at a single-qubit level. In this Letter, we argue how the existence of a small but finite effective temperature, which makes the initial state a mixed state, poses a real challenge to the fidelity constraints required for the scaling of quantum computers. Our theoretical results, carried out for a generic quantum circuit with N-qubit input states, are validated by test runs performed on a real quantum processor.

Temporal evolution of the Covid19 pandemic reproduction number: Estimations from proximal optimization to Monte Carlo sampling.

Monitoring the evolution of the Covid19 pandemic constitutes a critical step in sanitary policy design. Yet, the assessment of the pandemic intensity within the pandemic period remains a challenging task because of the limited quality of data made available by public health authorities (missing data, outliers and pseudoseasonalities, notably), that calls for cumbersome and ad-hoc preprocessing (denoising) prior to estimation. Recently, the estimation of the reproduction number, a measure of the pandemic intensity, was formulated as an inverse problem, combining data-model fidelity and space-time regularity constraints, solved by nonsmooth convex proximal minimizations. Though promising, that formulation lacks robustness against the limited quality of the Covid19 data and confidence assessment. The present work aims to address both limitations: First, it discusses solutions to produce a robust assessment of the pandemic intensity by accounting for the low quality of the data directly within the inverse problem formulation. Second, exploiting a Bayesian interpretation of the inverse problem formulation, it devises a Monte Carlo sampling strategy, tailored to a nonsmooth log-concave a posteriori distribution, to produce relevant credibility interval-based estimates for the Covid19 reproduction number. Clinical relevance Applied to daily counts of new infections made publicly available by the Health Authorities for around 200 countries, the proposed procedures permit robust assessments of the time evolution of the Covid19 pandemic intensity, updated automatically and on a daily basis.

Neuromorphic Silicon Photonics and Hardware-Aware Deep Learning for High-Speed Inference

The relentless growth of Artificial Intelligence (AI) workloads has fueled the drive towards non-Von Neuman architectures and custom computing hardware. Neuromorphic photonic engines aspire to synergize the low-power and high-bandwidth credentials of light-based deployments with novel architectures, towards surpassing the computing performance of their electronic counterparts. In this paper, we review recent progress in integrated photonic neuromorphic architectures and analyze the architectural and photonic hardware-based factors that limit their performance. Subsequently, we present our approach towards transforming silicon coherent neuromorphic layouts into high-speed and high-accuracy Deep Learning (DL) engines by combining robust architectures with hardware-aware DL training. Circuit robustness is ensured through a crossbar layout that circumvents insertion loss and fidelity constraints of state-of-the-art linear optical designs. Concurrently, we employ DL training models adapted to the underlying photonic hardware, incorporating noise- and bandwidth-limitations together with the supported activation function directly into Neural Network (NN) training. We validate experimentally the high-speed and high-accuracy advantages of hardware-aware DL models when combined with robust architectures through a SiPho prototype implementing a single column of a 4:4 photonic crossbar. This was utilized as the pen-ultimate hidden layer of a NN, revealing up to 5.93% accuracy improvement at 5GMAC/sec/axon when noise-aware training is enforced and allowing accuracies of 99.15% and 79.8% for the MNIST and CIFAR-10 classification tasks. Channel-aware training was then demonstrated by integrating the frequency response of the photonic hardware in NN training, with its experimental validation with the MNIST dataset revealing an accuracy increase of 12.93% at a record-high rate of 25GMAC/sec/axon.

Efficient Quantum Network Communication Using Optimized Entanglement Swapping Trees

Quantum network communication is challenging, as the no-cloning theorem in the quantum regime makes many classical techniques inapplicable; in particular, the direct transmission of qubit states over long distances is infeasible due to unrecoverable errors. For the long-distance communication of unknown quantum states, the only viable communication approach (assuming local operations and classical communications) is the teleportation of quantum states, which requires a prior distribution of the entangled pairs (EPs) of qubits. The establishment of EPs across remote nodes can incur significant latency due to the low probability of success of the underlying physical processes. The focus of our work is to develop efficient techniques that minimize EP generation latency. Prior works have focused on selecting entanglement <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">paths</i> ; in contrast, we select <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">entanglement swapping trees</i> —a more accurate representation of the entanglement generation structure. We develop a dynamic programming algorithm to select an optimal swapping tree for a single pair of nodes, under the given capacity and fidelity constraints. For the general setting, we develop an efficient iterative algorithm to compute a set of swapping trees. We present simulation results, which show that our solutions outperform the prior approaches by an order of magnitude and are viable for long-distance entanglement generation.

Spectral Gradient Fidelity and Spatial Hessian Hyper-Laplacian Sparsity Constraints for Variational Pansharpening

Spectral Gradient Fidelity and Spatial Hessian Hyper-Laplacian Sparsity Constraints for Variational Pansharpening

Nonsmooth Convex Optimization to Estimate the Covid-19 Reproduction Number Space-Time Evolution With Robustness Against Low Quality Data

Daily pandemic surveillance, often achieved through the estimation of the reproduction number, constitutes a critical challenge for national health authorities to design counter-measures. In an earlier work, we proposed to formulate the estimation of the reproduction number as an optimization problem, combining data-model fidelity and space-time regularity constraints, solved by nonsmooth convex proximal minimizations. Though promising, that first formulation significantly lacks robustness against the Covid-19 data low quality (irrelevant or missing counts, pseudo-seasonalities,...) stemming from the emergency and crisis context, which significantly impairs accurate pandemic evolution assessments. The present work aims to overcome these limitations by carefully crafting a functional permitting to estimate jointly, in a single step, the reproduction number and outliers defined to model low quality data. This functional also enforces epidemiology-driven regularity properties for the reproduction number estimates, while preserving convexity, thus permitting the design of efficient minimization algorithms, based on proximity operators that are derived analytically. The explicit convergence of the proposed algorithm is proven theoretically. Its relevance is quantified on real Covid-19 data, consisting of daily new infection counts for 200+ countries and for the 96 metropolitan France counties, publicly available at Johns Hopkins University and Sant&#x00E9;-Publique-France. The procedure permits automated daily updates of these estimates, reported via animated and interactive maps. Open-source estimation procedures will be made publicly available.

An Efficient Pansharpening Approach Based on Texture Correction and Detail Refinement

Pansharpening aims at fusing a multispectral (MS) image and panchromatic (PAN) image to obtain a high spatial resolution multispectral (HRMS) image. To obtain accurate details and reduce spectral distortion, this letter proposes an efficient pansharpening approach based on texture correction (TC) and detail refinement. First, a TC model is constructed based on spatial and spectral fidelity constraints to obtain a texture image that is highly correlated with the MS image. Second, a detail acquisition model is proposed by the consecutive parameter regression to adaptively refine the extracted details. Finally, the extracted details are injected into the up-sampled MS (UPMS) image to obtain the fused HRMS image. Experimental results demonstrate that the proposed method can obtain the high-quality results with high efficiency.

Adaptation in the digital era: The case of Robert Zemeckis’ Beowulf

From fidelity discourse, through medium specificity discourse, to intertextuality and remediation approach, adaptation studies have dynamically evolved and recently have responded with particular flexibility to the advent of the digital era. Even adaptations of classical literary texts, confronting the authority of their hypotexts, have daringly broken away from their fidelity constraints and ventured onto paths facilitated by the development of new media. This article discusses Robert Zemeckis’ 2007 adaptation of Beowulf and examines this film’s potential for illustrating the manifestations of digitality in adaptation discourses. A film that did not make it (in)to the box office, and an adaptation that makes literary fans cringe, it is still a fascinating cultural intertext: a radical reinterpretation of the Old English heroic poem, a star-studded special-effect cinematic extravaganza of an adventurous director, an illustration of adaptation going remediation and an inclusive transmedia hybrid.

SPB-Net: A Deep Network for SAR Imaging and Despeckling With Downsampled Data

Synthetic aperture radar (SAR) typically faces both large-scale data and speckle noise problems, which, respectively, induce enormous strains on transmission and storage and interfere with the analysis and interpretation of SAR images. To tackle these, we present a real-time processing deep network, called SPB-Net, to implement imaging and speckle suppression simultaneously. First, a novel imaging-despeckling observation model with the nonlogarithmic additive speckle noise is established. Subsequently, guided by the statistical properties of noise and sparse and detail-preserved requirements in SAR imaging and despeckling, we formulate an <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$L_{2}$ </tex-math></inline-formula> along with two <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$L_{1}$ </tex-math></inline-formula> regularizations as the fidelity, sparse, and image detail-preserved constraints, respectively. Convolution layers are employed to improve the feature representation capability in the latter <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$L_{1}$ </tex-math></inline-formula> term as well. Based on this, we construct a corresponding convex optimization problem. Then, the complex-valued split Bregman method, focusing on the complex-variable convex problem, is unfolded into a parameter-learnable and architecture-fixed SPB-Net to solve the proposed problem effectively and efficiently. Experimental results with the downsampled Radarsat-1 raw data demonstrate the validity in imaging and speckle suppression and the real-time processing capability of the proposed SPB-Net.

Lightning search algorithm-based contextually fused multilevel image segmentation

In this paper, a new well-organized fusion-based 3D Otsu energy thresholding prototypical for multilevel color image segmentation by means of lightning search algorithm (LSA) has been projected. Although, 3D Otsu works by means of between-class variances over the help of 3-D histogram but the performance is not satisfactory. As a result, the energy curve model is implemented, that works on contextual information of an image. However, using the concept of energy curve for 3D Otsu produces better result, but at the cost of complexity and also correspondingly the complication level for pick out appropriate thresholds is high. To overcome this limitation, the concept of LSA optimization algorithm is introduced. LSA is a fresh optimization process encouraged by the winding characteristics of lightening through a thunderstorm. In this paper, LSA is used to shorten the delinquent of comprehensive exploration for finding the finest thresholds. In addition to this, to enhance the quality of multi-level segmented image the concept of fusion based on local contrast is introduced. In this paper, 1D, 2D and 3D-Otsu methods using numerous optimization algorithms are implemented with energy curve and fusion based approach and compared with proposed fusion based energy 3D Otsu method using LSA algorithm. Experimental outputs demonstrate that the proposed Fusion-Energy-3D Otsu-LSA algorithm is outperforms and it can be established by comparing the well-known fidelity constraints of an image.

Spatial-Spectral Joint Compressed Sensing for Hyperspectral Images

Compressed sensing is one of the key technologies to reduce the volume of hyperspectral image for real-time storage and transmission. Reconstruction based on spectral unmixing show tremendous potential in hyperspectral compressed sensing compared with other conventional algorithms that directly reconstruct images. In this article, a joint spatial-spectral joint compressed sensing scheme is proposed. In this scheme, compressed hyperspectral data are collected by spatial-spectral hybrid compressed sampling. As for the reconstruction, an objective function is developed by introducing the fidelity constraints of spatial and spectral measurements and the row sparsity constraint of abundance that guarantee the precise reconstruction of hyperspectral images and obtain endmembers and abundances as by-products accurately. An augmented Lagrangian type algorithm is meticulously elaborated to solve the above optimization problem. Extensive experimental results on several real hyperspectral datasets indicate that the proposed approach can achieve a reconstruction accuracy higher than those of other state-of-the-art methods. The efficiency and feasibility of the proposed scheme give it great potential in hyperspectral compressed sensing.

Access Control for IoT Nodes With Energy and Fidelity Constraints

The presence of many battery-powered sensors in the Internet of Things paradigm calls for the design of energy-aware protocols. Source coding techniques make it possible to save some energy by compressing the packets sent over the network, but at the cost of poorer accuracy in the representation of the data. This paper addresses the problem of designing efficient policies to jointly perform processing and transmission tasks. In particular, we aim at defining a scheduling strategy with the twofold goal of extending the network lifetime and guaranteeing a low overall distortion of the transmitted data. We propose a time division multiple access-based access scheme that efficiently allocates resources to heterogeneous nodes. We use realistic rate-distortion curves to quantify the impact of compression on the data quality and propose a complete energy model that includes the energy spent for processing and transmitting the data, as well as the circuitry energy costs. We consider both full and statistical knowledge of the wireless channels and derive communication policies for the two cases. The overall problem is structured in modules and solved through convex and alternate programming techniques. Finally, we thoroughly evaluate the proposed algorithms and the influence of the design variables on the system performance adopting parameters taken from real sensors.

Hybrid spectral CT reconstruction.

Current photon counting x-ray detector (PCD) technology faces limitations associated with spectral fidelity and photon starvation. One strategy for addressing these limitations is to supplement PCD data with high-resolution, low-noise data acquired with an energy-integrating detector (EID). In this work, we propose an iterative, hybrid reconstruction technique which combines the spectral properties of PCD data with the resolution and signal-to-noise characteristics of EID data. Our hybrid reconstruction technique is based on an algebraic model of data fidelity which substitutes the EID data into the data fidelity term associated with the PCD reconstruction, resulting in a joint reconstruction problem. Within the split Bregman framework, these data fidelity constraints are minimized subject to additional constraints on spectral rank and on joint intensity-gradient sparsity measured between the reconstructions of the EID and PCD data. Following a derivation of the proposed technique, we apply it to the reconstruction of a digital phantom which contains realistic concentrations of iodine, barium, and calcium encountered in small-animal micro-CT. The results of this experiment suggest reliable separation and detection of iodine at concentrations ≥ 5 mg/ml and barium at concentrations ≥ 10 mg/ml in 2-mm features for EID and PCD data reconstructed with inherent spatial resolutions of 176 μm and 254 μm, respectively (point spread function, FWHM). Furthermore, hybrid reconstruction is demonstrated to enhance spatial resolution within material decomposition results and to improve low-contrast detectability by as much as 2.6 times relative to reconstruction with PCD data only. The parameters of the simulation experiment are based on an in vivo micro-CT experiment conducted in a mouse model of soft-tissue sarcoma. Material decomposition results produced from this in vivo data demonstrate the feasibility of distinguishing two K-edge contrast agents with a spectral separation on the order of the energy resolution of the PCD hardware.

Numerical and Visual Evaluation of Compressed Sensing MRI Using 3D Cartesian Sampling

We performed numerical and visual evaluation of compressed sensing MRI (CS-MRI) using 3D Cartesian sampling by numerical simulation. Three brain anatomical ROIs (white matter, gray matter, cerebrospinal fluid) of a T1-weighted image (T1WI), a T2-weighted image (T2WI) and a proton density-weighted image (PDWI) were used for numerical evaluation. Sampling ratio of the Cartesian grid was 30%. Reconstruction was performed by the projection onto convex sets (POCS) method with soft thresholding, subject to data fidelity constraints. In the absence of noise, RMSE of 3D-T1WI was 1.50, ant that of the 2D-T1WI of the transverse plane was in the range of 1.06 to 1.54; anatomical ROIs was in the range of 0.75 to 2.80; those of T2WI were 3.20, 2.77 to 3.06, and 1.81 to 4.51; those of PDWI were 1.69, 1.33 to 1.49, and 1.08 to 1.86. Visual evaluation was performed by three radiologists on the basis of three categories: artifact, anatomical structure, and tissue contrast. Average score of the visual evaluation indicated that anatomical structure and tissue contrast of CS images were equal to those of the original image, although a few artifacts were visible. If noise level was assumed to be 20 dB or less, anatomical structure and tissue contrast were not significantly degraded compared to noise-free CS images.

CT reconstruction from few-views with anisotropic edge-guided total variance

To overcome the oversmoothing drawback in the edge areas when reconstructing few-view CT with total variation (TV) minimization, in this paper, we propose an anisotropic edge-guided TV minimization framework for few-view CT reconstruction. In the framework, anisotropic TV is summed with pre-weighted image gradient and then used as the object function for minimizing. It includes edge-guided TV minimization (EGTV) and edge-guided adaptive-weighted TV minimization (EGAwTV) algorithms. For EGTV algorithm, the weights of the TV discretization term are updated by anisotropic edge information detected from the image, whereas the weights for EGAwTV are determined based on edge information and local image-intensity gradients. To solve the minimization problem of the proposed algorithm, a similar TV-based minimization implementation is developed to address the raw data fidelity and other constraints. The evaluation results using both computer simulations with the Shepp-Logan phantom and experimental data from a physical phantom demonstrate that the proposed algorithms exhibit noticeable gains in the merits of spatial resolution compared with the conventional TV and other modified TV algorithms.