Collecting data from diverse perspectives is essential across many fields to achieve high-resolution imaging, from Synthetic Aperture Imaging (SAI) to advanced microscopy techniques. However, due to persistent challenges, fully capturing variability in position, angle, and scale remains difficult, driving the need for advanced data generation techniques. In this paper, we utilise a combination of Implicit Neural Representations and HyperNetwork framework to generate datasets enriched with spatial variability, including variations in position, angle, and scale. This method enhances the diversity of generated data, enabling more flexible and robust image datasets applicable to various imaging tasks. Our approach is evaluated on the MNIST and cryo-EM datasets, where we demonstrate the generation of spatially diverse images that maintain high-quality attributes despite changes in spatial configuration. This work highlights the potential to improve data generation processes, leading to more versatile and comprehensive datasets for scientific use.

The Alternating Direction Method of Multipliers (ADMM) is uniquely suited for large-scale signal restoration problems, owing to its parallelizability. ADMM has been successfully deployed into several imaging modalities, including blind ptychography, phase retrieval, computer tomography, network unrolling, and magnetic resonance imaging. It is not an overstatement to say that while global convergence guarantees of ADMM under convex objective losses cement its utility, non-convex objectives offer superior reconstruction quality at the expense of these guarantees. In this paper, we break new ground with the development of invex ADMM which retains global optima guarantees for a novel class of non-convex, invex losses - an invex function is a mapping where any critical point is a global minimizer. More specifically, we propose a family of invex losses for which ADMM converges to the global minima, along with their guarantees. Our experimental evaluation and theoretical results shows that the proposed approach is very promising, and can aid in extending existing convergences guarantees of ADMM beyond traditional convex settings.

Signal restoration is an important constrained optimization problem with significant applications in various domains. Although non-convex constrained optimization problems have been shown to perform better than convex counterparts in terms of reconstruction quality, convex constrained optimization problems have been preferably for its global optima guarantees. Despite the success of non-convex methods in a large number of applications, it is not an overstatement to say that there is little or no hope for non-convex problems to ensure global optima. In this paper, for the first time, we develop invex constrained optimization theory to mitigate the loss of guarantees for global optima in non-convex constrained inverse problems, where the invex function is a mapping where any critical point is a global minimizer. We also develop relevant theories to extend the global optima guarantee to a set of quasi-invex functions - the largest optimizable mappings. More specifically, we propose a family of invex/quasi-invex of functions for handling constrained inverse problems using the non-convex setting along with guarantees for their global optima. Our experimental evaluation shows that the proposed approach is very promising and can aid in extending existing convex optimization algorithms, such as the alternating direction method of multipliers, and accelerated proximal gradient methods.

The semantic matching problem consists of recognizing if the candidate text is relevant to a particular input text. Semantic similarities can be determined from human-curated knowledge, but such knowledge may not be available in every language. Instead, statistical learning techniques have been applied, but these techniques circumvent the need for manual feature engineering by using large datasets to train models to perform semantic similarity scoring between portions of text or words. The pre-trained transformer provides a further mechanism to consolidate the information throughout a sentence into single sentence-level representations, but these representations may not be optimal for the matching task. As an alternative, we propose an interactive semantic transformer based on a greedy layer-wise framework to learn a distributed similarity representation for sentence pairs. The novelty of the architecture lies in an abstract representation of the semantic similarities created by three-stage learning strategies. Model training is accomplished through a greedy layer-wise training scheme, that incorporates both supervised and unsupervised learning. The proposed model is experimentally compared to state-of-the-art approaches on three different dataset types: the library TREC, the Yahoo!, and Stack Exchange community question datasets, and results show the proposed model outperforming other approaches.

In this paper, we summarize our effort to create and utilize an integrated framework to coordinate computational AI analytics tasks with the help of a task and experiment management workflow system. Our design is based on a minimalistic approach while at the same time allowing access to hybrid computational resources offered through the owner's computer, HPC computing centers, cloud resources, and distributed systems in general. Access to this framework includes a GUI for monitoring and managing the workflow, a REST service, a command line interface, as well as a Python interface. It uses a template-based batch management system that, through configuration files, easily allows for the generation of reproducible experiments while creating permutations over selected experiment parameters as typical in deep learning applications. The resulting framework was developed for analytics workflows targeting MLCommons benchmarks of AI applications on hybrid computing resources, as well as an educational tool for teaching scientists and students sophisticated concepts to execute computations on resources ranging from a single computer to many thousands of computers as part of on-premise and cloud infrastructure. We demonstrate the usefulness of the tool while creating FAIR principle-based application accuracy benchmark generation for the MLCommons Science Working Group Cloudmask application. The code is available as an open-source project in GitHub and is based on an easy-to-enhance framework called Cloudmesh. It can be applied to other applications easily.

Noting the importance of factorizing (or disentangling) the latent space, we propose a novel, non-probabilistic disentangling framework for autoencoders, based on the principles of symmetry transformations that are independent of one another. To the best of our knowledge, this is the first deterministic model that is aiming to achieve disentanglement based on autoencoders using only a reconstruction loss without pairs of images or labels, by explicitly introducing inductive biases into a model architecture through Euler encoding. The proposed model is then compared with a number of state-of-the-art models, relevant to disentanglement, including symmetry-based models and generative models. Our evaluation using six different disentanglement metrics, including the unsupervised disentanglement metric we propose here in this paper, shows that the proposed model can offer better disentanglement, especially when variances of the features are different, where other methods may struggle. We believe that this model opens several opportunities for linear disentangled representation learning based on deterministic autoencoders.

Convolution is a fundamental operation in image processing and machine learning. Aimed primarily at maintaining image size, padding is a key ingredient of convolution, which, however, can introduce undesirable boundary effects. We present a non-padding-based method for size-keeping convolution based on the preservation of differential characteristics of kernels. The main idea is to make convolution over an incomplete sliding window “collapse“ to a linear differential operator evaluated locally at its central pixel, which no longer requires information from the neighbouring missing pixels. While the underlying theory is rigorous, our final formula turns out to be simple: the convolution over an incomplete window is achieved by convolving its nearest complete window with a transformed kernel. This formula is computationally lightweight, involving neither interpolation or extrapolation nor restrictions on image and kernel sizes. Our method favours data with smooth boundaries, such as high-resolution images and fields from physics. Our experiments include: i) filtering analytical and non-analytical fields from computational physics and, ii) training convolutional neural networks (CNNs) for the tasks of image classification, semantic segmentation and super-resolution reconstruction. In all these experiments, our method has exhibited visible superiority over the compared ones.

The question answering system in open domain enables a machine to automatically select and generate the answer for questions posed by humans in a natural language form on the website. Previous approaches seek effective ways of extracting the semantic features between question and answer, but the contextual information effects in semantic matching are still limited by short-term memory. As an alternative, we propose an internal knowledge-based end-to-end model, enhanced by an attentive memory network for both answer selection and answer generation tasks by considering the full advantages of the semantics and multifacts (i.e., timescales, topics, and context). In detail, we design a long-term memory to learn the top-$k$fine-grained similarity representations, where two memory-aware mechanisms aggregate the series of semantic word-level and sentence-level similarities to support the coarse contextual information. Furthermore, we propose a novel memory refinement mechanism with the two-dimensional of writing heads that offer an efficient approach to multiview selection of the salient word pairs. In the training stage, we adopt the transformer-based transfer learning skill to effectively pretrain the model. Experimentally, we compare the state-of-the-art approaches on four public datasets, the experimental results show that the proposed model achieves competitive performance.

Image reconstruction enhanced by regularizers, e.g., to enforce sparsity, low rank or smoothness priors on images, has many successful applications in vision tasks such as computer photography, biomedical and spectral imaging. It has been well accepted that non-convex regularizers normally perform better than convex ones in terms of the reconstruction quality. But their convergence analysis is only established to a critical point, rather than the global optima. To mitigate the loss of guarantees for global optima, we propose to apply the concept of invexity and provide the first list of proved invex regularizers for improving image reconstruction. Moreover, we establish convergence guarantees to global optima for various advanced image reconstruction techniques after being improved by such invex regularization. To the best of our knowledge, this is the first practical work applying invex regularization to improve imaging with global optima guarantees. To demonstrate the effectiveness of invex regularization, numerical experiments are conducted for various imaging tasks using benchmark datasets.

The need for compilers to generate highly vectorized code is at an all-time high with the increasing vectorization capabilities of modern processors. To this end, the information that compilers have at their disposal, either through code analysis or via user annotations, is instrumental for auto-vectorization, and hence for the overall performance. However, the information that is available to compilers at compile time and its accuracy varies greatly, as does the resulting performance of vectorizing compilers. Benchmarks like the Test Suite for Vectorizing Compilers (TSVC) have been developed to evaluate the vectorization capability of such compilers. The overarching approach of TSVC and similar benchmarks is to evaluate the compilers under the best possible scenario (i.e., assuming that compilers have access to all useful contextual information at compile time). Although this idealistic view is useful to observe the capability of compilers for auto-vectorization, it is not a true reflection of the conditions found in real-world applications. In this article, we propose a novel method for evaluating the auto-vectorization capability of compilers. Instead of assuming that compilers have access to a wealth of information at compile time, we formulate a method to objectively supply or withdraw information that would otherwise aid the compiler in the auto-vectorization process. This method is orthogonal to the approach adopted by TSVC, and as such, it provides the means of assessing the capabilities of modern vectorizing compilers in a more detailed way. Using this new method, we exhaustively evaluated five industry-grade compilers (GNU, Intel, Clang, PGI, and IBM) on four representative vector platforms (AVX-2, AVX-512 (Skylake), AVX-512 (KNL), and AltiVec) using the modified version of TSVC and application-level proxy kernels. The results show the impact that withdrawing information has on the vectorization capabilities of each compiler and also prove the validity of the presented technique.

Correlation filter has been proven to be an effective tool for a number of approaches in visual tracking, particularly for seeking a good balance between tracking accuracy and speed. However, correlation filter-based models are susceptible to wrong updates stemming from inaccurate tracking results. To date, very little effort has been devoted towards handling the correlation filter update problem. In this paper, we propose a novel approach to address the correlation filter update problem. In our approach, we update and maintain multiple correlation filter models in parallel, and we use deep reinforcement learning for the selection of an optimal correlation filter model among them. To facilitate the decision process in an efficient manner, we propose a decision-net to deal with target appearance modeling, which is trained through hundreds of challenging videos using proximal policy optimization and a lightweight learning network. An exhaustive evaluation of the proposed approach on the OTB100 and OTB2013 benchmarks shows that the approach is effective enough to achieve the average success rate of 62.3% and the average precision score of 81.2%, both exceeding the performance of traditional correlation filter-based trackers.

In general, development of adequately complex mathematical models, such as deep neural networks, can be an effective way to improve the accuracy of learning models. However, this is achieved at the cost of reduced post-hoc model interpretability, because what is learned by the model can become less intelligible and tractable to humans as the model complexity increases. In this paper, we target a similarity learning task in the context of image retrieval, with a focus on the model interpretability issue. An effective similarity neural network (SNN) is proposed to offer not only to seek robust retrieval performance but also to achieve satisfactory post-hoc interpretability. The network is designed by linking the neuron architecture with the organization of a concept tree and by formulating neuron operations to pass similarity information between concepts. Various ways of understanding and visualizing what is learned by the SNN neurons are proposed. We also exhaustively evaluate the proposed approach using a number of relevant datasets against a number of state-of-the-art approaches to demonstrate the effectiveness of the proposed network. Our results show that the proposed approach can offer superior performance when compared against state-of-the-art approaches. Neuron visualization results are demonstrated to support the understanding of the trained neurons.

Energy efficiency (EE) and spectral efficiency (SE) are two of the key performance metrics in future wireless networks, covering both design and operational requirements. For previous conventional resource allocation techniques, these two performance metrics have been considered in isolation, resulting in severe performance degradation in either of these metrics. Motivated by this problem, in this paper, we propose a novel beamforming design that jointly considers the trade-off between the two performance metrics in a multiple-input single-output non-orthogonal multiple access system. In particular, we formulate a joint SE-EE based design as a multi-objective optimization (MOO) problem to achieve a good trade-off between the two performance metrics. However, this MOO problem is not mathematically tractable and, thus, it is difficult to determine a feasible solution due to the conflicting objectives, where both need to be simultaneously optimized. To overcome this issue, we exploit a priori articulation scheme combined with the weighted sum approach. Using this, we reformulate the original MOO problem as a conventional single objective optimization (SOO) problem. In doing so, we develop an iterative algorithm to solve this non-convex SOO problem using the sequential convex approximation technique. Simulation results are provided to demonstrate the advantages and effectiveness of the proposed approach over the available beamforming designs.

In this paper, we propose two beamforming designs for a multiple-input single-output non-orthogonal multiple access system considering the energy efficiency (EE) fairness between users. In particular, two quantitative fairness-based designs are developed to maintain fairness between the users in terms of achieved EE: max-min energy efficiency (MMEE) and proportional fairness (PF) designs. While the MMEE-based design aims to maximize the minimum EE of the users in the system, the PF-based design aims to seek a good balance between the global energy efficiency of the system and the EE fairness between the users. Detailed simulation results indicate that our proposed designs offer many-fold EE improvements over the existing energy-efficient beamforming designs.

In this paper, we propose a beamforming design that jointly considers two conflicting performance metrics, namely the sum rate and fairness, for a multiple-input single-output non-orthogonal multiple access system. Unlike the conventional rate-aware beamforming designs, the proposed approach has the flexibility to assign different weights to the objectives (i.e., sum rate and fairness) according to the network requirements and the channel conditions. In particular, the proposed design is first formulated as a multi-objective optimization problem, and subsequently mapped to a single objective optimization (SOO) problem by exploiting the weighted sum approach combined with a prior articulation method. As the resulting SOO problem is non-convex, we use the sequential convex approximation technique, which introduces multiple slack variables, to solve the overall problem. Simulation results are provided to demonstrate the performance and the effectiveness of the proposed approach along with detailed comparisons with conventional rate-aware-based beamforming designs.

When considering the future generation wireless networks, non-orthogonal multiple access (NOMA) represents a viable multiple access technique for improving the spectral efficiency. The basic performance of the NOMA is often enhanced using downlink beamforming and power allocation techniques. Although downlink beamforming has been previously studied with different performance criteria, such as sum-rate and max-min rate, it has not been studied in the multiuser, multiple-input single-output (MISO) case, particularly with the energy efficiency criteria. In this paper, we investigate the design of an energy efficient beamforming technique for downlink transmission in the context of a multiuser MISO-NOMA system. In particular, this beamforming design is formulated as a global energy efficiency (GEE) maximization problem with minimum user rate requirements and transmit power constraints. By using the sequential convex approximation technique and the Dinkelbach's algorithm to handle the non-convex nature of the GEE-Max problem, we propose two novel algorithms for solving the downlink beamforming problem for the MISO-NOMA system. Our evaluation of the proposed algorithms shows that they offer similar optimal designs and are effective in offering substantial energy efficiencies compared with the designs based on conventional methods.

Human action recognition from video sequences is a challenging topic in computer vision research. In recent years, many studies have explored the use of deep learning representations to consistently improve the analysis accuracy. Meanwhile, designing a fast and reliable framework is becoming increasingly important given the exponential growth of video data collected for many purposes (e.g. public security, entertainment, and early medical diagnosis etc.). In order to design a more efficient automatic human action annotation method, the sequential probability ratio test, one of the classical statistical sampling scheme, is adapted to solve a multi-classes hypothesis test problem in our work. With the proposed algorithm, the computational cost is reduced significantly without sacrificing the performance of the underlying system. The experimental results based on the UCF101 data set demonstrated the efficiency of the framework compared to the fixed sampling scheme.

The existing efforts in computer assisted semen analysis have been focused on high speed imaging and automated image analysis of sperm motility. This results in a large amount of data, and it is extremely challenging for both clinical scientists and researchers to interpret, compare and correlate the multidimensional and time-varying measurements captured from video data. In this work, we use glyphs to encode a collection of numerical measurements taken at a regular interval and to summarize spatio-temporal motion characteristics using static visual representations. The design of the glyphs addresses the needs for (a) encoding some 20 variables using separable visual channels, (b) supporting scientific observation of the interrelationships between different measurements and comparison between different sperm cells and their flagella, and (c) facilitating the learning of the encoding scheme by making use of appropriate visual abstractions and metaphors. As a case study, we focus this work on video visualization for computer-aided semen analysis, which has a broad impact on both biological sciences and medical healthcare. We demonstrate that glyph-based visualization can serve as a means of external memorization of video data as well as an overview of a large set of spatiotemporal measurements. It enables domain scientists to make scientific observation in a cost-effective manner by reducing the burden of viewing videos repeatedly, while providing them with a new visual representation for conveying semen statistics.

Abstract The majority of display devices used in visualization are 2D displays. Inevitably, it is often necessary to overlay one piece of visual information on top of another, especially in applications such as multi‐field visualization and geo‐spatial information visualization. In this paper, we present a conceptual framework for studying the mechanisms for overlaying multiple pieces of visual information while allowing users to recover occluded information. We adopt the term ‘multiplexing’ from tele‐ and data communication to encompass all such overlapping mechanisms. We establish 10 categories of visual multiplexing mechanisms. We draw support evidence from both perception literature and existing works in visualization to support this conceptual framework. We examine the relationships between multiplexing and information theoretic measures. This new conceptual categorization provides the much‐needed theory of visualization with an integral component.

Abstract In this paper, we present a novel visualization technique for assisting the observation and analysis of algorithmic complexity. In comparison with conventional line graphs, this new technique is not sensitive to the units of measurement, allowing multivariate data series of different physical qualities (e.g., time, space and energy) to be juxtaposed together conveniently and consistently. It supports multivariate visualization as well as uncertainty visualization. It enables users to focus on algorithm categorization by complexity classes, while reducing visual impact caused by constants and algorithmic components that are insignificant to complexity analysis. It provides an effective means for observing the algorithmic complexity of programs with a mixture of algorithms and black‐box software through visualization. Through two case studies, we demonstrate the effectiveness of complexity plots in complexity analysis in research, education and application.

Component-oriented software development has been attracting increasing attention for building complex distributed applications. A new infrastructure supporting this advanced concept is our prototype component framework based on the Grid component model. This paper provides an overview of the component framework and presents a case study where we utilise the component-oriented approach to develop a business process application for a biometric identification system. We then introduce the tools being developed as part of an integrated development environment to enable graphical component-based development of Grid applications. Finally, we report our initial findings and experiences of efficiently using the component framework and set of software tools.

Abstract Two‐dimensional arrays are generally arranged in memory in row‐major order or column‐major order. Traversing a row‐major array in column‐major order, or vice versa, leads to poor spatial locality. With large arrays the performance loss can be a factor of 10 or more. This paper explores the Morton storage layout, which has substantial spatial locality whether traversed in row‐major or column‐major order. Using a small suite of dense kernels working on two‐dimensional arrays, we have carried out an extensive study of the impact of poor array layout and of whether Morton layout can offer an attractive compromise. We show that Morton layout can lead to better performance than the worse of the two canonical layouts; however, the performance of Morton layout compared to the better choice of canonical layout is often disappointing. We further study one simple improvement of the basic Morton scheme: we show that choosing the correct alignment for the base address of an array in Morton layout can sometimes significantly improve the competitiveness of this layout. Copyright © 2006 John Wiley & Sons, Ltd.