Search

In this paper, we investigate a secure mobile edge computing (MEC) network in the presence of multiple eavesdroppers, where multiple users can offload parts of their tasks to the computational access point (CAP). The multiple eavesdroppers may overhear the confidential task offloading, which leads to information leakage. In order to address this issue, we present the minimization problem of the secrecy outage probability (SOP), by jointly taking into account the constraints from the latency and energy consumption. With the aim to improve the system secrecy performance, we then introduce three user selection criteria to choose the best user among multiple ones. Specifically, criterion I maximizes the locally computational capacity, while criterion II and III maximize the secrecy capacity and data rate of main links, respectively. For these criteria, we further analyze the system secrecy performance by deriving analytical and asymptotic expressions for the SOP, from which we can conclude important insights for the system design. Finally, simulation and analytical results are provided to verify the proposed analysis. The results show that the three criteria can efficiently safeguard the MEC networks, compared to the traditional local computing and fully offloading, especially with a large value of user number. [ABSTRACT FROM AUTHOR]

Voltage source converter (VSC) based devices have become widely accepted by the power industry in recent years as a result of renewable energy initiatives and other developments. Due to their nonlinear v∼i characteristics, it is essential to understand and model the harmonic impact of VSC devices in a power system. In response to such a need, this paper proposes a rigorous harmonic model of VSC devices suitable for harmonic power flow studies of large-scale power systems. Through detailed mathematical derivations, this research has shown that the model takes the form of a coupled frequency-dependent impedance matrix. Formulas to compute the impedance elements have been established. The results show that the impedance is independent of the harmonic voltages experienced by the VSC device, and thus it can be easily integrated into existing harmonic power flow tools. The accuracy of the model, as well as its usefulness for harmonic power flow studies, have been verified using EMT simulations. [ABSTRACT FROM AUTHOR]

Stochastic gradient descent (SGD) has become the method of choice for training highly complex and nonconvex models since it can not only recover good solutions to minimize training errors but also generalize well. Computational and statistical properties are separately studied to understand the behavior of SGD in the literature. However, there is a lacking study to jointly consider the computational and statistical properties in a nonconvex learning setting. In this paper, we develop novel learning rates of SGD for nonconvex learning by presenting high-probability bounds for both computational and statistical errors. We show that the complexity of SGD iterates grows in a controllable manner with respect to the iteration number, which sheds insights on how an implicit regularization can be achieved by tuning the number of passes to balance the computational and statistical errors. As a byproduct, we also slightly refine the existing studies on the uniform convergence of gradients by showing its connection to Rademacher chaos complexities. [ABSTRACT FROM AUTHOR]

This paper analyzes regularization terms proposed recently for improving the adversarial robustness of deep neural networks (DNNs), from a theoretical point of view. Specifically, we study possible connections between several effective methods, including input-gradient regularization, Jacobian regularization, curvature regularization, and a cross-Lipschitz functional. We investigate them on DNNs with general rectified linear activations, which constitute one of the most prevalent families of models for image classification and a host of other machine learning applications. We shed light on essential ingredients of these regularizations and re-interpret their functionality. Through the lens of our study, more principled and efficient regularizations can possibly be invented in the near future. [ABSTRACT FROM AUTHOR]

The stochastic block model (SBM) is a random graph model in which the edges are generated according to the underlying cluster structure on the vertices. The (ferromagnetic) Ising model, on the other hand, assigns ±1 labels to vertices according to an underlying graph structure in a way that if two vertices are connected in the graph then they are more likely to be assigned the same label. In SBM, one aims to recover the underlying clusters from the graph structure while in Ising model, an extensively-studied problem is to recover the underlying graph structure based on i.i.d. samples (labelings of the vertices). In this paper, we propose a natural composition of SBM and the Ising model, which we call the Stochastic Ising Block Model (SIBM). In SIBM, we take SBM in its simplest form, where $n$ vertices are divided into two equal-sized clusters and the edges are connected independently with probability $p$ within clusters and $q$ across clusters. Then we use the graph $G$ generated by the SBM as the underlying graph of the Ising model and draw $m$ i.i.d. samples from it. The objective is to exactly recover the two clusters in SBM from the samples generated by the Ising model, without observing the graph $G$. As the main result of this paper, we establish a sharp threshold $m^\ast $ on the sample complexity of this exact recovery problem in a properly chosen regime, where $m^\ast $ can be calculated from the parameters of SIBM. We show that when $m\ge m^\ast $ , one can recover the clusters from $m$ samples in $O(n)$ time as the number of vertices $n$ goes to infinity. When $m < m^\ast $ , we further show that for almost all choices of parameters of SIBM, the success probability of any recovery algorithms approaches 0 as $n\to \infty $. [ABSTRACT FROM AUTHOR]

This paper proposes a new algorithm, named Householder Dice (HD), for simulating dynamics on dense random matrix ensembles with rotational invariance. Examples include the Gaussian ensemble, the Haar-distributed random orthogonal ensemble, and their complex-valued counterparts. A “direct” approach to the simulation, where one first generates a dense $n \times n$ matrix from the ensemble, requires at least $\mathcal {O}(n^{2})$ resource in space and time. The HD algorithm overcomes this $\mathcal {O}(n^{2})$ bottleneck by using the principle of deferred decisions: rather than fixing the entire random matrix in advance, it lets the randomness unfold with the dynamics. At the heart of this matrix-free algorithm is an adaptive and recursive construction of (random) Householder reflectors. These orthogonal transformations exploit the group symmetry of the matrix ensembles, while simultaneously maintaining the statistical correlations induced by the dynamics. The memory and computation costs of the HD algorithm are $\mathcal {O}(nT)$ and $\mathcal {O}(nT^{2})$ , respectively, with $T$ being the number of iterations. When $T \ll n$ , which is nearly always the case in practice, the new algorithm leads to significant reductions in runtime and memory footprint. Numerical results demonstrate the promise of the HD algorithm as a new computational tool in the study of high-dimensional random systems. [ABSTRACT FROM AUTHOR]

The performance of a single neural network can vary unexpectedly corresponding to different classification tasks, and thus the network with fixed structure may lack flexibility and often lead to overfitting or underfitting. It is urgent, also the main objective of this paper, to deal with the limitation of the fixed neural network structure on classifying radar signals in different electromagnetic environments. We in this paper propose a variable network architecture search (NAS) mechanism, called balanced-NAS framework, and apply it in specific emitter identification (SEI) to greatly improve the flexibility of model searching. In the proposed balanced-NAS framework, a “block-cell” structure and a controller based recurrent neural network (RNN) are utilized to design models automatically according to external environment. In particular, a balance function is also proposed and utilized in the balanced-NAS framework, acting on the RNN controller to take both the validation accuracy and computational budget into consideration while searching for ideal models. The efficiency of the searching process is further enhanced by exploiting a progressive strategy to design simple and complicate child models where unpromising ones after each evaluation process are obsoleted to release searching space. Simulations and experiments indicate that the proposed balanced-NAS framework is extremely efficient and outperforms the conventional algorithms in classifying radar signals in different environments. [ABSTRACT FROM AUTHOR]

This paper derives the optimal Bayesian processing of an out-of-sequence (OOS) set of measurements in continuous-time for multiple target tracking. We consider a multi-target system modelled in continuous time that is discretised at the time steps when we receive the measurements, which are distributed according to the standard point target model. All information about this system at the sampled time steps is provided by the posterior density on the set of all trajectories. This density can be computed via the continuous-discrete trajectory Poisson multi-Bernoulli mixture (TPMBM) filter. When we receive an OOS measurement, the optimal Bayesian processing performs a retrodiction step that adds trajectory information at the OOS measurement time stamp followed by an update step. After the OOS measurement update, the posterior remains in TPMBM form. We also provide a computationally lighter alternative based on a trajectory Poisson multi-Bernoulli filter. The effectiveness of the two approaches to handle OOS measurements is evaluated via simulations. [ABSTRACT FROM AUTHOR]

Bulk integrated electricity and gas systems (IEGSs) introduce complex coupling relations and induce synergistic operation challenges. The growing uncertainty arising from the renewable power generation in the IEGS further aggravates the synergistic problems. Considering the availability of historical wind power generation data, this paper adopts a two-stage sample robust optimization (SRO) model, which is equivalent to the two-stage distributionally robust optimization (DRO) model with a ${\text{type}} - \infty $ Wasserstein ambiguity set, to address the wind power penetrated unit commitment optimal energy flow (UC-OEF) problem for the IEGS. Compared to the equivalent DRO model, the two-stage SRO model can be approximately transformed into a computationally efficient form. Specifically, we employ linear decision rules to simplify the proposed UC-OEF model. Moreover, we further enhance the tractability of the simplified model by exploring its structural features and, accordingly, develop a solution method. Simulation results on two IEGSs validate the effectiveness of the proposed model and solution method. [ABSTRACT FROM AUTHOR]

The approach of ambient signals-based load modeling (ASLM) was recently proposed to better track the time-varying changes of load models. To improve computation efficiency and model structure complexity, a hierarchical framework for ASLM is proposed in this paper. Through this framework, the hidden quasi-convexity of the load modeling problem is explored for the first time. This allows more complicated static load model structures and gradient or Hessian-based optimization algorithms to be used. In the upper level, the identification of dynamic load parameters is regarded as an optimization problem. In the lower level, the optimal static load parameters are obtained through linear regression for a given group of dynamic load parameters. Afterward, the regression residuals are regarded as the objective function (OF) of the upper level optimization problem. The proposed method is validated by the case study results on the Guangdong Power Grid. The results show that the OF is mostly quasi-convex after the transformation of the induction motor model, which provides the basis for the application of gradient or Hessian-based optimization algorithms. The case study results also validate that the proposed approach has better computation efficiency and model structure complexity compared with the previous ASLM approaches. [ABSTRACT FROM AUTHOR]

Stochastic unit commitment is an efficient method for grid operation in the presence of significant uncertainties. An example is an operation during a predicted hurricane with uncertain line out-ages. However, the solution quality comes at the cost of substantial computational burden, which makes its adoption challenging. This paper evaluates some possible ways that machine learning can be used to reduce this computational burden. First, a set of feasibility studies is conducted. Results suggest that using machine learning as an assistant to the stochastic unit commitment solver is more advantageous than using it as a standalone solver. In particular, the machine learning model is trained to facilitate solving the problem by determining the unnecessary constraints that can be removed from the original problem without affecting the final accuracy. The variables that can be used as input features/predictors or outputs for the machine learning model are determined through feasibility studies. Then, an algorithm to train and utilize a machine learning model is proposed. The method is tested on a 500-bus synthetic South Carolina system. Various test cases show an average reduction in solution time by more than 90% by using the trained machine learning model to assist the stochastic unit commitment solver. [ABSTRACT FROM AUTHOR]

Video summarization (VS) is generally formulated as a subset selection problem where a set of representative keyframes or key segments is selected from an entire video frame set. Though many sparse subset selection based VS algorithms have been proposed in the past decade, most of them adopt linear sparse formulation in the explicit feature vector space of video frames, and don’t consider the local or global relationships among frames. In this paper, we first extend the conventional sparse subset selection for VS into kernel block sparse subset selection (KBS3) to utilize the advantage of kernel sparse coding and introduce a local inter-frame relationship through packing of frame blocks. Going a step further, we propose a similarity based block sparse subset selection (SB2S3) model by applying a specially designed transformation matrix on the KBS3 model in order to introduce a kind of global inter-frame relationship through the similarity. Finally, a greedy pursuit based algorithm is devised for the proposed NP-hard model optimization. The proposed SB2S3 has the following advantages: 1) through the similarity between each frame and any other frame, the global relationship among all frames can be considered; 2) through block sparse coding, the local relationship of adjacent frames is further considered; and 3) it has a wider application, since features can derive similarity, but not vice versa. It is believed that the effect of modeling such global and local relationships among frames in this paper, is similar to that of modeling the long-range and short-range dependencies among frames in deep learning based methods. Experimental results on three benchmark datasets have demonstrated that the proposed approach is superior to not only other sparse subset selection based VS methods but also most unsupervised deep-learning based VS methods. [ABSTRACT FROM AUTHOR]

Graph pattern matching has been extensively investigated on general graphs without time information over decades. Nevertheless, few studies focus on temporal graphs, where a relationship between two vertices takes place at a specific moment and lingers for some time. In this paper, we propose a new notion so-called time-respecting flow graph, in which all paths are time-respecting (i.e., a sequence of contacts with non-decreasing time), and one vertex is distinguished as the root, from which other vertices can be reached via a time-respecting path. Based on this, we explore the problem of time-respecting flow graph pattern matching on temporal graphs. This problem motivates important applications in epidemiology, information diffusion, crime detection, etc. To address it, we present one baseline algorithm as well as two optimized algorithms that utilize several efficient matching strategies and topological sort based technique to boost efficiency. Extensive experimental evaluation using both real and synthetic data sets demonstrates the effectiveness and efficiency of our proposed algorithms. Compared with baseline method, our optimized algorithms could achieve up to three orders of magnitude speedup. [ABSTRACT FROM AUTHOR]

Automated machine learning (AutoML) has achieved remarkable progress on various tasks, which is attributed to its minimal involvement of manual feature and model designs. However, most of existing AutoML pipelines only touch parts of the full machine learning pipeline, e.g., neural architecture search or optimizer selection. This leaves potentially important components such as data cleaning and model ensemble out of the optimization, and still results in considerable human involvement and suboptimal performance. The main challenges lie in the huge search space assembling all possibilities over all components, as well as the generalization ability over different tasks like image, text, and tabular etc. In this paper, we present a first-of-its-kind fully AutoML pipeline, to comprehensively automate data preprocessing, feature engineering, model generation/selection/training and ensemble for an arbitrary dataset and evaluation metric. Our innovation lies in the comprehensive scope of a learning pipeline, with a novel “life-long” knowledge anchor design to fundamentally accelerate the search over the full search space. Such knowledge anchors record detailed information of pipelines and integrates them with an evolutionary algorithm for joint optimization across components. Experiments demonstrate that the result pipeline achieves state-of-the-art performance on multiple datasets and modalities. Specifically, the proposed framework was extensively evaluated in the NeurIPS 2019 AutoDL challenge, and won the only champion with a significant gap against other approaches, on all the image, video, speech, text and tabular tracks. [ABSTRACT FROM AUTHOR]

Neural architecture search (NAS) has emerged as a promising avenue for automatically designing task-specific neural networks. Existing NAS approaches require one complete search for each deployment specification of hardware or objective. This is a computationally impractical endeavor given the potentially large number of application scenarios. In this paper, we propose Neural Architecture Transfer (NAT) to overcome this limitation. NAT is designed to efficiently generate task-specific custom models that are competitive under multiple conflicting objectives. To realize this goal we learn task-specific supernets from which specialized subnets can be sampled without any additional training. The key to our approach is an integrated online transfer learning and many-objective evolutionary search procedure. A pre-trained supernet is iteratively adapted while simultaneously searching for task-specific subnets. We demonstrate the efficacy of NAT on 11 benchmark image classification tasks ranging from large-scale multi-class to small-scale fine-grained datasets. In all cases, including ImageNet, NATNets improve upon the state-of-the-art under mobile settings (≤ 600M Multiply-Adds). Surprisingly, small-scale fine-grained datasets benefit the most from NAT. At the same time, the architecture search and transfer is orders of magnitude more efficient than existing NAS methods. Overall, experimental evaluation indicates that, across diverse image classification tasks and computational objectives, NAT is an appreciably more effective alternative to conventional transfer learning of fine-tuning weights of an existing network architecture learned on standard datasets. Code is available at https://github.com/human-analysis/neural-architecture-transfer. [ABSTRACT FROM AUTHOR]

Recently, with the explosive increase in Internet data, the traditional Graph-based Semi-Supervised Learning (GSSL) model is not suitable to deal with large scale data as the high computation complexity. Besides, GSSL models perform classification on a fixed input data graph. The quality of initialized graph has a great effect on the classification result. To solve this problem, in this paper, we propose a novel approach, named optimal bipartite graph-based SSL (OBGSSL). Instead of fixing the input data graph, we learn a new bipartite graph to make the result more robust. Based on the learned bipartite graph, the labels of the original data and anchors can be calculated simultaneously, which solves co-classification problem in SSL. Then, we use the label of anchor to handle out-of-sample problem, which preserves well classification performance and saves much time. The computational complexity of OBGSSL is O(ndmt + nm2), which is a significant improvement compared with traditional GSSL methods that need O(n2d + n3) , where n, d, m and t are the number of samples, features anchors and iterations, respectively. Experimental results demonstrate the effectiveness and efficiency of our OBGSSL model. [ABSTRACT FROM AUTHOR]

Global sensitivity analysis (GSA) of distribution system with respect to stochastic PV and load variations plays an important role in designing optimal voltage control schemes. This paper proposes a data-driven framework for GSA of distribution system. In particular, two representative surrogate modeling-based approaches are developed, including the traditional Gaussian process-based and the analysis of variance (ANOVA) kernel ones. The key idea is to develop a surrogate model that captures the hidden global relationship between voltage and real and reactive power injections from the historical data. With the surrogate model, the Sobol indices can be conveniently calculated through either the sampling-based method or the analytical method to assess the global sensitivity of voltage to variations of load and PV power injections. The sampling-based method estimates the Sobol indices using Monte Carlo simulations while the analytical method calculates them by resorting to the ANOVA expansion framework. Comparison results with other model-based GSA methods on the unbalanced three-phase IEEE 37-bus and 123-bus distribution systems show that the proposed framework can achieve much higher computational efficiency with negligible loss of accuracy. The results on a real 240-bus distribution system using actual smart meter data further validate the feasibility and scalability of the proposed framework. [ABSTRACT FROM AUTHOR]

Large blackouts in power grids are often the consequence of uncontrolled failure cascades. The ability to predict the failure cascade process in an efficient and accurate manner is important for power system contingency analysis. In this paper, we propose to apply the influence model for the prediction and screening of failure cascades in large scale DC and AC power networks. Then, the trained influence model is applied to some large power grids with thousands of buses and transmission lines. The prediction performance is evaluated in four different aspects, from the global perspective of the overall failure size to the individual information regarding the link failure time. The results show that under limited training samples, the proposed framework is capable of predicting the failure cascade size with a 7% error rate, the final state of links with a 10% error rate, and the failure time within 1 time unit for both the DC and AC model. One major advantage of the proposed method is that it can reduce the computational time of the failure cascade prediction by a few orders of magnitude with limited compromise in accuracy, as compared to the power flow based contingency analysis. Another important feature of the proposed method is that the trained influence parameters can reveal the critical initial contingencies. This information is very helpful for identifying the worst contingency scenarios for system operators. [ABSTRACT FROM AUTHOR]

A state estimation framework that eliminates the need for a topology processor is presented in this paper. By retaining switching devices (SDs) in the network model, this approach allows estimation of their statuses. Consequently, topology error detection becomes part of the SE process. Since this approach requires expansion of bus-branch models with SDs, the conventional state estimation formulation is accordingly modified to avoid numerical issues due to extremely small (large) impedance values of open (closed) switching devices. The scalability of the proposed framework is achieved by parallel processing, which is implemented after partitioning the system into zones. The measurement overhead is kept minimal by utilizing two optimal measurement placement algorithms and taking advantage of KCL-based virtual measurements. Case studies presented show that the proposed method can identify concurrent bad data and topology errors. The improvements in computation times due to parallel processing are demonstrated through simulations on the IEEE 300-bus system with and without zone-partitioning. [ABSTRACT FROM AUTHOR]

This paper proposes a new decentralized data-driven load restoration (DDLR) scheme for transmission and distribution (TD) systems with high penetration of wind power. Robust DDLR models are constructed in order to handle uncertainties and ensure the feasibility of decentralized schemes. The Wasserstein metric is used to describe the ambiguity sets of probability distributions in order to build the complete DDLR model and realize computationally tractable formulation. A data-driven model-nested analytical target cascading (DATC) algorithm is developed to obtain the final load restoration result by iteratively solving small-scale mathematical models. The proposed DDLR scheme provides load restoration results with adjustable robustness, and performance efficiency is independent from the amount of data. The DDLR scheme makes full use of the available data while respecting information privacy requirements of independent operated systems, and ensures the feasibility of a decentralized load restoration strategy even in the worst-case condition. The effectiveness of the proposed method is validated using a small-scale TD system and a large-scale system with the IEEE 118-bus TS and thirty IEEE-33 DSs, showing high computational efficiency and superior restoration performance. [ABSTRACT FROM AUTHOR]

In this paper, a coupled interaction matrix is proposed to describe the interactions between line outages and the load shed at buses. The coupled interaction matrix is effectively estimated by the Expectation Maximization algorithm. A highly probabilistic coupled interaction model is further proposed to efficiently generate cascades with both line outages and the load shed based on the coupled interaction matrix and the distribution of initial outages. To mitigate cascading failures, critical links are identified based on the coupled interaction matrix by calculating a comprehensive severity index that considers the consequences of both line outages and the load shed. Simulation results on the IEEE 300-bus system verify the effectiveness of the proposed approach. The cascades generated from the coupled interaction model match the statistics of the original cascades very well. The identified critical links based on the comprehensive severity index enable a proper tradeoff between reducing line outages and reducing the load shed, leading to a better mitigation effect than only considering either line outages or the load shed. [ABSTRACT FROM AUTHOR]

This paper presents the modeling of some protective relays commonly used in generation and transmission systems, and their integration in three-phase RMS dynamic simulation tool. The three-phase models of the network and the power apparatuses, utilizing phase frame representation, enlarges the possibility to better represent the protection systems, since the relays involving ground and neutral circuitry can be modeled. The network can be modeled with a node-breaker topology representation, facilitating the integration of protecting relays and the switchgear. The relay modeling framework can also be used in positive-sequence RMS dynamic simulation tools with few adjustments in the measured quantities. Simulation results in realistic small and large-scale systems showing the performance of the proposed relay modeling framework and a comparison with an EMT tool are presented. [ABSTRACT FROM AUTHOR]

Though the convex optimization has been widely used in power systems, it still cannot guarantee to yield a tight (accurate) solution to some problems. To mitigate this issue, this paper proposes an ensemble learning based convex approximation for alternating current (AC) power flow equations that differs from the existing convex relaxations. The proposed approach is based on three-phase quadratic power flow equations in rectangular coordinates. To develop this data-driven convex approximation of power flows, the polynomial regression (PR) is first deployed as a basic learner to fit convex relationships between the independent and dependent variables. Then, ensemble learning algorithms such as gradient boosting (GB) and bagging are introduced to combine learners to boost model performance. Based on the learned convex approximation of power flow, optimal power flow (OPF) is formulated as a convex quadratic programming problem. The simulation results on IEEE standard cases of both balanced and unbalanced systems show that, in the context of solving OPF, the proposed data-driven convex approximation outperforms the conventional semi-definite programming (SDP) relaxation in both accuracy and computational efficiency, especially in the cases that the conventional SDP relaxation fails. [ABSTRACT FROM AUTHOR]

Detection, parsing, and future predictions on sequence data (e.g., videos) require the algorithms to capture non-Markovian and compositional properties of high-level semantics. Context-free grammars are natural choices to capture such properties, but traditional grammar parsers (e.g., Earley parser) only take symbolic sentences as inputs. In this paper, we generalize the Earley parser to parse sequence data which is neither segmented nor labeled. Given the output of an arbitrary probabilistic classifier, this generalized Earley parser finds the optimal segmentation and labels in the language defined by the input grammar. Based on the parsing results, it makes top-down future predictions. The proposed method is generic, principled, and widely applicable. Experiment results clearly show the benefit of our method for both human activity parsing and prediction on three video datasets. [ABSTRACT FROM AUTHOR]

Biobased production has gained much attention in academia and industries as it can achieve environmental, social, and economic sustainability based on renewable materials. This paper addresses a sustainable operation control problem of biobased production with a particular focus on continuous process. We first formulate a dynamical model of biobased continuous production and present its optimal control problem. Furthermore, we discuss the characterization of solutions to the dynamical model and the relevant properties of the optimal control problem. This control problem is a multiobjective nonlinear optimization program. To tackle this problem, we develop a hybrid algorithm by combining a particle swarm algorithm with a multisearch procedure. We further provide a real case to validate our proposed models and algorithm. For this case, we evaluate the impact of inputs on operation dynamics, compared with experimental data. We find that the flow rate of raw materials have a higher impact on the productivity and sustainability of biobased operations than initial concentrations. Finally, we adopt the flow rate of raw materials as a control variable and identify the best operations policies. Computational results reveal that the proposed dynamical and control models are valid and that the hybrid algorithm is capable of solving multiobjective nonlinear optimization. [ABSTRACT FROM AUTHOR]

Semiconductor manufacturing consists of multiple sequential processes. In addition, even in a single process, a wafer must pass several steps. Accordingly, a dataset generated in semiconductor manufacturing has sequential information. Thus, the sequential information between steps and processes must be considered when predicting a target variable such as a yield or defect status. This paper proposes a method that utilizes the concept of residual learning to capture sequential information. Specifically, we propose to learn several modules that use data gathered starting from different steps and obtain a final decision by combining all modules’ decisions. In each module including multiple models, the first model is trained to predict the target variable using the data from the earliest step, and the remaining models are trained to predict the residuals that cannot be explained by the models for the previous steps based on the concept of residual learning. We conducted extensive experiments using two real-world semiconductor manufacturing datasets and found that even though each module’s performance was not good, the final decision obtained by combining all the modules’ decisions achieved a significant performance improvement. As a result, the proposed method significantly outperformed the baseline models. [ABSTRACT FROM AUTHOR]

Timely acquiring the earthquake-induced damage of buildings is crucial for emergency assessment and post-disaster rescue. Optical remote sensing is a typical method for obtaining seismic data due to its wide coverage and fast response speed. Convolutional neural networks (CNNs) are widely applied for remote sensing image recognition. However, insufficient extraction and expression ability of global correlations between local image patches limit the performance of dense building segmentation. This paper proposes an improved Swin Transformer to segment dense urban buildings from remote sensing images with complex backgrounds. The original Swin Transformer is used as a backbone of the encoder, and a convolutional block attention module is employed in the linear embedding and patch merging stages to focus on significant features. Hierarchical feature maps are then fused to strengthen the feature extraction process and fed into the UPerNet (as the decoder) to obtain the final segmentation map. Collapsed and non-collapsed buildings are labeled from remote sensing images of the Yushu and Beichuan earthquakes. Data augmentations of horizontal and vertical flipping, brightness adjustment, uniform fogging, and non-uniform fogging are performed to simulate actual situations. The effectiveness and superiority of the proposed method over the original Swin Transformer and several mature CNN-based segmentation models are validated by ablation experiments and comparative studies. The results show that the mean intersection-over-union of the improved Swin Transformer reaches 88.53%, achieving an improvement of 1.3% compared to the original model. The stability, robustness, and generalization ability of dense building recognition under complex weather disturbances are also validated. [ABSTRACT FROM AUTHOR]

Low-rank tensor representation philosophy has enjoyed a reputation in many hyperspectral image (HSI) low-level vision applications, but previous studies often failed to comprehensively exploit the low-rank nature of HSI along different modes in low-dimensional subspace, and unsurprisingly handled only one specific task. To address these challenges, in this paper, we figured out that in addition to the spatial correlation, the spectral dependency of HSI also implicitly exists in the coefficient tensor of its subspace, this crucial dependency that was not fully utilized by previous studies yet can be effectively exploited in a cascaded manner. This led us to propose a unified subspace low-rank learning regime with a new tensor cascaded rank minimization, named STCR, to fully couple the low-rankness of HSI in different domains for various low-level vision tasks. Technically, the high-dimensional HSI was first projected into a low-dimensional tensor subspace, then a novel tensor low-cascaded-rank decomposition was designed to collapse the constructed tensor into three core tensors in succession to more thoroughly exploit the correlations in spatial, nonlocal, and spectral modes of the coefficient tensor. Next, difference continuity-regularization was introduced to learn a basis that more closely approximates the HSI’s endmembers. The proposed regime realizes a comprehensive delineation of the self-portrait of HSI tensor. Extensive evaluations conducted with dozens of state-of-the-art (SOTA) baselines on eight datasets verified that the proposed regime is highly effective and robust to typical HSI low-level vision tasks, including denoising, compressive sensing reconstruction, inpainting, and destriping. The source code of our method is released at https://github.com/CX-He/STCR.git. [ABSTRACT FROM AUTHOR]

Dependency-aware jobs, such as the big data analytic workflows, are commonly executed on the cloud. They are compiled to directed acyclic graphs, with tasks linked in regarding the dependency. The cloud scheduler, which maintains a large number of resources, is responsible to execute tasks in parallel. To resolve the complex dependencies, Deep Reinforcement Learning (DRL) based schedulers are widely applied. However, we find that the DRL-based schedulers are vulnerable to the perturbations in the input jobs and may generate falsified decisions to benefit a particular job while delaying the others. By perturbation, we mean a slight adjustment to the job's node features or dependencies, while not changing its functionality. In this paper, we first explore the vulnerability of DRL-based schedulers to job perturbations without accessing the information of the DRL models used in the scheduler. We devise the black-box perturbation system, in which, a proxy model is trained to mimic the DRL-based scheduling policy. We show that the high-faith proxy model can help to craft effective perturbations. The DRL-based schedulers can be as high as 60% likely to be badly affected by the perturbations. Then, we investigate the solution to improve the robustness of DRL-based schedulers to such perturbations. We propose an adversarial training framework to force the neural model to adapt to the perturbation patterns during training so as to eliminate the potential damage during applications. Experiments show that the adversarial-trained scheduler is more robust, reducing the chance of being affected to 3-fold less and the potential bad effects halved. [ABSTRACT FROM AUTHOR]

Sleep staging is the essential step in sleep quality assessment and sleep disorders diagnosis. However, most current automatic sleep staging approaches use recurrent neural networks (RNN), resulting in a relatively large training burden. Moreover, these methods only extract information of the whole epoch or adjacent epochs, ignoring the local signal variations within epoch. To address these issues, a novel deep learning architecture named segmented attention network (SAN) is proposed in this paper. The architecture can be divided into feature extraction (FE) and time sequence encoder (TSE). The FE module consists of multiple multiscale CNN (MMCNN) and residual squeeze and excitation block (SE block). The former extracts features from multiple equal-length EEG segments and the latter reinforced the features. The TSE module based on a multi-head attention mechanism could capture the temporal information in the features extracted by FE module. Noteworthy, in SAN, we replaced the RNN module with a TSE module for temporal learning and made the network faster. The evaluation of the model was performed on two widely used public datasets, Montreal Archive of Sleep Studies (MASS) and Sleep-EDFX, and one clinical dataset from Huashan Hospital of Fudan University, Shanghai, China (HSFU). The proposed model achieved the accuracy of 85.5%, 86.4%, 82.5% on Sleep-EDFX, MASS and HSFU, respectively. The experimental results exhibited favorable performance and consistent improvements of SAN on different datasets in comparison with the state-of-the-art studies. It also proved the necessity of sleep staging by integrating the local characteristics within epochs and adjacent informative features among epochs. [ABSTRACT FROM AUTHOR]

Recently, hyperbolic deep neural networks (HDNNs) have been gaining momentum as the deep representations in the hyperbolic space provide high fidelity embeddings with few dimensions, especially for data possessing hierarchical structure. Such a hyperbolic neural architecture is quickly extended to different scientific fields, including natural language processing, single-cell RNA-sequence analysis, graph embedding, financial analysis, and computer vision. The promising results demonstrate its superior capability, significant compactness of the model, and a substantially better physical interpretability than its counterpart in the euclidean space. To stimulate future research, this paper presents a comprehensive review of the literature around the neural components in the construction of HDNN, as well as the generalization of the leading deep approaches to the hyperbolic space. It also presents current applications of various tasks, together with insightful observations and identifying open questions and promising future directions. [ABSTRACT FROM AUTHOR]

A dynamically weighted directed network (DWDN) is frequently encountered in various big data-related applications like a terminal interaction pattern analysis system (TIPAS) concerned in this study. It consists of large-scale dynamic interactions among numerous nodes. As the involved nodes increase drastically, it becomes impossible to observe their full interactions at each time slot, making a resultant DWDN High Dimensional and Incomplete (HDI). An HDI DWDN, in spite of its incompleteness, contains rich knowledge regarding involved nodes’ various behavior patterns. To extract such knowledge from an HDI DWDN, this paper proposes a novel Alternating direction method of multipliers (ADMM)-based Nonnegative Latent-factorization of Tensors (ANLT) model. It adopts three-fold ideas: a) building a data density-oriented augmented Lagrangian function for efficiently handling an HDI tensor's incompleteness and nonnegativity; b) splitting the optimization task in each iteration into an elaborately designed subtask series where each one is solved based on the previously solved ones following the ADMM principle to achieve fast convergence; and c) theoretically proving that its convergence is guaranteed with its efficient learning scheme. Experimental results on six DWDNs from real applications demonstrate that the proposed ANLT outperforms state-of-the-art models significantly in both computational efficiency and prediction accuracy for missing links of an HDI DWDN. Hence, this study proposes a novel and efficient approach to large-scale DWDN representation. [ABSTRACT FROM AUTHOR]

Clinically oriented deep learning algorithms, combined with large-scale medical datasets, have significantly promoted computer-aided diagnosis. To address increasing ethical and privacy issues, Federated Learning (FL) adopts a distributed paradigm to collaboratively train models, rather than collecting samples from multiple institutions for centralized training. Despite intensive research on FL, two major challenges are still existing when applying FL in the real-world medical scenarios, including the performance degradation (i.e., retrogress) after each communication and the intractable class imbalance. Thus, in this paper, we propose a novel personalized FL framework to tackle these two problems. For the retrogress problem, we first devise a Progressive Fourier Aggregation (PFA) at the server side to gradually integrate parameters of client models in the frequency domain. Then, at the client side, we design a Deputy-Enhanced Transfer (DET) to smoothly transfer global knowledge to the personalized local model. For the class imbalance problem, we propose the Conjoint Prototype-Aligned (CPA) loss to facilitate the balanced optimization of the FL framework. Considering the inaccessibility of private local data to other participants in FL, the CPA loss calculates the global conjoint objective based on global imbalance, and then adjusts the client-side local training through the prototype-aligned refinement to eliminate the imbalance gap with such a balanced goal. Extensive experiments are performed on real-world dermoscopic and prostate MRI FL datasets. The experimental results demonstrate the advantages of our FL framework in real-world medical scenarios, by outperforming state-of-the-art FL methods with a large margin. The source code is available at https://github.com/CityU-AIM-Group/PRR-Imbalance https://github.com/CityU-AIM-Group/PRR-Imbalance. [ABSTRACT FROM AUTHOR]

This paper presents an injected current sensitivity (ICS) based multi-phase load flow (LF) methodology with minimal Jacobian computation for the three-phase unbalanced distribution system with multiple Distributed Energy Resources (DERs). In the proposed approach, first, a generalized bus admittance and Jacobian matrix have been formulated that include various distribution system components such as lines, shunt capacitors, voltage control devices such as regulators, different transformer connections, and load models. Second, DERs are modeled as a PV bus and incorporated into the proposed LF algorithm by formulating a reactive power injection-based sensitivity matrix that iteratively computes its net power injections. Unlike the traditional Jacobian matrix-based LF methods where an update of Jacobian (size and element) is required for each PV bus, this method does not require any update, hence, making it faster and more flexible to include a large number of DERs. From the various tests performed on the standard IEEE three-phase distribution network and their derivatives, it has been observed that the proposed approach is accurate, efficient, computationally less complex, and scalable. [ABSTRACT FROM AUTHOR]

Recently, large offshore wind power plants have been installed far from the shore, using long HVAC three-core armored cables to export power. Its high capacitance may contribute to the appearance of unwanted phenomena, such as overvoltages or resonances at low frequencies. To adequately assess these problems, detailed and reliable cable models are required to develop time-domain/frequency-domain analyses on this type of cables. This paper presents, for the first time in the literature, an assessment on the performance of 3D finite element method-based (3D-FEM) models for developing frequency-domain analyses on three-core armored cables, confronting simulation results with experimental measurements found in the literature for three real cables. To this aim, a simplified ultra-shortened 3D-FEM model is proposed to reduce the simulation time during frequency sweeps, through which relevant aspects never analyzed before with frequency-domain 3D-FEM simulations are addressed, such as total losses, induced sheath current, magnetic field around the power cable, positive and zero sequence harmonic impedances, as well as resonant frequencies. Also, a time-domain example derived from the frequency-domain analysis is provided. Remarkable results are obtained when comparing computed values and measurements, presenting the simplified ultra-shortened 3D-FEM model as a valuable tool for the frequency-domain analysis of these cables. [ABSTRACT FROM AUTHOR]

The heterogeneity in recently published knowledge graph embedding models’ implementations, training, and evaluation has made fair and thorough comparisons difficult. To assess the reproducibility of previously published results, we re-implemented and evaluated 21 models in the PyKEEN software package. In this paper, we outline which results could be reproduced with their reported hyper-parameters, which could only be reproduced with alternate hyper-parameters, and which could not be reproduced at all, as well as provide insight as to why this might be the case. We then performed a large-scale benchmarking on four datasets with several thousands of experiments and 24,804 GPU hours of computation time. We present insights gained as to best practices, best configurations for each model, and where improvements could be made over previously published best configurations. Our results highlight that the combination of model architecture, training approach, loss function, and the explicit modeling of inverse relations is crucial for a model’s performance and is not only determined by its architecture. We provide evidence that several architectures can obtain results competitive to the state of the art when configured carefully. We have made all code, experimental configurations, results, and analyses available at https://github.com/pykeen/pykeen and https://github.com/pykeen/benchmarking. [ABSTRACT FROM AUTHOR]

Graph learning has emerged as a promising technique for multi-view clustering due to its efficiency of learning a unified graph from multiple views. Previous multi-view graph learning methods mainly try to exploit the multi-view consistency to boost learning performance. However, these methods ignore the prevalent multi-view diversity which may be induced by noise, corruptions, or even view-specific attributes. In this paper, we propose to simultaneously and explicitly leverage the multi-view consistency and the multi-view diversity in a unified framework. The consistent parts are further fused to our target graph with a clear clustering structure, on which the cluster label to each instance can be directly allocated without any postprocessing such as $k$ k -means in classical spectral clustering. In addition, our model can automatically assign suitable weight for each view based on its clustering capacity. By leveraging the subtasks of measuring the diversity of graphs, integrating the consistent parts with automatically learned weights, and allocating cluster label to each instance in a joint framework, each subtask can be alternately boosted by utilizing the results of the others towards an overall optimal solution. Extensive experimental results on several benchmark multi-view datasets demonstrate the effectiveness of our model in comparison to several state-of-the-art algorithms. [ABSTRACT FROM AUTHOR]

Federated learning (FL) is an emerging privacy-preserving paradigm that enables multiple participants collaboratively to train a global model without uploading raw data. Considering heterogeneous computing and communication capabilities of different participants, asynchronous FL can avoid the stragglers effect in synchronous FL and adapts to scenarios with vast participants. Both staleness and non-IID data in asynchronous FL would reduce the model utility. However, there exists an inherent contradiction between the solutions to the two problems. That is, mitigating the staleness requires to select less but consistent gradients while coping with non-IID data demands more comprehensive gradients. To address the dilemma, this paper proposes a two-stage weighted $K$ K asynchronous FL with adaptive learning rate (WKAFL). By selecting consistent gradients and adjusting learning rate adaptively, WKAFL utilizes stale gradients and mitigates the impact of non-IID data, which can achieve multifaceted enhancement in training speed, prediction accuracy and training stability. We also present the convergence analysis for WKAFL under the assumption of unbounded staleness to understand the impact of staleness and non-IID data. Experiments implemented on both benchmark and synthetic FL datasets show that WKAFL has better overall performance compared to existing algorithms. [ABSTRACT FROM AUTHOR]

Long short-term memory (LSTM) is a type of powerful deep neural network that has been widely used in many sequence analysis and modeling applications. However, the large model size problem of LSTM networks make their practical deployment still very challenging, especially for the video recognition tasks that require high-dimensional input data. Aiming to overcome this limitation and fully unlock the potentials of LSTM models, in this paper we propose to perform algorithm and hardware co-design towards high-performance energy-efficient LSTM networks. At algorithm level, we propose to develop fully decomposed hierarchical Tucker (FDHT) structure-based LSTM, namely FDHT-LSTM, which enjoys ultra-low model complexity while still achieving high accuracy. In order to fully reap such attractive algorithmic benefit, we further develop the corresponding customized hardware architecture to support the efficient execution of the proposed FDHT-LSTM model. With the delicate design of memory access scheme, the complicated matrix transformation can be efficiently supported by the underlying hardware without any access conflict in an on-the-fly way. Our evaluation results show that both the proposed ultra-compact FDHT-LSTM models and the corresponding hardware accelerator achieve very high performance. Compared with the state-of-the-art compressed LSTM models, FDHT-LSTM enjoys both order-of-magnitude reduction (more than $1000 \times$ 1000 × ) in model size and significant accuracy improvement (0.6% to 12.7%) across different video recognition datasets. Meanwhile, compared with the state-of-the-art tensor decomposed model-oriented hardware TIE, our proposed FDHT-LSTM architecture achieve $2.5\times$ 2. 5 × , $1.46\times$ 1. 46 × and $2.41\times$ 2. 41 × increase in throughput, area efficiency and energy efficiency, respectively on LSTM-Youtube workload. For LSTM-UCF workload, our proposed design also outperforms TIE with $1.9\times$ 1. 9 × higher throughput, $1.83\times$ 1. 83 × higher energy efficiency and comparable area efficiency. [ABSTRACT FROM AUTHOR]

As deep neural networks (DNNs) continue to find applications in ever more domains, the exact nature of the neural network architecture becomes an increasingly sensitive subject, due to either intellectual property protection or risks of adversarial attacks. While prior work has explored aspects of the risk associated with model leakage, exactly which parts of the model are most sensitive and how one infers the full architecture of the DNN when nothing is known about the structure a priori are problems that have been left unexplored. In this paper we address this gap, first by presenting a schema for reasoning about model leakage holistically, and then by proposing and quantitatively evaluating DeepSniffer, a novel learning-based model extraction framework that uses no prior knowledge of the victim model. DeepSniffer is robust to architectural and system noises introduced by the complex memory hierarchy and diverse run-time system optimizations. Taking GPU platforms as a showcase, DeepSniffer performs model extraction by learning both the architecture-level execution features of kernels and the inter-layer temporal association information introduced by the common practice of DNN design. We demonstrate that DeepSniffer works experimentally in the context of an off-the-shelf Nvidia GPU platform running a variety of DNN models and that the extracted models significantly improve attempts at crafting adversarial inputs. The DeepSniffer project has been released in https://github.com/xinghu7788/DeepSniffer. [ABSTRACT FROM AUTHOR]

Blockchain technologies can enable secure computing environments among mistrusting parties. Permissioned blockchains are particularly enlightened by companies, enterprises, and government agencies due to their efficiency, customizability, and governance-friendly features. Obviously, seamlessly fusing blockchain and cloud computing can significantly benefit permissioned blockchains; nevertheless, most blockchains implemented on clouds are originally designed for loosely-coupled networks where nodes communicate asynchronously, failing to take advantages of the closely-coupled nature of cloud servers. In this paper, we propose an innovative cloud-oriented blockchain – CloudChain, which is a modularized three-layer system composed of the network layer, consensus layer, and blockchain layer. CloudChain is based on a shared-memory model where nodes communicate synchronously by direct memory accesses. We realize the shared-memory model with the Remote Direct Memory Access technology, based on which we propose a shared-memory consensus algorithm to ensure presistence and liveness, the two crucial blockchain security properties countering Byzantine nodes. We also implement a CloudChain prototype based on a RoCEv2-based testbed to experimentally validate our design, and the results verify the feasibility and efficiency of CloudChain. [ABSTRACT FROM AUTHOR]

To improve the viewer’s Quality of Experience (QoE) and optimize computer graphics applications, 3D model quality assessment (3D-QA) has become an important task in the multimedia area. Point cloud and mesh are the two most widely used digital representation formats of 3D models, the visual quality of which is quite sensitive to lossy operations like simplification and compression. Therefore, many related studies such as point cloud quality assessment (PCQA) and mesh quality assessment (MQA) have been carried out to measure the visual quality of distorted 3D models. However, most previous studies utilize full-reference (FR) metrics, which indicates they can not predict the quality level in the absence of the reference 3D model. Furthermore, few 3D-QA metrics consider color information, which significantly restricts their effectiveness and scope of application. In this paper, we propose a no-reference (NR) quality assessment metric for colored 3D models represented by both point cloud and mesh. First, we project the 3D models from 3D space into quality-related geometry and color feature domains. Then, the 3D natural scene statistics (3D-NSS) and entropy are utilized to extract quality-aware features. Finally, a support vector regression (SVR) model is employed to regress the quality-aware features into visual quality scores. Our method is validated on the colored point cloud quality assessment database (SJTU-PCQA), the Waterloo point cloud assessment database (WPC), and the colored mesh quality assessment database (CMDM). The experimental results show that the proposed method outperforms most compared NR 3D-QA metrics with competitive computational resources and greatly reduces the performance gap with the state-of-the-art FR 3D-QA metrics. The code of the proposed model is publicly available now at https://github.com/zzc-1998/NR-3DQA. [ABSTRACT FROM AUTHOR]

Recently, angular margin-based methods have become the mainstream approach for unconstrained face recognition with remarkable success. However, robust face recognition still remains a challenge, as the face is subject to variations in pose, age, expression, occlusion, and illumination, especially in unconstrained scenarios. Since the training dataset are always collected in unconstrained scenarios, it is inevitable that there’re significant number of hard examples in the training process. In this paper, we design a hard example selection function to effectively identify hard examples in the training procedure with the supervision of angular margin-based losses. Furthermore, a novel Intra-class Hard Example Mining (IHEM) loss function is proposed, which penalizes the cosine distance between the hard examples and their class centers to enhance the discriminative power of face representations. To ensure high performance for face recognition, we combine the supervision of angular margin-based loss and IHEM loss for model training. Specifically, during the training procedure, the angular margin-based loss guarantees the power of feature discrimination for face recognition, while the IHEM loss further encourages the intra-class compactness of hard example. Extensive results demonstrate the superiority of our approach. [ABSTRACT FROM AUTHOR]

Deep Neural Networks (DNN) are gaining higher commercial values in computer vision applications, e.g., image classification, video analytics, etc. This calls for urgent demands of the intellectual property (IP) protection of DNN models. In this paper, we present a novel watermarking scheme to achieve the ownership verification of DNN architectures. Existing works all embedded watermarks into the model parameters while treating the architecture as public property. These solutions were proven to be vulnerable by an adversary to detect or remove the watermarks. In contrast, we claim the model architectures as an important IP for model owners, and propose to implant watermarks into the architectures. We design new algorithms based on Neural Architecture Search (NAS) to generate watermarked architectures, which are unique enough to represent the ownership, while maintaining high model usability. Such watermarks can be extracted via side-channel-based model extraction techniques with high fidelity. We conduct comprehensive experiments on watermarked CNN models for image classification tasks and the experimental results show our scheme has negligible impact on the model performance, and exhibits strong robustness against various model transformations and adaptive attacks. [ABSTRACT FROM AUTHOR]

Automatic surgical scene segmentation is fundamental for facilitating cognitive intelligence in the modern operating theatre. Previous works rely on conventional aggregation modules (e.g., dilated convolution, convolutional LSTM), which only make use of the local context. In this paper, we propose a novel framework STswinCL that explores the complementary intra- and inter-video relations to boost segmentation performance, by progressively capturing the global context. We firstly develop a hierarchy Transformer to capture intra-video relation that includes richer spatial and temporal cues from neighbor pixels and previous frames. A joint space-time window shift scheme is proposed to efficiently aggregate these two cues into each pixel embedding. Then, we explore inter-video relation via pixel-to-pixel contrastive learning, which well structures the global embedding space. A multi-source contrast training objective is developed to group the pixel embeddings across videos with the ground-truth guidance, which is crucial for learning the global property of the whole data. We extensively validate our approach on two public surgical video benchmarks, including EndoVis18 Challenge and CaDIS dataset. Experimental results demonstrate the promising performance of our method, which consistently exceeds previous state-of-the-art approaches. Code is available at https://github.com/YuemingJin/STswinCL. [ABSTRACT FROM AUTHOR]

Intrinsic image decomposition is the task of mapping image to albedo and shading. Classical approaches derive methods from spatial models. The modern literature stresses evaluation, by comparing predictions to human judgements (“lighter”, “same as”, “darker”). The best modern intrinsic image methods train a map from image to albedo using images rendered from computer graphics models and example human judgements. This approach yields practical methods, but obtaining rendered images can be inconvenient. Furthermore, the approach cannot explain how a one could learn to recover intrinsic images without geometric, surface and illumination models, as people and animals appear to do. This paper describes a method that learns intrinsic image decomposition without seeing human annotations, rendered data, or ground truth data. Instead, the method relies on paradigms – spatial models of albedo and of shading. Rather than finding the “best” albedo and shading for an image via optimization, our approach trains a neural network on synthetic images. The synthetic images are constructed by multiplying albedos and shading fields sampled from our models. The network is subject to a novel smoothing procedure that ensures good behavior at short scales on real images. An averaging procedure ensures that reported albedo and shading are largely equivariant – different crops and scalings of an image will report the same albedo and shading at shared points. This averaging procedure controls long scale error. The standard evaluation for an intrinsic image method is a WHDR score. Our method achieves WHDR scores competitive with those of strong recent methods allowed to see training WHDR annotations, rendered data, and ground truth data. Our method produces albedo and shading maps with attractive qualitative properties – for example, albedo fields do not suppress wood grain and represent narrow grooves in surfaces well. Because our method is unsupervised, we can compute estimates of the test/train variance of WHDR scores; these are quite large, and suggest is unsafe to rely small differences in reported WHDR. [ABSTRACT FROM AUTHOR]

This paper introduces versatile filters to construct efficient convolutional neural networks that are widely used in various visual recognition tasks. Considering the demands of efficient deep learning techniques running on cost-effective hardware, a number of methods have been developed to learn compact neural networks. Most of these works aim to slim down filters in different ways, e.g., investigating small, sparse or quantized filters. In contrast, we treat filters from an additive perspective. A series of secondary filters can be derived from a primary filter with the help of binary masks. These secondary filters all inherit in the primary filter without occupying more storage, but once been unfolded in computation they could significantly enhance the capability of the filter by integrating information extracted from different receptive fields. Besides spatial versatile filters, we additionally investigate versatile filters from the channel perspective. Binary masks can be further customized for different primary filters under orthogonal constraints. We conduct theoretical analysis on network complexity and an efficient convolution scheme is introduced. Experimental results on benchmark datasets and neural networks demonstrate that our versatile filters are able to achieve comparable accuracy as that of original filters, but require less memory and computation cost. [ABSTRACT FROM AUTHOR]

Traditional Deep Neural Network (DNN) security is mostly related to the well-known adversarial input example attack. Recently, another dimension of adversarial attack, namely, attack on DNN weight parameters, has been shown to be very powerful. As a representative one, the Bit-Flip-based adversarial weight Attack (BFA) injects an extremely small amount of faults into weight parameters to hijack the executing DNN function. Prior works of BFA focus on un-targeted attack that can hack all inputs into a random output class by flipping a very small number of weight bits stored in computer memory. This paper proposes the first work of targeted BFA based (T-BFA) adversarial weight attack on DNNs, which can intentionally mislead selected inputs to a target output class. The objective is achieved by identifying the weight bits that are highly associated with classification of a targeted output through a class-dependent vulnerable weight bit searching algorithm. Our proposed T-BFA performance is successfully demonstrated on multiple DNN architectures for image classification tasks. For example, by merely flipping 27 out of 88 million weight bits of ResNet-18, our T-BFA can misclassify all the images from ’Hen’ class into ’Goose’ class (i.e., 100% attack success rate) in ImageNet dataset, while maintaining 59.35% validation accuracy. Moreover, we successfully demonstrate our T-BFA attack in a real computer prototype system running DNN computation, with Ivy Bridge-based Intel i7 CPU and 8GB DDR3 memory. [ABSTRACT FROM AUTHOR]

3D neural networks are widely used in real-world applications (e.g., AR/VR headsets, self-driving cars). They are required to be fast and accurate; however, limited hardware resources on edge devices make these requirements rather challenging. Previous work processes 3D data using either voxel-based or point-based neural networks, but both types of 3D models are not hardware-efficient due to the large memory footprint and random memory access. In this paper, we study 3D deep learning from the efficiency perspective. We first systematically analyze the bottlenecks of previous 3D methods. We then combine the best from point-based and voxel-based models together and propose a novel hardware-efficient 3D primitive, Point-Voxel Convolution (PVConv). We further enhance this primitive with the sparse convolution to make it more effective in processing large (outdoor) scenes. Based on our designed 3D primitive, we introduce 3D Neural Architecture Search (3D-NAS) to explore the best 3D network architecture given a resource constraint. We evaluate our proposed method on six representative benchmark datasets, achieving state-of-the-art performance with 1.8-23.7× measured speedup. Furthermore, our method has been deployed to the autonomous racing vehicle of MIT Driverless, achieving larger detection range, higher accuracy and lower latency. [ABSTRACT FROM AUTHOR]

Conventional salient object detection models cannot differentiate the importance of different salient objects. Recently, two works have been proposed to detect saliency ranking by assigning different degrees of saliency to different objects. However, one of these models cannot differentiate object instances and the other focuses more on sequential attention shift order inference. In this paper, we investigate a practical problem setting that requires simultaneously segment salient instances and infer their relative saliency rank order. We present a novel unified model as the first end-to-end solution, where an improved Mask R-CNN is first used to segment salient instances and a saliency ranking branch is then added to infer the relative saliency. For relative saliency ranking, we build a new graph reasoning module by combining four graphs to incorporate the instance interaction relation, local contrast, global contrast, and a high-level semantic prior, respectively. A novel loss function is also proposed to effectively train the saliency ranking branch. Besides, a new dataset and an evaluation metric are proposed for this task, aiming at pushing forward this field of research. Finally, experimental results demonstrate that our proposed model is more effective than previous methods. We also show an example of its practical usage on adaptive image retargeting. [ABSTRACT FROM AUTHOR]