Search

This report describes The University of Texas Student Cluster Competition team’s effort to reproduce the results of “MemXCT: memory-centric X-ray CT reconstruction with massive parallelization” (Hidayetoğlu et al., 2019). The article details a new memory-centric approach that reconstructs X-ray computed tomography (XCT) from noisy raw data. In our reproduction experiments, we utilized Microsoft Azure’s CycleCloud tool to provision, orchestrate, and manage our computing cluster in the cloud. In particular, we scheduled and benchmarked reconstruction workloads using Azure’s CPU-based HC44rs and GPU-based NC12s v2 virtual machine (VM) types to evaluate the scalability properties of the reconstruction approach and the performance differences between architectures. The HC44rs VMs contained 44 Intel Xeon Platinum cores, while the NC12s v2 VM was equipped with two NVIDIA P100 GPUs. We used a recent version of Intel’s compiler stack with the MKL library for our CPU code along with CUDA 11.1 on GPUs. Overall, our results confirm the findings of the original article, demonstrating similar acceleration on GPUs and scalability properties on CPUs. Digital artifacts from these experiments are available at: 10.5281/zenodo.5598108 [ABSTRACT FROM AUTHOR]

The tridiagonal solver is an important kernel and is widely supported in mainstream numerical libraries. While parallel algorithms have been studied for many-core architectures, the performance of current algorithms and implementations is still hindered by input size sensitivity and cross-platform portability. In this paper, we propose a novel algorithm WM-pGE for the batched solution of diagonally dominant tridiagonal systems. The algorithm balances the key design objectives, including computation complexity, memory complexity, parallelism, and input size sensitivity, better than existing algorithms. Moreover, an elegant formulation is presented to show the implementation and cross-platform optimization without loss of efficiency and generality, by extracting the platform-dependent works into only four vector operators. The results from our batched tridiagonal experiments show that the proposed algorithm outperforms the prior work PCR-pThomas by 25% and 12% on NVIDIA Tesla V100 in single and double precision, respectively. On Intel KNL, our method achieves a 10% improvement in performance over PCR-pThomas in double precision. [ABSTRACT FROM AUTHOR]

This paper presents a deep architecture, called pyramidal semantic correspondence networks (PSCNet), that estimates locally-varying affine transformation fields across semantically similar images. To deal with large appearance and shape variations that commonly exist among different instances within the same object category, we leverage a pyramidal model where the affine transformation fields are progressively estimated in a coarse-to-fine manner so that the smoothness constraint is naturally imposed. Different from the previous methods which directly estimate global or local deformations, our method first starts to estimate the transformation from an entire image and then progressively increases the degree of freedom of the transformation by dividing coarse cell into finer ones. To this end, we propose two spatial pyramid models by dividing an image in a form of quad-tree rectangles or into multiple semantic elements of an object. Additionally, to overcome the limitation of insufficient training data, a novel weakly-supervised training scheme is introduced that generates progressively evolving supervisions through the spatial pyramid models by leveraging a correspondence consistency across image pairs. Extensive experimental results on various benchmarks including TSS, Proposal Flow-WILLOW, Proposal Flow-PASCAL, Caltech-101, and SPair-71k demonstrate that the proposed method outperforms the lastest methods for dense semantic correspondence. [ABSTRACT FROM AUTHOR]

Recent work has shown that convolutional networks can be substantially deeper, more accurate, and efficient to train if they contain shorter connections between layers close to the input and those close to the output. In this paper, we embrace this observation and introduce the Dense Convolutional Network (DenseNet), which connects each layer to every other layer in a feed-forward fashion. Whereas traditional convolutional networks with $L$ L layers have $L$ L connections—one between each layer and its subsequent layer—our network has $\frac{L(L+1)}{2}$ L (L + 1) 2 direct connections. For each layer, the feature-maps of all preceding layers are used as inputs, and its own feature-maps are used as inputs into all subsequent layers. DenseNets have several compelling advantages: they alleviate the vanishing-gradient problem, encourage feature reuse and substantially improve parameter efficiency. We evaluate our proposed architecture on four highly competitive object recognition benchmark tasks (CIFAR-10, CIFAR-100, SVHN, and ImageNet). DenseNets obtain significant improvements over the state-of-the-art on most of them, whilst requiring less parameters and computation to achieve high performance. [ABSTRACT FROM AUTHOR]

The nine papers in this special section focus on new developments in agile software and reports on applications for its use. A key aspect for the extensive use of agile software is that it supports developers with coping with the growing uncertainty and turbulence in technological and market environments. Feedback and change are at the core of Agile for a dynamic, evolving, and organic, rather than static, predefined, and mechanistic development process advocated by waterfall management. To create timely, high-quality, cost-efficient, and innovative solutions, Agile developers organized in small, colocated, autonomous teams, build and test software in rapid iterative cycles, actively involving users to gather feedback, updating the project scope, and plan "on-the-fly," using face-to-face communication as opposed to documentation. These papers contribute to the state-of-the-art of agile research by offering a rich, up-todate account of the dynamics occurring when expanding Agile into "not-just-software" contexts of the key challenges and perils related to the scaling and of the possible solutions to them. [ABSTRACT FROM AUTHOR]

This paper studies the device activity detection problem in a multi-cell massive multiple-input multiple-output (MIMO) system, in which the active devices transmit signature sequences to multiple base stations (BSs) that are connected to a central unit (CU), and the BSs cooperate across multiple cells to detect the active devices based on the sample covariance matrices at the BSs. This paper demonstrates the importance of exploiting the knowledge of channel large-scale fadings in this cooperative detection setting through a phase transition analysis, which characterizes the length of signature sequences needed for successful device activity detection in the massive MIMO regime. It is shown that when the large-scale fadings are known, the phase transition for the multi-cell scenario is approximately the same as that of a single-cell system. In this case, the length of the signature sequences required for reliable activity detection in the multi-cell system can be made to be independent of the number of cells through cooperation, in contrast to the case where the large-scale fadings are not known. Further, this paper considers the case in which the fronthaul links between the BSs and the CU have capacity constraints and proposes a novel cooperation scheme based on the quantization of preliminary detection results at the BSs and the reconstruction of the sample covariance matrices at the CU. Simulations show that the proposed method significantly outperforms the scheme of directly quantizing the sample covariance matrices. [ABSTRACT FROM AUTHOR]

While early AutoML frameworks focused on optimizing traditional ML pipelines and their hyperparameters, a recent trend in AutoML is to focus on neural architecture search. In this paper, we introduce Auto-PyTorch, which brings together the best of these two worlds by jointly and robustly optimizing the network architecture and the training hyperparameters to enable fully automated deep learning (AutoDL). Auto-PyTorch achieves state-of-the-art performance on several tabular benchmarks by combining multi-fidelity optimization with portfolio construction for warmstarting and ensembling of deep neural networks (DNNs) and common baselines for tabular data. To thoroughly study our assumptions on how to design such an AutoDL system, we additionally introduce a new benchmark on learning curves for DNNs, dubbed LCBench, and run extensive ablation studies of the full Auto-PyTorch on typical AutoML benchmarks, eventually showing that Auto-PyTorch performs better than several state-of-the-art competitors. [ABSTRACT FROM AUTHOR]

Differentiable architecture search (DARTS) enables effective neural architecture search (NAS) using gradient descent, but suffers from high memory and computational costs. In this paper, we propose a novel approach, namely Partially-Connected DARTS (PC-DARTS), to achieve efficient and stable neural architecture search by reducing the channel and spatial redundancies of the super-network. In the channel level, partial channel connection is presented to randomly sample a small subset of channels for operation selection to accelerate the search process and suppress the over-fitting of the super-network. Side operation is introduced for bypassing (non-sampled) channels to guarantee the performance of searched architectures under extremely low sampling rates. In the spatial level, input features are down-sampled to eliminate spatial redundancy and enhance the efficiency of the mixed computation for operation selection. Furthermore, edge normalization is developed to maintain the consistency of edge selection based on channel sampling with the architectural parameters for edges. Theoretical analysis shows that partial channel connection and parameterized side operation are equivalent to regularizing the super-network on the weights and architectural parameters during bilevel optimization. Experimental results demonstrate that the proposed approach achieves higher search speed and training stability than DARTS. PC-DARTS obtains a top-1 error rate of 2.55 percent on CIFAR-10 with 0.07 GPU-days for architecture search, and a state-of-the-art top-1 error rate of 24.1 percent on ImageNet (under the mobile setting) within 2.8 GPU-days. [ABSTRACT FROM AUTHOR]

While the vehicular network enables geographically distributed cooperative computation, its mature implementation has long been constrained due to the lack of an effective management platform. In this paper, employing the security and privacy attributes of blockchain, we propose a novel Blockchain-enabled Large-scale Parked Vehicular Computing (BLPVC) architecture to utilize the potential solar energy and vehicular computational resources in the outdoor parking lot. However, the uneven green power supply and random arrival time of electric vehicles compose the highly complex environment. Accordingly, in this paper, to handle the efficient utilization of the distributed resources by blockchain technology, we propose an integrated optimization framework which leverages the green energy utilization and service latency limit among the processes of block generation, task computing, and communication, whereas such a design leads to the mixed-timescale stochastic optimization problem. To this end, corresponding to the dynamic solar energy arrival, we propose a shaped deep deterministic policy gradient (DDPG) algorithm to accelerate the learning rate of computational frequency control in the short-term stage; while in the long-term stage, for the mixed-integer programming (MIP) of task offloading and blockchain parameters adjustment, a series of transformation is employed to preserve convexity. Finally, experiments are carried out on Python demonstrating that the proposed scheme achieves a balanced performance between service latency and distributed resources, while the battery depreciation cost is heavily reduced. [ABSTRACT FROM AUTHOR]

Driven by the outstanding performance of neural networks in the structured euclidean domain, recent years have seen a surge of interest in developing neural networks for graphs and data supported on graphs. The graph is leveraged at each layer of the neural network as a parameterization to capture detail at the node level with a reduced number of parameters and computational complexity. Following this rationale, this paper puts forth a general framework that unifies state-of-the-art graph neural networks (GNNs) through the concept of EdgeNet. An EdgeNet is a GNN architecture that allows different nodes to use different parameters to weigh the information of different neighbors. By extrapolating this strategy to more iterations between neighboring nodes, the EdgeNet learns edge- and neighbor-dependent weights to capture local detail. This is a general linear and local operation that a node can perform and encompasses under one formulation all existing graph convolutional neural networks (GCNNs) as well as graph attention networks (GATs). In writing different GNN architectures with a common language, EdgeNets highlight specific architecture advantages and limitations, while providing guidelines to improve their capacity without compromising their local implementation. For instance, we show that GCNNs have a parameter sharing structure that induces permutation equivariance. This can be an advantage or a limitation, depending on the application. In cases where it is a limitation, we propose hybrid approaches and provide insights to develop several other solutions that promote parameter sharing without enforcing permutation equivariance. Another interesting conclusion is the unification of GCNNs and GATs —approaches that have been so far perceived as separate. In particular, we show that GATs are GCNNs on a graph that is learned from the features. This particularization opens the doors to develop alternative attention mechanisms for improving discriminatory power. [ABSTRACT FROM AUTHOR]

Weight sharing promises to make neural architecture search (NAS) tractable even on commodity hardware. Existing methods in this space rely on a diverse set of heuristics to design and train the shared-weight backbone network, a.k.a. the super-net. Since heuristics substantially vary across different methods and have not been carefully studied, it is unclear to which extent they impact super-net training and hence the weight-sharing NAS algorithms. In this paper, we disentangle super-net training from the search algorithm, isolate 14 frequently-used training heuristics, and evaluate them over three benchmark search spaces. Our analysis uncovers that several commonly-used heuristics negatively impact the correlation between super-net and stand-alone performance, whereas simple, but often overlooked factors, such as proper hyper-parameter settings, are key to achieve strong performance. Equipped with this knowledge, we show that simple random search achieves competitive performance to complex state-of-the-art NAS algorithms when the super-net is properly trained. [ABSTRACT FROM AUTHOR]

Modern methods for counting people in crowded scenes rely on deep networks to estimate people densities in individual images. As such, only very few take advantage of temporal consistency in video sequences, and those that do only impose weak smoothness constraints across consecutive frames. In this paper, we advocate estimating people flows across image locations between consecutive images and inferring the people densities from these flows instead of directly regressing them. This enables us to impose much stronger constraints encoding the conservation of the number of people. As a result, it significantly boosts performance without requiring a more complex architecture. Furthermore, it allows us to exploit the correlation between people flow and optical flow to further improve the results. We also show that leveraging people conservation constraints in both a spatial and temporal manner makes it possible to train a deep crowd counting model in an active learning setting with much fewer annotations. This significantly reduces the annotation cost while still leading to similar performance to the full supervision case. [ABSTRACT FROM AUTHOR]

In prior parts of this series, I analyzed the 1) number of all issued patents and issued computer architecture patents; 2) the prosecution time and effective patent term; 3) the number of claims, breakdown of independent and dependent claims, and effect that excess claim fees had on the numbers of total and independent claims; and 4) the type of claims (apparatus, method, or Beauregard), and effect that the Supreme Court's decision in Alice v. CLS Bank had on the number of independent and dependent method claims, for patents that were issued to 18 leading computer architecture companies and filed between 1996 and 2020. This article examines the 1) number of "backward" citations to previously issued/published U.S. patents and U.S. patent publications, foreign patents, and Other References and 2) the number of "forward" citations to a company's patent by another U.S. patent or U.S. patent publication. [ABSTRACT FROM AUTHOR]

Millimeter wave (mmWave) frequency spectrum offers orders of magnitude greater spectrum to mitigate the severe spectrum shortage in conventional cellular bands. To overcome the high propagation loss in the mmWave band, massive multiple-input and multiple-output (MIMO) can be adopted at both transmitter and receiver to provide large beamforming gains. At the same time, hybrid architecture is applied to reduce the huge power consumption caused by devices operating at radio frequency (RF). However, because of the hybrid architecture and large number of antennas, it is hard to obtain the channel state information (CSI) which is crucial for obtaining desirable beamforming gains. Off-grid error and sparsity pattern (SP) estimation error are two main limiting factors of the performance of most existing compressive sensing (CS) based channel estimation (CE) algorithms. Off-grid error presents when the true angle does not lie on the discretized angle grid of mmWave channel in the spatial domain. In this paper, we first propose a fast Bayesian matching pursuit method with ‘virtual sparsity’ to improve the accuracy of SP estimation and name it as the improved Bayesian matching pursuit (IBMP). Then an enhanced algorithm, named off-grid IBMP (OG-IBMP), is developed to mitigate the off-grid problem, followed by a theoretical analysis of OG-IBMP. This method iteratively updates the selected grid points and updates the corresponding parameters based on the maximum a posteriori (MAP) criterion. Numerical simulations are performed to validate our theoretical analysis and evaluate the performance of the proposed method. Compared to other existing methods, the results show that our proposed OG-IBMP algorithm greatly reduces the off-grid error and significantly enhances the accuracy of the SP estimation with low computational complexity. [ABSTRACT FROM AUTHOR]

The cell-free massive multiple-input multiple-output (CFmMIMO) aims to provide uniform quality of service (QoS) for all users, and can be used in small-area scenarios such as indoor industrial networks. This paper studies the CFmMIMO system for indoor industrial scenarios. Firstly, an access point (AP) grouping based hierarchical network topology is proposed. Based on this, we propose an effective AP selection method. To reduce pilot contamination, a pilot assignment scheme based on inspection robot (IR) location is proposed. Considering the high reliability requirement of industrial data transmission, the power control and backhaul combining are jointly optimized to maximize the minimum signal to interference plus noise ratio (SINR). The scalability of the proposed CFmMIMO system is analyzed, and a scalable power control method is proposed. The simulations demonstrate the effectiveness of the AP selection method, pilot assignment scheme, and the joint optimization algorithm for power control and backhaul combining. Moreover, the impact of network scale and network load on system performance is evaluated and analyzed in the simulations. [ABSTRACT FROM AUTHOR]

The separation of the data capture and analysis in modern vision systems has led to a massive amount of data transfer between the end devices and cloud computers, resulting in long latency, slow response, and high power consumption. Efficient hardware architectures are under focused development to enable Artificial Intelligence (AI) at the resource-limited sensing devices. One of the most promising solutions is to enable Processing-in-Pixel (PIP) scheme. However, the conventional schemes suffer from the low fill-factor issue. This paper proposes a PIP based Complementary Metal-Oxide-Semiconductor (CMOS) sensor architecture, which allows convolution operation before the column readout circuit to significantly reduce the overall power consumption while improving the resource utilization of the succeeding deep learning accelerator. The simulation results show that the proposed architecture could support the computing efficiency up to 3.37 TOPS/W at the 8-bit weight configuration, which is four times as high as the conventional schemes after normalization. The transistors required for each pixel are only 3.5T, significantly improving the fill-factor. [ABSTRACT FROM AUTHOR]

This paper presents hardware-friendly algorithm for Gini-index (GI) cooperative-spectrum-sensing (CSS) algorithm for the data-fusion based cooperative cognitive-radio network. It simplifies the complex computations of sample-covariance-matrix (SCM) elements and test-statistics value of the conventional GI-based CSS algorithm. It delivers excellent detection performance under the realistic scenario of non-uniform dynamical noise and signal-power. Based on GI-based CSS algorithm, three different VLSI architectures are proposed for the cooperative spectrum sensor (CSR): CSR-VLAR1, CSR-VLAR2, and CSR-VLAR3. Here, CSR-VLAR1 is the first-time reported CSR-architecture for the conventional GI-based CSS algorithm. Subsequently, CSR-VLAR2 represents hardware-architecture of the proposed hardware-friendly GI-based CSS algorithm. Eventually, additional architectural optimization has been applied to CSR-VLAR2 that is transformed into the most hardware-efficient VLSI-architecture of CSR, referred as CSR-VLAR3, which is ASIC chip-fabricated in UMC 130 nm-CMOS technology node. Furthermore, both CSR-VLAR1 and CSR-VLAR2 are synthesized and post-layout simulated in the same technology node. Our ASIC-chip of CSR-VLAR3 occupies 0.35 mm2 of core-area and consumes 8.31 mW of total power at 88.8 MHz of maximum clock frequency, when the supply voltage is 1.2 V. Our CSR ASIC-chip has been functionally verified with the aid of real-world signals, using USRPs and FPGAs based test-setup of cooperative cognitive-radio network. Measured results of our design are compared with reported implementations where the proposed CSR is $4.52\times $ hardware-efficient and $2.8\times $ power-efficient than the state-of-the-art CSR-implementations. Thus, our work addresses the key challenge of designing hardware-efficient CSR that delivers excellent detection performance in the real-world scenario. [ABSTRACT FROM AUTHOR]

This paper explores criticality-based real-time scheduling of neural-network-based machine inference pipelines in cyber-physical systems (CPS) to mitigate the effect of algorithmic priority inversion. We specifically focus on the perception subsystem, an important subsystem feeding other components (e.g., planning and control). In general, priority inversion occurs in real-time systems when computations that are of lower priority are performed together with or ahead of those that are of higher priority. In current machine perception software, significant priority inversion occurs because resource allocation to the underlying neural network models does not differentiate between critical and less critical data within a scene. To remedy this problem, in recent work, we proposed an architecture to partition the input data into regions of different criticality, then formulated a utility-based optimization problem to batch and schedule their processing in a manner that maximizes confidence in perception results, subject to criticality-based time constraints. This journal extension matures the work in several directions: (i) We extend confidence maximization to a generalized utility optimization formulation that accounts for criticality in the utility function itself, offering finer-grained control over resource allocation within the perception pipeline; (ii) we further instantiate and compare two different criticality metrics (distance-based and relative velocity-based) to understand their relative advantages; and (iii) we explore the limitations of the approach, specifically how inaccuracies in criticality-based attention cueing affect performance. All experiments are conducted on the NVIDIA Jetson AGX Xavier platform with a real-world driving dataset. [ABSTRACT FROM AUTHOR]

Modern top-performing object detectors depend heavily on backbone networks, whose advances bring consistent performance gains through exploring more effective network structures. In this paper, we propose a novel and flexible backbone framework, namely CBNet, to construct high-performance detectors using existing open-source pre-trained backbones under the pre-training fine-tuning paradigm. In particular, CBNet architecture groups multiple identical backbones, which are connected through composite connections. Specifically, it integrates the high- and low-level features of multiple identical backbone networks and gradually expands the receptive field to more effectively perform object detection. We also propose a better training strategy with auxiliary supervision for CBNet-based detectors. CBNet has strong generalization capabilities for different backbones and head designs of the detector architecture. Without additional pre-training of the composite backbone, CBNet can be adapted to various backbones (i.e., CNN-based vs. Transformer-based) and head designs of most mainstream detectors (i.e., one-stage vs. two-stage, anchor-based vs. anchor-free-based). Experiments provide strong evidence that, compared with simply increasing the depth and width of the network, CBNet introduces a more efficient, effective, and resource-friendly way to build high-performance backbone networks. Particularly, our CB-Swin-L achieves 59.4% box AP and 51.6% mask AP on COCO test-dev under the single-model and single-scale testing protocol, which are significantly better than the state-of-the-art results (i.e., 57.7% box AP and 50.2% mask AP) achieved by Swin-L, while reducing the training time by $6\times $. With multi-scale testing, we push the current best single model result to a new record of 60.1% box AP and 52.3% mask AP without using extra training data. Code is available at https://github.com/VDIGPKU/CBNetV2 . [ABSTRACT FROM AUTHOR]

This article addresses polynomial computation with unipolar stochastic logic by exploiting correlation between the bit-streams. The AND-OR, double-NAND, OR-AND and double-NOR circuits are presented for polynomials with all positive coefficients whose sum is less than or equal to one by mathematically analyzing the joint probability distribution of coefficient bit-streams. The NAND-AND expansion is also developed for polynomials with alternatively positive and negative coefficients whose absolute values are decreasing by applying the same idea. Unlike the original methods with multiple uncorrelated random number sources (RNSs) for coefficient bit-stream generation, the presented methods only require a single RNS. Since the RNSs take up huge hardware resource in stochastic circuits, the proposed RNS-sharing techniques for polynomial computation result in a significant reduction of hardware complexity. For the factorization technique in the general polynomials, this paper enhances the original stochastic designs for the second-order polynomial and further presents the simple correlation-dependent circuits. Results show that the proposed architectures are superior to the previous ones by reducing the total number of RNSs. [ABSTRACT FROM AUTHOR]

With the development of 6G wireless communication technologies, various resource-intensive and delay-sensitive vehicle application tasks are generated. These application tasks can be offloaded to Mobile Edge Computing (MEC) which deploys computing resources at the edge of networks. Besides, the recent proposed Cybertwin, as the digital representation of the complicated physical end-systems, can help the terminals obtain the required services from networks. Vehicles enabled by Cybertwin can offload their tasks to MEC and achieve better performance. In this paper, we focus on the study of a hybrid energy-powered multi-server MEC system with Cybertwin. Vehicles enabled by Cybertwin and edge servers send the current network status and unprocessed vehicle application tasks to the macro base station (MBS) to achieve the better allocation of resources. Energy harvesting (EH) devices are deployed on edge servers to form a “green energy-grid” hybrid energy supply model. We formulate a stochastic offloading optimization problem, and the goal is to minimize the system cost. The stochastic optimization problem is decomposed into three sub-problems. Then, we design an efficient multi-vehicle task offloading (EMT) algorithm to achieve the trade-off between system cost and task queue length. Theoretical analysis shows that EMT algorithm can optimize the total cost of the MEC system and guarantee the system performance. According to experimental evaluation, we verify the performance of the EMT algorithm. [ABSTRACT FROM AUTHOR]

Pedestrian detection is an important issue in an intelligent transportation system and involves complex hardware architecture. This high complexity and low detection accuracy make it a prompt topic of research. This paper proposes a novel feature extractor with its efficient hardware implementation for the real-time pedestrian detection system. The proposed approach termed here as Histogram of All Significant Gradients (HASG) improves the Histogram of Significant Gradients (HSG) technique by the inclusion of diagonal gradients. The diagonal gradients give an add-on feature which improves the detection accuracy of the detection system. The overhead of extra computation is compensated here by the proposition of a hardware architecture that utilizes only integer computation. The arctangent operation which is a floating-point operation is replaced here by a simplified architecture that uses only integer computation units. The proposed hardware architecture is found to have 73.65% reduced hardware consumption in contrast to the existing one. The complete design is implemented on the Artix-7 FPGA device with a maximum achievable clock frequency of 115 MHz. [ABSTRACT FROM AUTHOR]

Using deep neural networks (DNNs) to explore spatial patterns and temporal dynamics of human brain activities has been an important yet challenging problem because the artificial neural networks are hard to be designed manually. There have been several promising deep learning methods, e.g., deep belief network (DBN), convolutional neural network (CNN), and deep sparse recurrent auto-encoder (DSRAE), that can decompose neuroscientific and meaningful spatiotemporal patterns from 4D functional Magnetic Resonance Imaging (fMRI) data. However, those previous studies still depend on hand-crafted neural network architectures and hyperparameters, which are not optimal in various senses. In this paper, we employ the evolutionary algorithms (EA) to optimize the deep neural architecture of DSRAE by minimizing the expected loss of initialized models, named eNAS-DSRAE (evolutionary Neural Architecture Search on Deep Sparse Recurrent Auto-Encoder). Also, validation experiments are designed and performed on the publicly available human connectome project (HCP) 900 datasets, and the results achieved by the optimized eNAS-DSRAE suggested that our framework can successfully identify the spatiotemporal features and perform better than the hand-crafted neural network models. To our best knowledge, the proposed eNAS-DSRAE is not only among the earliest NAS models that can extract connectome-scale meaningful spatiotemporal brain networks from 4D fMRI data, but also is an effective framework to optimize the RNN-based models. [ABSTRACT FROM AUTHOR]

3D object recognition is a hot research topic. Particularly, view-based methods, which represent a 3D object with a collection of its rendered views on the 2D domain, play an important role in this field. Currently, view-based researches tend to aggregate information from multiple views via pooling based strategies to endow the models with the characteristic of view permutation invariance, at the cost of inevitable loss of useful features. In this paper, we introduce a new method that learns a more comprehensive descriptor for a 3D object from its views while successfully keeping its robustness to the variation of view permutation. Our method disentangles the information in the set of multi-view images into a global category-related feature and a set of view-permutation related features. To unbind these two parts, an encode-decoder based disentangling architecture is proposed, which barely bring extra computations compared to the baseline model. Systematic experiments are conducted for this new method to demonstrates the effectiveness and the competitive performance based on ModelNet40, ModelNet10, and ShapeNetCore55 datasets. Codes for our paper will be released soon on “ https://github.com/hjjpku/multi%5fview%5fsort ”. [ABSTRACT FROM AUTHOR]

In this paper, we propose a geometric neural network with edge-aware refinement (GeoNet++) to jointly predict both depth and surface normal maps from a single image. Building on top of two-stream CNNs, GeoNet++ captures the geometric relationships between depth and surface normals with the proposed depth-to-normal and normal-to-depth modules. In particular, the “depth-to-normal” module exploits the least square solution of estimating surface normals from depth to improve their quality, while the “normal-to-depth” module refines the depth map based on the constraints on surface normals through kernel regression. Boundary information is exploited via an edge-aware refinement module. GeoNet++ effectively predicts depth and surface normals with high 3D consistency and sharp boundaries resulting in better reconstructed 3D scenes. Note that GeoNet++ is generic and can be used in other depth/normal prediction frameworks to improve 3D reconstruction quality and pixel-wise accuracy of depth and surface normals. Furthermore, we propose a new 3D geometric metric (3DGM) for evaluating depth prediction in 3D. In contrast to current metrics that focus on evaluating pixel-wise error/accuracy, 3DGM measures whether the predicted depth can reconstruct high quality 3D surface normals. This is a more natural metric for many 3D application domains. Our experiments on NYUD-V2 and KITTI datasets verify that GeoNet++ produces fine boundary details and the predicted depth can be used to reconstruct high quality 3D surfaces. [ABSTRACT FROM AUTHOR]

Geometric deep learning is a relatively nascent field that has attracted significant attention in the past few years. This is partly due to the availability of data acquired from non-euclidean domains or features extracted from euclidean-space data that reside on smooth manifolds. For instance, pose data commonly encountered in computer vision reside in Lie groups, while covariance matrices that are ubiquitous in many fields and diffusion tensors encountered in medical imaging domain reside on the manifold of symmetric positive definite matrices. Much of this data is naturally represented as a grid of manifold-valued data. In this paper we present a novel theoretical framework for developing deep neural networks to cope with these grids of manifold-valued data inputs. We also present a novel architecture to realize this theory and call it the ManifoldNet. Analogous to vector spaces where convolutions are equivalent to computing weighted sums, manifold-valued data ‘convolutions’ can be defined using the weighted Fréchet Mean (${\sf wFM}$ wFM ). (This requires endowing the manifold with a Riemannian structure if it did not already come with one.) The hidden layers of ManifoldNet compute ${\sf wFM}$ wFM s of their inputs, where the weights are to be learnt. This means the data remain manifold-valued as they propagate through the hidden layers. To reduce computational complexity, we present a provably convergent recursive algorithm for computing the ${\sf wFM}$ wFM . Further, we prove that on non-constant sectional curvature manifolds, each ${\sf wFM}$ wFM layer is a contraction mapping and provide constructive evidence for its non-collapsibility when stacked in layers. This captures the two fundamental properties of deep network layers. Analogous to the equivariance of convolution in euclidean space to translations, we prove that the ${\sf wFM}$ wFM is equivariant to the action of the group of isometries admitted by the Riemannian manifold on which the data reside. To showcase the performance of ManifoldNet, we present several experiments using both computer vision and medical imaging data sets. [ABSTRACT FROM AUTHOR]

Semiconductor manufacturing is on the cusp of a revolution – the Internet of Things (IoT). With IoT we can connect all the equipment and feed information back to the factory so that quality issues can be detected. In this situation, more and more edge devices are used in wafer inspection equipment. This edge device must have the ability to quickly detect defects. Therefore, how to develop a high-efficiency architecture for automatic defect classification to be suitable for edge devices is the primary task. In this paper, we present a novel architecture that can perform defect classification in a more efficient way. The first function is self-proliferation, using a series of linear transformations to generate more feature maps at a cheaper cost. The second function is self-attention, capturing the long-range dependencies of feature map by the channel-wise and spatial-wise attention mechanism. We named this method as self-proliferation-and-attention neural network (SP&A-Net). This method has been successfully applied to various defect pattern classification tasks. Compared with other latest methods, SP&A-Net has higher accuracy and lower computation cost in many defect inspection tasks. [ABSTRACT FROM AUTHOR]