Large-scale floating-point matrix multiplication is a fundamental kernel in many scientific and engineering applications. Most existing work only focus on accelerating matrix multiplication on FPGA by adopting a linea...
详细信息
Deep clustering aims to cluster unlabeled data by embedding them into a subspace based on deep model. The key challenge of deep clustering is to learn discriminative representations for input data with high dimensions...
详细信息
Deep clustering aims to cluster unlabeled data by embedding them into a subspace based on deep model. The key challenge of deep clustering is to learn discriminative representations for input data with high dimensions. In this paper, we present a deep discriminative clustering network for clustering the real-world images. We use a convolutional auto-encoder stacked with a softmax layer to predict clustering assignments. To learn a discriminative representations, the proposed approach adds discriminative loss as embedded regularization with relative entropy minimization. With the discriminative loss, the network can not only produce clustering assignments, but also learn discriminative features by reducing intra-cluster distance and increasing inter-cluster distance. We evaluate the proposed method on three datasets: MNIST-full, YTF and FRGC-v2.0. We outperform state-of-the-art results on MNIST-full and FRGC-v2.0 and achieve competitive result on YTF. The source code has been made publicly available at .
We present Fast-Downsampling MobileNet (FD-MobileNet), an efficient and accurate network for very limited computational budgets (e.g., 10-140 MFLOPs). Our key idea is applying a fast down-sampling strategy to MobileNe...
详细信息
We present Fast-Downsampling MobileNet (FD-MobileNet), an efficient and accurate network for very limited computational budgets (e.g., 10-140 MFLOPs). Our key idea is applying a fast down-sampling strategy to MobileNet framework. In FD-MobileNet, we perform 32× downsampling within 12 layers, only half the layers in the original MobileNet. This design brings three advantages: (i) It remarkably reduces the computational cost. (ii) It increases the information capacity and achieves significant performance improvements. (iii) It is engineering-friendly and provides fast actual inference speed. Experiments on ILSVRC 2012 and PASCAL VOC datasets demonstrate that FD-MobileNet consistently outperforms MobileNet and achieves comparable results with ShuffleNet under different computational budgets, for instance, surpassing Mobile-Net by 5.5% on the ILSVRC 2012 top-1 accuracy and 8.3% on the VOC 2007 mAP under a complexity of 12 MFLOPs. On an ARM-based device, FD-MobileNet achieves 1.11× inference speedup over MobileNet and 1.82× over ShuffleNet under the same complexity.
To provide timely results for big data analytics, it is crucial to satisfy deadline requirements for MapReduce jobs in today's production environments. Much effort has been devoted to the problem of meeting deadlines...
详细信息
To provide timely results for big data analytics, it is crucial to satisfy deadline requirements for MapReduce jobs in today's production environments. Much effort has been devoted to the problem of meeting deadlines, and typically there exist two kinds of solutions. The first is to allocate appropriate resources to complete the entire job before the specified time limit, where missed deadlines result because of tight deadline constraints or lack of resources; the second is to run a pre-constructed sample based on deadline constraints, which can satisfy the time requirement but fail to maximize the volumes of processed data. In this paper, we propose a deadline-oriented task scheduling approach, named 'Dart', to address the above problem. Given a specified deadline and restricted resources, Dart uses an iterative estimation method, which is based on both historical data and job running status to precisely estimate the real-time job completion time. Based on the estimated time, Dart uses an approach-revise algorithm to make dynamic scheduling decisions for meeting deadlines while maximizing the amount of processed data and mitigating stragglers. Dart also efficiently handles task failures and data skew, protecting its performance from being harmed. We have validated our approach using workloads from OpenCloud and Facebook on a cluster of 64 virtual machines. The results show that Dart can not only effectively meet the deadline but also process near-maximum volumes of data even with tight deadlines and limited resources.
In this paper,we propose an indoor robot autonomous navigation *** robot firstly explores in an unknown environment,and then navigates autonomously by using the explored *** robot is equipped a 2 D laser scanner as th...
详细信息
In this paper,we propose an indoor robot autonomous navigation *** robot firstly explores in an unknown environment,and then navigates autonomously by using the explored *** robot is equipped a 2 D laser scanner as the main *** laser scanner is used for path planning and frontier-based exploration.A 2 D global occupancy map is built for path planning,frontier-based exploration and multi-objective autonomous *** scans are transmitted into Simultaneous Localization and Mapping(SLAM) process in the exploration *** indoor environment,the exploration efficiency is improved by merging a heuristic *** using multi-threading technology and a 3 D perception approach proposed in this paper,the robot equipped with a low-cost RGBD sensor can detect all kinds of obstacles to achieve highly reliable navigation in complicated 3 D ***,we develop a multi-objective navigation application to make human-robot interaction more convenient and satisfy multi-task *** approaches are demonstrated by experimental results.
Image restoration problems are typical ill-posed problems where the regularization term plays an important role. The regularization term learned via generative approaches is easy to transfer to various image restorati...
详细信息
As the number of publicly available services grows, discovering proper services becomes an important issue and has attracted amount of attempts. This paper presents a new customizable and effective matchmaker, called ...
详细信息
Acoustic scene classification is an intricate problem for a machine. As an emerging field of research, deep Convolutional Neural Networks (CNN) achieve convincing results. In this paper, we explore the use of multi-sc...
详细信息
Internet-based virtual computing environment (iVCE) has been proposed to combine data centers and other kinds of computing resources on the Internet to provide efficient and economical services. Virtual machines (...
详细信息
Internet-based virtual computing environment (iVCE) has been proposed to combine data centers and other kinds of computing resources on the Internet to provide efficient and economical services. Virtual machines (VMs) have been widely used in iVCE to isolate different users/jobs and ensure trustworthiness, but traditionally VMs require a long period of time for booting, which cannot meet the requirement of iVCE's large-scale and highly dynamic applications. To address this problem, in this paper we design and implement VirtMan, a fast booting system for a large number of virtual machines in iVCE. VirtMan uses the Linux Small Computer System Interface (SCSI) target to remotely mount to the source image in a scalable hierarchy, and leverages the homogeneity of a set of VMs to transfer only necessary image data at runtime. We have implemented VirtMan both as a standalone system and for OpenStack. In our 100-server testbed, VirtMan boots up 1000 VMs (with a 15 CB image of Windows Server 2008) on 100 physical servers in less than 120 s, which is three orders of magnitude lower than current public clouds.
暂无评论