Image clustering is one of the challenging tasks in machine learning, and has been extensively used in various applications. Recently, various deep clustering methods has been proposed. These methods take a two-stage ...
详细信息
Image clustering is one of the challenging tasks in machine learning, and has been extensively used in various applications. Recently, various deep clustering methods has been proposed. These methods take a two-stage approach, feature learning and clustering, sequentially or jointly. We observe that these works usually focus on the combination of reconstruction loss and clustering loss, relatively little work has focused on improving the learning representation of the neural network for clustering. In this paper, we propose a deep convolutional embedded clustering algorithm with inception-like block (DCECI). Specifically, an inception-like block with different type of convolution filters are introduced in the symmetric deep convolutional network to preserve the local structure of convolution layers. We simultaneously minimize the reconstruction loss of the convolutional autoencoders with inception-like block and the clustering loss. Experimental results on multiple image datasets exhibit the promising performance of our proposed algorithm compared with other competitive methods.
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.
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.
Infrastructure as a service clouds hide the complexity of maintaining the physical infrastructure with a slight disadvantage: they also hide their internal working details. Should users need knowledge about these deta...
详细信息
Valuable training data is often owned by independent organizations and located in multiple data centers. Most deep learning approaches require to centralize the multi-datacenter data for performance purpose. In practi...
详细信息
Hardware-based middleboxes are ubiquitous in computer networks, which usually incur high deployment and management expenses. A recently arsing trend aims to address those problems by outsourcing the functions of tradi...
详细信息
Indoor-Outdoor scene classification problem have been proposed for almost 20 years and widely applied to general scene classification, image retrieval, image processing and robot application. But there is no consensus...
详细信息
ISBN:
(纸本)9781510845541
Indoor-Outdoor scene classification problem have been proposed for almost 20 years and widely applied to general scene classification, image retrieval, image processing and robot application. But there is no consensus on one particular scene classification technique that can solve the Indoor-Outdoor scene classification problem perfectly. As larger image dataset has been developed and machine learning technology especially deep learning based methods achieve remarkable performance in computer vision, we aim to provide guidance and direction for researchers to tackle the Indoor-Outdoor scene classification problem with more powerful and robust solution through concluding the Indoor-Outdoor scene classification approaches which have been proposed in last 20 years. In this paper, we review the Indoor-Outdoor scene classification including feature extraction, classifier and related dataset. Their advantages and disadvantages are discussed. At last we conclude some challenging problems remain unsolved and propose some potential solutions.
New non-volatile memory （e.g., phase-change memory） provides fast access, large capacity, byteaddressability, and non-volatility features. These features, fast-byte-persistency, will bring new opportunities to fault...
详细信息
New non-volatile memory （e.g., phase-change memory） provides fast access, large capacity, byteaddressability, and non-volatility features. These features, fast-byte-persistency, will bring new opportunities to fault tolerance. We propose a fine-grained checkpoint based on non-volatile memory. We extend the current virtual memory manager to manage non-volatile memory, and design a persistent heap with support for fast allocation and checkpointing of persistent objects. To achieve a fine-grained checkpoint, we scatter objects across virtual pages and rely on hardware page-protection to monitor the modifications. In our system, two objects in different virtual pages may reside on the same physical page. Modifying one object would not interfere with the other object. This allows us to monitor and checkpoint objects smaller than 4096 bytes in a fine-grained way. Compared with previous page-grained based checkpoint mechanisms, our new checkpoint method can greatly reduce the data copied at checkpoint time and better leverage the limited bandwidth of non-volatile memory.
GEMM is the main computational kernel in BLAS3. Its micro-kernel is either hand-crafted in assembly code or generated from C code by general-purpose compilers (guided by architecture-specific directives or auto-tuning...
详细信息
ISBN:
(纸本)9781509049318
GEMM is the main computational kernel in BLAS3. Its micro-kernel is either hand-crafted in assembly code or generated from C code by general-purpose compilers (guided by architecture-specific directives or auto-tuning). Therefore, either performance or portability suffers. We present a POrtable Compiler Approach, Poca, implemented in LLVM, to automatically generate and optimize this micro-kernel in an architecture-independent manner, without involving domain experts. The key insight is to leverage a wide range of architecture-specific abstractions already available in LLVM, by first generating a vectorized micro-kernel in the architecture-independent LLVM IR and then improving its performance by applying a series of domain-specific yet architecture-independent optimizations. The optimized micro-kernel drops easily in existing GEMM frameworks such as BLIS and OpenBLAS. Validation focuses on optimizing GEMM in double precision on two architectures. On Intel Sandybridge and AArch64 Cortex-A57, Poca's micro-kernels outperform expert-crafted assembly code by 2.35% and 7.54%, respectively, and both BLIS and OpenBLAS achieve competitive or better performance once their micro-kernels are replaced by Poca's.
Image annotation generates a set of semantic labels that describe the contents of an input *** deep learning techniques have achieved significant success in many areas of image *** this paper,we present a multi-label ...
详细信息
Image annotation generates a set of semantic labels that describe the contents of an input *** deep learning techniques have achieved significant success in many areas of image *** this paper,we present a multi-label image annotation method that combines unsupervised object hypotheses generation and deep neural *** an image,object hypotheses are generated in an unsupervised *** we extract the image features for each hypothesis with a deep neural network *** combining the features of all hypotheses,we get the features of the entire ***,we calculate for each label the probability of that the label is correlated with the given *** can be trained in an end-to-end way using the standard backward propagation *** results on multiple benchmark datasets show that our method is better than the state-of-the-art ones.
暂无评论