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
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
Dangling pointer error is pervasive in C/C++ programs and it is very hard to detect. This paper introduces an efficient detector to detect dangling pointer error in C/C++ programs. By selectively leave some memory acc...
详细信息
Modern object detectors usually suffer from low accuracy issues, as foregrounds always drown in tons of backgrounds and become hard examples during training. Compared with those proposal-based ones, real-time detector...
详细信息
Modern object detectors usually suffer from low accuracy issues, as foregrounds always drown in tons of back-grounds and become hard examples during training. Compared with those proposal-based ones, real-time detecto...
详细信息
Modern object detectors usually suffer from low accuracy issues, as foregrounds always drown in tons of back-grounds and become hard examples during training. Compared with those proposal-based ones, real-time detectors are in far more serious trouble since they renounce the use of region-proposing stage which is used to filter a majority of back-grounds for achieving real-time rates. Though foregrounds as hard examples are in urgent need of being mined from tons of backgrounds, a considerable number of state-of-the-art real-time detectors, like YOLO series, have yet to profit from existing hard example mining methods, as using these methods need detectors fit series of prerequisites. In this paper, we propose a general hard example mining method named Loss Rank Mining (LRM) to fill the gap. LRM is a general method for real-time detectors, as it utilizes the final feature map which exists in all real-time detectors to mine hard examples. By using LRM, some elements representing easy examples in final feature map are filtered and detectors are forced to concentrate on hard examples during training. Extensive experiments validate the effectiveness of our method. With our method, the improvements of YOLOv2 detector on auto-driving related dataset KITTI and more general dataset PASCAL VOC are over 5% and 2% mAP, respectively. In addition, LRM is the first hard example mining strategy which could fit YOLOv2 perfectly and make it better applied in series of real scenarios where both real-time rates and accurate detection are strongly demanded.
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
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.
The pull-based development model, widely used in distributed software teams on open source communities, can efficiently gather the wisdom from crowds. Instead of sharing access to a central repository,contributors cre...
详细信息
The pull-based development model, widely used in distributed software teams on open source communities, can efficiently gather the wisdom from crowds. Instead of sharing access to a central repository,contributors create a fork, update it locally, and request to have their changes merged back, i.e., submit a pull-request. On the one hand, this model lowers the barrier to entry for potential contributors since anyone can submit pull-requests to any repository, but on the other hand it also increases the burden on integrators, who are responsible for assessing the proposed patches and integrating the suitable changes into the central repository. The role of integrators in pull-based development is crucial. They must not only ensure that pull-requests should meet the project’s quality standards before being accepted, but also finish the evaluations in a timely manner. To keep up with the volume of incoming pull-requests, continuous integration(CI) is widely adopted to automatically build and test every pull-request at the time of submission. CI provides extra evidences relating to the quality of pull-requests, which would help integrators to make final decision(i.e., accept or reject). In this paper, we present a quantitative study that tries to discover which factors affect the process of pull-based development model, including acceptance and latency in the context of CI. Using regression modeling on data extracted from a sample of Git Hub projects deploying the Travis-CI service, we find that the evaluation process is a complex issue, requiring many independent variables to explain adequately. In particular, CI is a dominant factor for the process, which not only has a great influence on the evaluation process per se, but also changes the effects of some traditional predictors.
The Internet based cyber-physical world has profoundly changed the information environment for the development of artificial intelligence(AI), bringing a new wave of AI research and promoting it into the new era of AI...
详细信息
The Internet based cyber-physical world has profoundly changed the information environment for the development of artificial intelligence(AI), bringing a new wave of AI research and promoting it into the new era of AI 2.0. As one of the most prominent characteristics of research in AI 2.0 era, crowd intelligence has attracted much attention from both industry and research communities. Specifically, crowd intelligence provides a novel problem-solving paradigm through gathering the intelligence of crowds to address challenges. In particular, due to the rapid development of the sharing economy, crowd intelligence not only becomes a new approach to solving scientific challenges, but has also been integrated into all kinds of application scenarios in daily life, e.g., online-tooffline(O2O) application, real-time traffic monitoring, and logistics management. In this paper, we survey existing studies of crowd intelligence. First, we describe the concept of crowd intelligence, and explain its relationship to the existing related concepts, e.g., crowdsourcing and human computation. Then, we introduce four categories of representative crowd intelligence platforms. We summarize three core research problems and the state-of-the-art techniques of crowd intelligence. Finally, we discuss promising future research directions of crowd intelligence.
暂无评论