In this paper, we present OpenMedIA, an open-source toolbox library containing a rich set of deep learning methods for medical image analysis under heterogeneous Artificial Intelligence (AI) computing platforms. Vario...
详细信息
Document-level event extraction task has achieved significant progress based on template generation methods. However, there is no reasonable regulation and restriction in the existing template-based generation methods...
Document-level event extraction task has achieved significant progress based on template generation methods. However, there is no reasonable regulation and restriction in the existing template-based generation methods, which results in the uncontrollability of the generation results. In some scenarios, model generates entities that do not belong to the input text, or generate template content repeatedly. It is determined by the nature of the extraction task and the generation task. To this end, we propose a controllable template generation event extraction model. According to the characteristics of template generation and event extraction tasks, the model devises copy mechanism, inhibition mechanism and rejection mechanism under the appropriately constructed template. Our model achieves state-of-the-art result on MUC-4 dataset, and finally through experimental analysis, it demonstrates the effectiveness of each mechanism we proposed.
How to preserve causal and totally ordered event delivery is an important issue in real-time serverless DVE(distributed Virtual Environment). However, most of the related works are designed to maintain causal order me...
详细信息
How to preserve causal and totally ordered event delivery is an important issue in real-time serverless DVE(distributed Virtual Environment). However, most of the related works are designed to maintain causal order merely or time stamped order with intensive computation and bandwidth overhead. In this paper, we proposed a novel distributed algorithm to maintain the before-and-after relationship between events, both causal and concurrent, of DVE at each individual node. Several simulation experiments are carried out to evaluate the performance of our algorithm and the results demonstrate that the algorithm is effective in preserving causal and totally ordered event delivery and more efficient than the previous algorithms.
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.
Due to the large message transmission latency in distributed Virtual Environments(DVEs) on Wide Area Net-work(WAN), the effectiveness of causality consistency control of message ordering is determined by not only caus...
详细信息
Due to the large message transmission latency in distributed Virtual Environments(DVEs) on Wide Area Net-work(WAN), the effectiveness of causality consistency control of message ordering is determined by not only causal order of messages but also the real-timeness. If merely causal order is considered, the real-time property of DVEs may not be ensured because of the unlimited waiting time for the delayed messages. While if only real-timeness is emphasized, there may be too many delayed messages, which have to be discarded, to maintain the quality of causal message ordering. Therefore, a trade-off between the quality of causal order delivery and real-timeness is necessary for DVEs. In this article, a novel causality based message ordering approach is presented. In general, this new approach dynamically balances the demands of causal order delivery and real-timeness. Experiment results demonstrate the approach can enhance the quality of causality, while simultaneously keep the real-time property of DVEs.
This paper presents reuse-aware modulo scheduling to maximizing stream reuse and improving concurrency for stream-level loops running on stream processors. The novelty lies in the development of a new representation f...
详细信息
ISBN:
(纸本)9783981080162
This paper presents reuse-aware modulo scheduling to maximizing stream reuse and improving concurrency for stream-level loops running on stream processors. The novelty lies in the development of a new representation for an unrolled and software-pipelined stream-level loop using a set of reuse equations, resulting in simultaneous optimization of two performance objectives for the loop, reuse and concurrency, in a unified framework. We have implemented this work in the compiler developed for our 64-bit FT64 stream processor. Our experimental results obtained on FT64 and by simulation using nine representative stream applications demonstrate the effectiveness of the proposed approach.
In order to resolve the problem of skew phenomenon in the handwritten document image during the scanning process, a new skew angle detection algorithm based on maximum gradient difference as well as Hough transform wa...
详细信息
Convolutional Neural Networks (CNNs), one of the most representative algorithms of deep learning, are widely used in various artificial intelligence applications. Convolution operations often take most of the computat...
详细信息
Extraordinary large datasets of high performance computing applications require improvement in existing storage and retrieval mechanisms. Moreover, enlargement of the gap between data processing and I/O operations'...
详细信息
ISBN:
(纸本)9781479915194
Extraordinary large datasets of high performance computing applications require improvement in existing storage and retrieval mechanisms. Moreover, enlargement of the gap between data processing and I/O operations' throughput will bound the system performance to storage and retrieval operations and remarkably reduce the overall performance of high performance computing clusters. File replication is a way to improve the performance of I/O operations and increase network utilization by storing several copies of every file. Furthermore, this will lead to a more reliable and fault-tolerant storage cluster. In order to improve the response time of I/O operations, we have proposed a mechanism that estimates the required number of replicas for each file based on its popularity. Besides that, the remaining space of storage cluster is considered in the evaluation of replication factors and the number of replicas is adapted to the storage state. We have implemented the proposed mechanism using HDFS and evaluated it using MapReduce framework. Evaluation results prove its capability to improve the response time of read operations and increase network utilization. Consequently, this mechanism reduces the overall response time of read operations by considering files' popularity in replication process and adapts the replication factor to the cluster state.
Beyond classical domain-specific adversarial training, a recently proposed task-specific framework has achieved a great success in single source domain adaptation by utilizing task-specific decision boundaries. Howeve...
Beyond classical domain-specific adversarial training, a recently proposed task-specific framework has achieved a great success in single source domain adaptation by utilizing task-specific decision boundaries. However, compared to single-source-single-target setting, multi-source domain adaptation (MDA) shows more powerful capability to handle with most real-life cases. To align target domain with diverse multi-source domains using task-specific decision boundaries, we provide a deep insight of task-specific framework on MDA for the first time. Accordingly, we propose a novel task-specific multi-source domain adaptation method (TMDA) with a clustering embedded adversarial training process. Specifically, the proposed TMDA detects and refines less discriminative target representations through a max-min optimization over two adversarial task-specific classifiers. Moreover, our analysis implies that scattered multi-source representations disturb the adversarial training under the task-specific framework. To tight up the dispersed source representations, we embeds a relationship-based domain clustering into TMDA. Empirical results demonstrate that our TMDA outperforms state-of-the-art methods on toy dataset, sentiment analysis and digit classification.
暂无评论