检索结果-内蒙古大学图书馆

Proceedings of the 36th International Conference on Neural Information Processing Systems

作者： Liang Zhang Anwen Hu Qin Jin School of Information Renmin University of China School of Information Renmin University of China and Key Laboratory of Data Engineering and Knowledge Engineering (MOE) Renmin University of China

ISBN: (纸本)9781713871088

Vision and diverse languages are important information sources in our living world. A model that understands multi-modalities and multi-languages can be applied to a wider range of real-life scenarios. To build such a multimodal and multilingual model, existing works try to ensemble vision-language data from multiple languages in pre-training. However, due to the large number of languages, these works often require huge computing resources and cannot be flexibly extended to new languages. In this work, we propose a Multi-Lingual Acquisition (MLA) framework that can easily empower a monolingual Vision-Language Pre-training (VLP) model with multilingual capability. Specifically, we design a lightweight language acquisition encoder based on state-of-the-art monolingual VLP models. We further propose a two-stage training strategy to optimize the language acquisition encoder, namely the Native Language Transfer stage and the Language Exposure stage. With much less multilingual training data and computing resources, our model achieves state-of-the-art performance on multilingual image-text and video-text retrieval benchmarks.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Three-dimensional diabetic macular edema thickness maps based on fluid segmentation and fovea detection using deep learning

引用

International Journal of Ophthalmology(English edition) 2022年第3期15卷 495-501页

作者： Jing-Jing Xu Yang Zhou Qi-Jie Wei Kang Li Zhen-Ping Li Tian Yu Jian-Chun Zhao Da-Yong Ding Xi-Rong Li Guang-Zhi Wang Hong Dai School of Medicine Tsinghua UniversityBeijing 100084China Visionary Intelligence Company Limited Beijing 100872China Department of Ophthalmology Beijing HospitalNational Center of GerontologyInstitute of Geriatric MedicineChinese Academy of Medical ScienciesBeijing 100730China Key Lab of Data Engineering and Knowledge Engineering Renmin University of ChinaBeijing 100872China

AIM: To explore a more accurate quantifying diagnosis method of diabetic macular edema(DME) by displaying detailed 3D morphometry beyond the gold-standard quantification indicator-central retinal thickness(CRT) and apply it in follow-up of DME ***: Optical coherence tomography(OCT) scans of 229 eyes from 160 patients were *** manually annotated cystoid macular edema(CME), subretinal fluid(SRF) and fovea as ground *** convolution neural networks(DCNNs) were constructed including U-Net, sASPP, HRNetV2-W48, and HRNetV2-W48+Object-Contextual Representation(OCR) for fluid(CME+SRF) segmentation and fovea detection respectively, based on which the thickness maps of CME, SRF and retina were generated and divided by Early Treatment Diabetic Retinopathy Study(ETDRS) ***: In fluid segmentation, with the best DCNN constructed and loss function, the dice similarity coefficients(DSC) of segmentation reached 0.78(CME), 0.82(SRF), and 0.95(retina).In fovea detection, the average deviation between the predicted fovea and the ground truth reached 145.7±117.8 μ*** generated macular edema thickness maps are able to discover center-involved DME by intuitive morphometry and fluid volume, which is ignored by the traditional definition of CRT>250 μ*** maps could also help to discover fluid above or below the fovea center ignored or underestimated by a single OCT ***: Compared to the traditional unidimensional indicator-CRT, 3D macular edema thickness maps are able to display more intuitive morphometry and detailed statistics of DME, supporting more accurate diagnoses and follow-up of DME patients.

关键词： diabetic macular edema fluid segmentation fovea detection 3D macular edema thickness maps deep learning

来源：评论

学校读者我要写书评

暂无评论

Reverse Nearest Neighbor Heat Maps: A Tool for Influence Exploration

Reverse Nearest Neighbor Heat Maps: A Tool for Influence Exp...

引用

IEEE International Conference on data engineering

作者： Yu Sun Rui Zhang Andy Yuan Xue Jianzhong Qi Xiaoyong Du Department of Computing and Information Systems University of Melbourne Renmin University of China and Key Laboratory of Data Engineering and Knowledge Engineering MOE

ISBN: (纸本)9781509020218

We study the problem of constructing a reverse nearest neighbor (RNN) heat map by finding the RNN set of every point in a two-dimensional space. Based on the RNN set of a point, we obtain a quantitative influence (i.e., heat) for the point. The heat map provides a global view on the influence distribution in the space, and hence supports exploratory analyses in many applications such as marketing and resource management. To construct such a heat map, we first reduce it to a problem called Region Coloring (RC), which divides the space into disjoint regions within which all the points have the same RNN set. We then propose a novel algorithm named CREST that efficiently solves the RC problem by labeling each region with the heat value of its containing points. In CREST, we propose innovative techniques to avoid processing expensive RNN queries and greatly reduce the number of region labeling operations. We perform detailed analyses on the complexity of CREST and lower bounds of the RC problem, and prove that CREST is asymptotically optimal in the worst case. Extensive experiments with both real and synthetic data sets demonstrate that CREST outperforms alternative algorithms by several orders of magnitude.

关键词： Heating Radio frequency Indexes

来源：评论

学校读者我要写书评

暂无评论

Deep Text Classification Can be Fooled

arXiv

引用

arXiv 2017年

作者： Liang, Bin Li, Hongcheng Su, Miaoqiang Bian, Pan Li, Xirong Shi, Wenchang School of Information Renmin University of China Beijing China Key laboratory of Data Engineering and Knowledge Engineering MOE Beijing China

In this paper, we present an effective method to craft text adversarial samples, revealing one important yet underestimated fact that DNN-based text classifiers are also prone to adversarial sample attack. Specifically, confronted with different adversarial scenarios, the text items that are important for classification are identified by computing the cost gradients of the input (white-box attack) or generating a series of occluded test samples (black-box attack). Based on these items, we design three perturbation strategies, namely insertion, modification, and removal, to generate adversarial samples. The experiment results show that the adversarial samples generated by our method can successfully fool both state-of-the-art character-level and word-level DNN-based text classifiers. The adversarial samples can be perturbed to any desirable classes without compromising their utilities. At the same time, the introduced perturbation is difficult to be perceived. Copyright © 2017, The Authors. All rights reserved.

关键词： Classification (of information)

来源：评论

学校读者我要写书评

暂无评论

Sentiment classification via L2-norm deep belief network 11

Sentiment classification via L2-norm deep belief network

引用

20th ACM Conference on Information and knowledge Management, CIKM'11

作者： Liu, Tao Li, Minghui Zhou, Shusen Du, Xiaoyong Key Laboratory of Data Engineering and Knowledge Engineering MOE 100872 Beijing China School of Information Renmin University of China 100872 Beijing China Microsoft Asian Research and Development Group 100080 Beijing China Shenzhen Graduate School Harbin Institute of Technology 518055 Shenzhen China

ISBN: (纸本)9781450307178

Automatic analysis of sentiments expressed in large scale online reviews is very important for intelligent business applications. Sentiment classification is the most popular task of sentiment analysis, which is more challenging than traditional topic-based text classification. Basic features, such as vocabulary words, are not enough to classify sentiments well. Deep Belief Network (DBN) is introduced to discover more abstract features of sentiments. To capture full information of the features, large-size network can be constructed, but at the same time, large-size network tends to over fit the training data and even noise, which will reduce the generalization ability of the network. In this paper, L2-norm Deep Belief Network (L2DBN) is proposed, which uses L2-norm regularization to optimize the network parameters of DBN. L2DBN is first initialized by an unsupervised layer-wise training algorithm, and then fine-tuned by a supervised procedure. Network parameters are optimized using both classification loss and network complexity. Experimental results show that the proposed L2DBN outperforms the state-of-the-art method and the basic DBN on golden, noisy and heterogeneous datasets. © 2011 ACM.

关键词： Sentiment analysis

来源：评论

学校读者我要写书评

暂无评论

What matters for ad-hoc video search? A large-scale evaluation on TRECVID

arXiv

引用

arXiv 2021年

作者： Chen, Aozhu Hu, Fan Wang, Zihan Zhou, Fangming Li, Xirong AIMC Lab. School of Information Renmin University of China Key Lab of Data Engineering and Knowledge Engineering Renmin University of China

For quantifying progress in Ad-hoc Video Search (AVS), the annual TRECVID AVS task is an important international evaluation. Solutions submitted by the task participants vary in terms of their choices of cross-modal matching models, visual features and training data. As such, what one may conclude from the evaluation is at a high level that is insufficient to reveal the influence of the individual components. In order to bridge the gap between the current solution-level comparison and the desired component-wise comparison, we propose in this paper a large-scale and systematic evaluation on TRECVID. By selected combinations of state-of-the-art matching models, visual features and (pre-)training data, we construct a set of 25 different solutions and evaluate them on the TRECVID AVS tasks 2016–2020. The presented evaluation helps answer the key question of what matters for AVS. The resultant observations and learned lessons are also instructive for developing novel AVS solutions. Copyright © 2021, The Authors. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Enabling Efficient NVM-Based Text Analytics without Decompression

Enabling Efficient NVM-Based Text Analytics without Decompre...

引用

International Conference on data engineering

作者： Xiaokun Fang Feng Zhang Junxiang Nong Mingxing Zhang Puyun Hu Yunpeng Chai Xiaoyong Du Key Laboratory of Data Engineering and Knowledge Engineering (MOE) and School of Information Renmin University of China Department of Computer Science and Engineering Tsinghua University

ISBN: (数字)9798350317152

ISBN: (纸本)9798350317169

Text analytics directly on compression (TADOC) is a promising technology designed for handling big data analytics. However, a substantial amount of DRAM is required for high performance, which limits its usage in many important scenarios where the capacity of DRAM is limited, such as memory-constrained systems. Non-volatile memory (NVM) is a novel storage technology that combines the advantage of reading per-formance and byte addressability of DRAM with the durability of traditional storage devices like SSD and HDD. Unfortunately, no research demonstrates how to use NVM to reduce DRAM utilization in compressed data analytics. In this paper, we propose N-TADOC, which substitutes DRAM with NVM while maintaining TADOC's analytics performance and space savings. Utilizing an NVM block device to reduce DRAM utilization presents two challenges, including poor data locality in traversing datasets and auxiliary data structure reconstruction on NVM. We develop novel designs to solve these challenges, including a pruning method with NVM pool management, bottom-up upper bound estimation, correspondent data structures, and persistence strategy at different levels of cost. Experimental results show that on four real-world datasets, N-TADOC achieves 2.04× performance speedup compared to the processing directly on the uncompressed data and 70.7% DRAM space saving compared to the original TADOC.

关键词： Performance evaluation Upper bound data analysis Costs Nonvolatile memory Random access memory Estimation

来源：评论

学校读者我要写书评

暂无评论

Personalized Clustering via Targeted Representation Learning

arXiv

引用

arXiv 2024年

作者： Geng, Xiwen Zhao, Suyun Yu, Yixin Peng, Borui Du, Pan Chen, Hong Li, Cuiping Wang, Mengdie Key Lab of Data Engineering and Knowledge Engineering MOE Renmin University of China China School of Information Renmin University of China China School of Statistics Remin University of China China

Clustering traditionally aims to reveal a natural grouping structure within unlabeled data. However, this structure may not always align with users’ preferences. In this paper, we propose a personalized clustering method that explicitly performs targeted representation learning by interacting with users via modicum task information (e.g., must-link or cannot-link pairs) to guide the clustering direction. We query users with the most informative pairs, i.e., those pairs most hard to cluster and those most easy to miscluster, to facilitate the representation learning in terms of the clustering preference. Moreover, by exploiting attention mechanism, the targeted representation is learned and augmented. By leveraging the targeted representation and constrained contrastive loss as well, personalized clustering is obtained. Theoretically, we verify that the risk of personalized clustering is tightly bounded, guaranteeing that active queries to users do mitigate the clustering risk. Experimentally, extensive results show that our method performs well across different clustering tasks and datasets, even when only a limited number of queries are available. Copyright © 2024, The Authors. All rights reserved.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

Energy-efficient Robust data-centric Storage in Wireless Sensor Networks

Energy-efficient Robust Data-centric Storage in Wireless Sen...

引用

第三届IEEE无线通讯、网络技术暨移动计算国际会议

作者： Yongxuan Lai Yufeng Wang Hong Chen School of Information Renmin University of China Beijing P.R.China Key Laboratory of Data Engineering and Knowledge Engineering MOE

In this paper, we propose a new Dynamic datacentric Storage (DDS) mechanism in wireless sensor network. DDS, which is aware of the data distributions of the network, dynamically adjusts the mappings from sensor readings to the storage points to reduce the cost of storing these readings, as well as to balance the storage and workload in the network. Moreover, it takes advantage of the GPSR routing protocol to store multiple copies of readings to improve the robustness of the network with little overhead. Simulation results show that the approach is more energy-efficient and robust than other data-centric schemes.

关键词： energy-efficient robust storage data-centric storage wireless sensor networks

来源：评论

学校读者我要写书评

暂无评论

EdgeNN: Efficient Neural Network Inference for CPU-GPU Integrated Edge Devices

EdgeNN: Efficient Neural Network Inference for CPU-GPU Integ...

引用

International Conference on data engineering

作者： Chenyang Zhang Feng Zhang Kuangyu Chen Mingjun Chen Bingsheng He Xiaoyong Du Key Laboratory of Data Engineering and Knowledge Engineering (MOE) and School of Information Renmin University of China School of Computing National University of Singapore

With the development of the architectures and the growth of AIoT application requirements, data processing on edge has become popular. Neural network inference is widely employed for data analytics on edge devices. This paper extensively explores neural network inference on integrated edge devices and proposes EdgeNN, the first neural network inference solution on CPU-GPU integrated edge devices. EdgeNN has three novel characteristics. First, EdgeNN can adaptively utilize the unified physical memory and conduct the zero-copy optimization. Second, EdgeNN involves a novel inference-targeted inter- and intra-kernel CPU-GPU hybrid execution approach, which co-runs the CPU with the GPU to fully utilize the edge device’s computing resources. Third, EdgeNN adopts a fine-grained adaptive inference tuning approach, which can divide the complicated inference structure into sub-tasks mapped to the CPU and the GPU. Experiments show that on six popular neural network inference tasks, EdgeNN brings an average of 3.97×, 3.12×, and 8.80× speedups to inference on the CPU of the integrated device, inference on a mobile phone CPU, and inference on an edge CPU device. Additionally, it achieves 22.02% time benefits to the direct execution of the original programs. Specifically, 9.93% comes from better utilization of unified memory, and 10.76% comes from CPU-GPU hybrid execution. Besides, EdgeNN can deliver 29.14× and 5.70× higher energy efficiency than the edge CPU and the discrete GPU, respectively. We have made EdgeNN available at https://***/ChenyangZhang-cs/EdgeNN.

关键词：

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：