检索结果-内蒙古大学图书馆

24th IEEE International Conference on High Performance Computing and Communications, 8th IEEE International Conference on Data science and Systems, 20th IEEE International Conference on Smart City and 8th IEEE International Conference on Dependability in Sensor, Cloud and Big Data Systems and Application, HPCC/DSS/SmartCity/DependSys 2022

作者： Wei, Cunyang Jia, Haipeng Zhang, Yunquan Li, Kun Wang, Luhan Institute of Computing Technology Chinese Academy of Sciences State Key Lab of Processors Beijing China School of Computer Science and Technology University of Chinese Academy of Sciences Beijing China Microsoft Research China

ISBN: (纸本)9798350319934

The trend in modern high performance computing is to decompose a large linear algebraic problem into many small problems that can be solved independently. Although there are many studies to obtain near-peak performance for large-scale dense matrix operations, it is not sufficient for batch operations with small matrices. The study of small GEMM kernel optimization and load balanced scheduling of batch operations on ARM processors is not enough. In this paper, we present LBBGEMM, a load-balanced batch GEMM framework for optimizing large groups of variable-size small GEMM to boost near-optimal performance based on ARMv8 architecture. The LBBGEMM is divided into the install-time stage and the run-time stage. At the install-time stage, we analyze the characteristics of each transposition mode to design the high-performance small GEMM kernel without data packing. This strategy greatly reduces the memory access overhead. In addition, we optimize instruction scheduling and instruction selection carefully to achieve optimal performance. The run-time stage provides a comprehensive auto-tuning process for batch GEMM by using a tiling designer and a pre-grouped dynamic scheduling algorithm. The tiling designer generates high-performance execution plans for each group of matrices with different sizes. Then we divide the large group of GEMM operations into small task groups. These task groups are assigned to threads for execution in the form of command queues through our proposed dynamic mapping between threads and tasks. This pre-grouped multi-thread task scheduling algorithm greatly improves the speedup of multi-thread. The experiments show that LBBGEMM could achieve significant performance improvements in batch GEMM compared with other mainstream BLAS libraries. © 2022 IEEE.

关键词： Matrix algebra

来源：评论

学校读者我要写书评

暂无评论

StreamDCIM: A Tile-based Streaming Digital CIM Accelerator with Mixed-stationary Cross-forwarding Dataflow for Multimodal Transformer

arXiv

引用

arXiv 2025年

作者： Qin, Shantian Qiang, Ziqing Fan, Zhihua Li, Wenming An, Xuejun Ye, Xiaochun Fan, Dongrui State Key Lab of Processors Institute of Computing Technology Chinese Academy of Sciences Beijing China School of Computer Science and Technology University of Chinese Academy of Sciences Beijing China

Multimodal Transformers are emerging artificial intelligence (AI) models designed to process a mixture of signals from diverse modalities. Digital computing-in-memory (CIM) architectures are considered promising for achieving high efficiency while maintaining high accuracy. However, current digital CIM-based accelerators exhibit inflexibility in microarchitecture, dataflow, and pipeline to effectively accelerate multimodal Transformer. In this paper, we propose StreamDCIM, a tile-based streaming digital CIM accelerator for multimodal Transformers. It overcomes the above challenges with three features: First, we present a tile-based reconfigurable CIM macro microarchitecture with normal and hybrid reconfigurable modes to improve intra-macro CIM utilization. Second, we implement a mixed-stationary cross-forwarding dataflow with tile-based execution decoupling to exploit tile-level computation parallelism. Third, we introduce a ping-pong-like fine-grained compute-rewriting pipeline to overlap high-latency on-chip CIM rewriting. Experimental results show that StreamDCIM outperforms non-streaming and layer-based streaming CIM-based solutions by geomean 2.63× and 1.28× on typical multimodal Transformer models. Copyright © 2025, The Authors. All rights reserved.

关键词： Reconfigurable architectures

来源：评论

学校读者我要写书评

暂无评论

Few-Shot Object Detection via Variational Feature Aggregation

arXiv

引用

arXiv 2023年

作者： Han, Jiaming Ren, Yuqiang Ding, Jian Yan, Ke Xia, Gui-Song NERCMS School of Computer Science Wuhan University China State Key Lab. LIESMARS Wuhan University China YouTu Lab Tencent China

As few-shot object detectors are often trained with abundant base samples and fine-tuned on few-shot novel examples, the learned models are usually biased to base classes and sensitive to the variance of novel examples. To address this issue, we propose a meta-learning framework with two novel feature aggregation schemes. More precisely, we first present a Class-Agnostic Aggregation (CAA) method, where the query and support features can be aggregated regardless of their categories. The interactions between different classes encourage class-agnostic representations and reduce confusion between base and novel classes. Based on the CAA, we then propose a Variational Feature Aggregation (VFA) method, which encodes support examples into class-level support features for robust feature aggregation. We use a variational autoencoder to estimate class distributions and sample variational features from distributions that are more robust to the variance of support examples. Besides, we decouple classification and regression tasks so that VFA is performed on the classification branch without affecting object localization. Extensive experiments on PASCAL VOC and COCO demonstrate that our method significantly outperforms a strong baseline (up to 16%) and previous state-of-the-art methods (4% in average). Code will be available at: https://***/csuhan/VFA. © 2023, CC BY.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

FEDGT: FEDERATED NODE CLASSIFICATION WITH SCAlabLE GRAPH TRANSFORMER

arXiv

引用

arXiv 2024年

作者： Zhang, Zaixi Hu, Qingyong Yu, Yang Gao, Weibo Liu, Qi Anhui Province Key Lab of Big Data Analysis and Application School of Computer Science and Technology University of Science and Technology of China China State Key Laboratory of Cognitive Intelligence Anhui Hefei China Hong Kong University of Science and Technology Hong Kong

Graphs are widely used to model relational data. As graphs are getting larger and larger in real-world scenarios, there is a trend to store and compute subgraphs in multiple local systems. For example, recently proposed subgraph federated learning methods train Graph Neural Networks (GNNs) distributively on local subgraphs and aggregate GNN parameters with a central server. However, existing methods have the following limitations: (1) The links between local subgraphs are missing in subgraph federated learning. This could severely damage the performance of GNNs that follow message-passing paradigms to update node/edge features. (2) Most existing methods overlook the subgraph heterogeneity issue, brought by subgraphs being from different parts of the whole graph. To address the aforementioned challenges, we propose a scalable Federated Graph Transformer (FedGT) in the paper. Firstly, we design a hybrid attention scheme to reduce the complexity of the Graph Transformer to linear while ensuring a global receptive field with theoretical bounds. Specifically, each node attends to the sampled local neighbors and a set of curated global nodes to learn both local and global information and be robust to missing links. The global nodes are dynamically updated during training with an online clustering algorithm to capture the data distribution of the corresponding local subgraph. Secondly, FedGT computes clients' similarity based on the aligned global nodes with optimal transport. The similarity is then used to perform weighted averaging for personalized aggregation, which well addresses the data heterogeneity problem. Finally, extensive experimental results on 6 datasets and 2 subgraph settings demonstrate the superiority of FedGT. © 2024, CC BY.

关键词： Graph neural networks

来源：评论

学校读者我要写书评

暂无评论

EgpuIP: An Embedded GPU Accelerated Library for Image Processing 24

EgpuIP: An Embedded GPU Accelerated Library for Image Proces...

引用

作者： Wang, Luhan Jia, Haipeng Zhang, Yunquan Li, Kun Wei, Cunyang Institute of Computing Technology Chinese Academy of Sciences State Key Lab of Processors Beijing China School of Computer Science and Technology University of Chinese Academy of Sciences Beijing China Microsoft Research China

ISBN: (纸本)9798350319934

With the advances of embedded GPUs' programming models like GLES and OpenCL, the mobile processor has gained more parallel computing capability, which enables real-time image processing on portable devices. GLES is an excellent option to implement high-performance image processing on embedded GPUs due to its low hardware overhead. However, most GLES studies only focus on porting specific algorithms to embedded GPUs without a general optimization guide. In order to address the pending problems, this paper presents effective performance optimization chains to guide the optimization of image processing algorithms by using GLES. The image processing algorithms can be divided into three modes including data-independent, data-sharing and data-related according to their memory access and calculation characteristics. Based on this classification, our optimization chains contain four optimization directions. 1) Optimizing access to off-chip memory for the memory-bound data-independent algorithm;2) Exploiting data locality by utilizing shared memory and cache for the data-sharing algorithm;3) Redesigning the algorithm to optimize the sharing of computational results between threads for the data-related algorithm;4) Making full use of computation resource for the above three algorithms. Based on these optimization chains, we design an embedded GPU accelerated image processing library, EgpuIP. To evaluate specific optimization methods and performance improvements, we employ histogram equalization, Gaussian pyramid and integral filter as the representative algorithm from EgpuIP and adequately optimize them guided by the proposed optimization chains. Compared to the OpenCV, experiments show that the three algorithms in EgpuIP provide up to 19×88×, and 3× speedup respectively. © 2022 IEEE.

关键词： Graphics processing unit

来源：评论

学校读者我要写书评

暂无评论

ImageScope: Unifying Language-Guided Image Retrieval via Large Multimodal Model Collective Reasoning

arXiv

引用

arXiv 2025年

作者： Luo, Pengfei Zhou, Jingbo Xu, Tong Xia, Yuan Xu, Linli Chen, Enhong School of Computer Science and Technology University of Science and Technology of China State Key Laboratory of Cognitive Intelligence Hefei China Business Intelligence Lab Baidu Research Beijing China Baidu Inc Beijing China

With the proliferation of images in online content, language-guided image retrieval (LGIR) has emerged as a research hotspot over the past decade, encompassing a variety of subtasks with diverse input forms. While the development of large multimodal models (LMMs) has significantly facilitated these tasks, existing approaches often address them in isolation, requiring the construction of separate systems for each task. This not only increases system complexity and maintenance costs, but also exacerbates challenges stemming from language ambiguity and complex image content, making it difficult for retrieval systems to provide accurate and reliable results. To this end, we propose ImageScope, a training-free, three-stage framework that leverages collective reasoning to unify LGIR tasks. The key insight behind the unification lies in the compositional nature of language, which transforms diverse LGIR tasks into a generalized text-to-image retrieval process, along with the reasoning of LMMs serving as a universal verification to refine the results. To be specific, in the first stage, we improve the robustness of the framework by synthesizing search intents across varying levels of semantic granularity using chain-of-thought (CoT) reasoning. In the second and third stages, we then reflect on retrieval results by verifying predicate propositions locally, and performing pairwise evaluations globally. Experiments conducted on six LGIR datasets demonstrate that ImageScope outperforms competitive baselines. Comprehensive evaluations and ablation studies further confirm the effectiveness of our design. © 2025, CC BY-NC-ND.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

PDMA: Probabilistic service migration approach for delay-aware and mobility-aware mobile edge computing

PDMA: Probabilistic service migration approach for delay-awa...

引用

作者： Xu, Minxian Zhou, Qiheng Wu, Huaming Lin, Weiwei Ye, Kejiang Xu, Chengzhong Shenzhen Institutes of Advanced Technology Chinese Academy of Sciences Shenzhen China Center for Applied Mathematics Tianjin University Tianjin China School of Computer Science and Engineering South China University of Technology Guangzhou China State Key Lab of IOTSC Department of Computer Science University of Macau China

As a key technology in the 5G era, mobile edge computing (MEC) has developed rapidly in recent years. MEC aims to reduce the service delay of mobile users, while alleviating the processing pressure on the core network. MEC can be regarded as an extension of cloud computing on the user side, which can deploy edge servers and bring computing resources closer to mobile users, and provide more efficient interactions. However, due to the user's dynamic mobility, the distance between the user and the edge server will change dynamically, which may cause fluctuations in Quality of Service. Therefore, when a mobile user moves in the MEC environment, certain approaches are needed to schedule services deployed on the edge server to ensure the user experience. In this article, we model service scheduling in MEC scenarios and propose a delay-aware and mobility-aware service management approach based on concise probabilistic methods. This approach has low computational complexity and can effectively reduce service delay and migration costs. Furthermore, we conduct experiments by utilizing multiple realistic datasets and use iFogSim to evaluate the performance of the algorithm. The results show that our proposed approach can optimize the performance on service delay, with 8%–20% improvement and reduce the migration cost by more than 75% compared with baselines during the rush hours. © 2021 John Wiley & Sons Ltd.

关键词： Mobile edge computing

来源：评论

学校读者我要写书评

暂无评论

Testing autonomous systems with believed equivalence refinement

arXiv

引用

arXiv 2021年

作者： Cheng, Chih-Hong Yan, Rongjie DENSO AUTOMOTIVE Deutschland GmbH Eching Germany State Key Laboratory of Computer Science ISCAS Beijing China

Continuous engineering of autonomous driving functions commonly requires deploying vehicles in road testing to obtain inputs that cause problematic decisions. Although the discovery leads to producing an improved system, it also challenges the foundation of testing using equivalence classes and the associated relative test coverage criterion. In this paper, we propose believed equivalence, where the establishment of an equivalence class is initially based on expert belief and is subject to a set of available test cases having a consistent valuation. Upon a newly encountered test case that breaks the consistency, one may need to refine the established categorization in order to split the originally believed equivalence into two. Finally, we focus on modules implemented using deep neural networks where every category partitions an input over the real domain. We present both analytical and lazy methods to suggest the refinement. The concept is demonstrated in analyzing multiple autonomous driving modules, indicating the potential of our proposed approach. Copyright © 2021, The Authors. All rights reserved.

关键词： Equivalence classes

来源：评论

学校读者我要写书评

暂无评论

ImageScope: Unifying Language-Guided Image Retrieval via Large Multimodal Model Collective Reasoning 25

ImageScope: Unifying Language-Guided Image Retrieval via Lar...

引用

34th ACM Web Conference, WWW 2025

ISBN: (纸本)9798400712746

关键词： Photointerpretation

来源：评论

学校读者我要写书评

暂无评论

CAMInterHand: Cooperative Attention for Multi-View Interactive Hand Pose and Mesh Reconstruction

CAMInterHand: Cooperative Attention for Multi-View Interacti...

引用

IEEE International Conference on Robotics and Automation (ICRA)

作者： Guwen Han Qi Ye Anjun Chen Jiming Chen College of Computer Science and Technology Zhejiang University Hangzhou China College of Control Science and Engineering Zhejiang University Hangzhou China The College of Control Science and Engineeringthe State Key Laboratory of Industrial Control Technology Zhejiang University and the Key Key Lab of CS&AUS of Zhejiang Province

ISBN: (数字)9798350384574

ISBN: (纸本)9798350384581

Interactive hand mesh reconstruction from singleview images poses a significant challenge with the severe occlusion and depth ambiguity inherent in interactive hand gestures. Recent approaches that employ probabilistic models and tokenpruned techniques have shown decent results in multi-view human body reconstruction. Nevertheless, these methods have not fully utilized multi-scale semantic information from multiview images and are not applicable in scenarios involving severe occlusion during dual-hand interactions. Simultaneously, current single-view methods independently reconstruct the left and right hands, which are ineffective in enhancing the interaction between both hands. To address these challenges, we propose CAMInterHand, a cooperative attention-based method for multi-view interactive hand pose and mesh reconstruction. Specifically, CAMInterHand extracts local pyramid features and global vertex features from multi-scale feature maps of multi-view images, enabling the exploration of rich local semantic information and facilitating effective feature alignment. Furthermore, CAMInterHand employs the cooperative attention fusion module to fuse all features from multi-view images, enhancing interactions among vertices of dual hands within global and local contexts. We conduct extensive experiments on the large-scale multi-view dataset InterHand2.6M and CAMInterHand achieves a substantial performance improvement over existing methods for multi-view and single-view interactive hand reconstruction.

关键词： Fuses Semantics Feature extraction Probabilistic logic Data mining Robotics and automation Image reconstruction

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：