检索结果-内蒙古大学图书馆

Towards optimized tensor code generation for deep learning on sunway many-core processor

Frontiers of computer Science 2024年第2期18卷 1-15页

作者： Mingzhen LI Changxi LIU Jianjin LIAO Xuegui ZHENG Hailong YANG Rujun SUN Jun XU Lin GAN Guangwen YANG Zhongzhi LUAN Depei QIAN State Key Laboratory of Software Development Environment Beijing 100191China School of Computer Science and Engineering Beihang UniversityBeijing 100191China National University of Singapore Singapore 119077Singapore State Key Laboratory of Mathematical Engineering and Advanced Computing Wuxi 214000China Science and Technology on Special System Simulation Laboratory Beijing Simulation Center Beijing 100854China Department of Computer Science and Technology Tsinghua UniversityBeijing 100084China

The flourish of deep learning frameworks and hardware platforms has been demanding an efficient compiler that can shield the diversity in both software and hardware in order to provide application *** the existing deep learning compilers,TVM is well known for its efficiency in code generation and optimization across diverse hardware *** the meanwhile,the Sunway many-core processor renders itself as a competitive candidate for its attractive computational power in both scientific computing and deep learning *** paper combines the trends in these two ***,we propose swTVM that extends the original TVM to support ahead-of-time compilation for architecture requiring cross-compilation such as *** addition,we leverage the architecture features during the compilation such as core group for massive parallelism,DMA for high bandwidth memory transfer and local device memory for data locality,in order to generate efficient codes for deep learning workloads on *** experiment results show that the codes generated by swTVM achieve 1.79x improvement of inference latency on average compared to the state-of-the-art deep learning framework on Sunway,across eight representative *** work is the first attempt from the compiler perspective to bridge the gap of deep learning and Sunway processor particularly with productivity and efficiency in *** believe this work will encourage more people to embrace the power of deep learning and Sunwaymany-coreprocessor.

关键词： sunway processor deep learning compiler code generation performance optimization

来源：评论

学校读者我要写书评

暂无评论

OnMKD: An Online Mutual Knowledge Distillation Framework for Passage Retrieval 12th

OnMKD: An Online Mutual Knowledge Distillation Framework for...

引用

12th National CCF Conference on Natural Language Processing and Chinese Computing, NLPCC 2023

作者： Deng, Jiali Li, Dongyang Zhang, Taolin He, Xiaofeng School of Computer Science and Technology East China Normal University Shanghai China School of Software Engineering East China Normal University Shanghai China NPPA Key Laboratory of Publishing Integration Development ECNUP Shanghai China

ISBN: (纸本)9783031446955

Dense passage retriever recalls a set of relevant passages from a large corpus according to a natural language question. The dual-encoder architecture is prevalent in dense passage retrievers, which is based on large-scale pre-trained language models (PLMs). However, existing PLMs usually have thick structures and bulky parameters, resulting in large memory and time consumption. To overcome the limitation of PLMs, in this paper we apply online distillation to passage retrieval and propose an Online Mutual Knowledge Distillation framework (OnMKD). Specifically, we obtain a lightweight retriever by simultaneously updating two peer networks with the same dual-encoder structure and different initial parameters, named Online Mutual Knowledge Refinement. To further interact with the latent knowledge of intermediate layers, we utilize a novel cross-wise contrastive loss to alternate the representation of questions and passages. Experimental results indicate that our framework outperforms other small baselines with the same number of layers on multiple QA benchmarks. Compared to the heavy PLMs, OnMKD significantly accelerates the inference process and reduces storage requirements with only a slight sacrifice in performance. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2023.

关键词： Distillation

来源：评论

学校读者我要写书评

暂无评论

Topology entropy: Enhancing graph partitioning for TAD identification and single-cell clustering

引用

Computational and Structural Biotechnology Journal 2025年 27卷 1864-1886页

作者： Liang, Qiushi Zhao, Shengjie Chen, Lingxi Li, Shuai Cheng School of Computer Science and Technology Tongji University Shanghai201804 China Department of Computer Science City University of Hong Kong 999077 Hong Kong Department of Biomedical Sciences City University of Hong Kong 999077 Hong Kong Engineering Research Center of Key Software Technologies for Smart City Perception and Planning Ministry of Education China

Entropy quantifies the limits of information compression and provides a theoretical foundation for exploring complex structures in large-scale graphs. However, effective metrics are needed to capture the intricate structural details in biological graphs. In this paper, we introduce the topology entropy encoding tree to quantify the complexity of biological graphs and show that minimizing the associated entropy is equivalent to optimal graph partitioning. We develop two methods, TEC-O and TEC-U, for partitioning ordered and unordered biological graphs. TEC-O is applied to identify Topologically Associated Domains (TADs) in Hi-C contact maps, while TEC-U is used for cell clustering in single-cell sequencing data. Results from simulated datasets demonstrate that topology entropy is robust to noise and effectively captures structural information, outperforming existing methods. Experiments on Hi-C data from five cell lines and ten single-cell sequencing datasets show that TEC-O and TEC-U achieve the highest accuracy in TAD detection and cell clustering, respectively, providing biologically meaningful insights. © 2025 The Authors

关键词： Cell culture

来源：评论

学校读者我要写书评

暂无评论

SLSNet: Weakly-Supervised Skin Lesion Segmentation Network with Self-attentions 20th

SLSNet: Weakly-Supervised Skin Lesion Segmentation Network w...

引用

20th Pacific Rim International Conference on Artificial Intelligence, PRICAI 2023

作者： Pei, Songwen Huang, Junjie School of Optical-Electrical and Computer Engineering University of Shanghai for Science and Technology Shanghai200093 China State Key Laboratory of Computer Architecture Institute of Computing Technology Chinese Academy of Sciences Beijing100190 China Engineering Research Center of Software/Hardware Co-design Technology and Application Ministry of Education East China Normal University Shanghai200062 China

ISBN: (纸本)9789819970247

computer-aided skin lesion segmentation with high precision is crucial to diagnose skin cancers in the early stage. However, the lack of pixel-level labels makes the skin lesion segmentation tasks challenging. To tackle this problem, a new weakly-supervised skin lesion segmentation network with self-attentions named SLSNet is proposed. SLSNet contains two modules and uses image-level labels as supervision information. One module named Intra-image Self-attention Seed Expansion (ISE) digs intra-image self-attentions with an expansion loss and a confidence loss to expand seed areas. The other module named Inter-image Affinity-based Noise Suppression (IAS) suppresses the noise pixels in attention maps via inter-image correlations. Extensive experiments conducted on ISIC-2017 dataset show that SLSNet achieves relatively high performance while reducing human labeling efforts. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd 2024.

关键词： Expansion

来源：评论

学校读者我要写书评

暂无评论

Real-IAD: A Real-World Multi-View Dataset for Benchmarking Versatile Industrial Anomaly Detection

Real-IAD: A Real-World Multi-View Dataset for Benchmarking V...

引用

Conference on computer Vision and Pattern Recognition (CVPR)

作者： Chengjie Wang Wenbing Zhu Bin-Bin Gao Zhenye Gan Jiangning Zhang Zhihao Gu Shuguang Qian Mingang Chen Lizhuang Ma Shanghai Jiao Tong University Youtu Lab Tencent Fudan University Ronacheer Co. Ltd Shanghai Development Center of Computer Software Technology

ISBN: (数字)9798350353006

ISBN: (纸本)9798350353013

Industrial anomaly detection (I AD) has garnered signif-icant attention and experienced rapid development. However, the recent development of I AD approach has encountered certain difficulties due to dataset limitations. On the one hand, most of the state-of-the-art methods have achieved saturation (over 99% in AUROC) on mainstream datasets such as MVTec, and the differences of methods cannot be well distinguished, leading to a significant gap between public datasets and actual application scenarios. On the other hand, the research on various new practical anomaly detection settings is limited by the scale of the dataset, posing a risk of overfitting in evaluation results. Therefore, we propose a large-scale, Real-world, and multi-view Industrial Anomaly Detection dataset, named Real- I AD, which contains 150K high-resolution images of 30 different objects, an order of magnitude larger than existing datasets. It has a larger range of defect area and ratio proportions, making it more challenging than previous datasets. To make the dataset closer to real application scenarios, we adopted a multi-view shooting method and proposed sample-level evaluation metrics. In addition, beyond the general unsupervised anomaly detection setting, we propose a new setting for Fully Unsupervised Indus-trial Anomaly Detection (FUIAD) based on the observation that the yield rate in industrial production is usually greater than 60%, which has more practical application value. Finally, we report the results of popular I AD methods on the Real- I AD dataset, providing a highly challenging benchmark to promote the development of the I AD field.

关键词： Training Measurement Noise Metals Production Benchmark testing Inspection

来源：评论

学校读者我要写书评

暂无评论

Multi-Objective Optimization of Multi-Product Parallel Disassembly Line Balancing Problem Considering Multi-Skilled Workers Using a Discrete Chemical Reaction Optimization Algorithm

引用

computers, Materials & Continua 2024年第9期80卷 4475-4496页

作者： Xiwang Guo Liangbo Zhou Zhiwei Zhang Liang Qi Jiacun Wang Shujin Qin Jinrui Cao College of Information and Control Engineering Liaoning Petrochemical UniversityFushun113000China Department of Computer Science and Technology Shandong University of Science and TechnologyQingdao266590China Department of Computer Science and Software Engineering Monmouth UniversityWest Long BranchNJ 07764USA Research Center of the Economic and Social Development of Henan East Provincial Joint Shangqiu Normal UniversityShangqiu476000China Department of Computer Science New Jersey City UniversityJersey CityNJ 07305USA

This work investigates a multi-product parallel disassembly line balancing problem considering multi-skilled workers.A mathematical model for the parallel disassembly line is established to achieve maximized disassembly profit and minimized workstation cycle *** on a product’s AND/OR graph,matrices for task-skill,worker-skill,precedence relationships,and disassembly correlations are developed.A multi-objective discrete chemical reaction optimization algorithm is *** enhance solution diversity,improvements are made to four reactions:decomposition,synthesis,intermolecular ineffective collision,and wall invalid collision reaction,completing the evolution of molecular *** established model and improved algorithm are applied to ball pen,flashlight,washing machine,and radio combinations,*** a Collaborative Resource Allocation(CRA)strategy based on a Decomposition-Based Multi-Objective Evolutionary Algorithm,the experimental results are compared with four classical algorithms:MOEA/D,MOEAD-CRA,Non-dominated Sorting Genetic Algorithm Ⅱ(NSGA-Ⅱ),and Non-dominated Sorting Genetic Algorithm Ⅲ(NSGA-Ⅲ).This validates the feasibility and superiority of the proposed algorithm in parallel disassembly production lines.

关键词： Parallel disassembly line balancing problem multi-product multiskilled workers discrete chemical reaction optimization algorithm

来源：评论

学校读者我要写书评

暂无评论

SG-LSBA: Semantic Latent Space Backdoor Attack on Stable Diffusion 3rd

SG-LSBA: Semantic Latent Space Backdoor Attack on Stable Di...

引用

3rd International Conference on Cyberspace Simulation and Evaluation, CSE 2024

作者： Pan, Yu Chen, Jiahao Wang, Lin Dai, Bingrong School of Computer and Information Engineering Shanghai Polytechnic University Shanghai201209 China Shanghai Development Center of Computer Software Technology Shanghai201112 China

ISBN: (纸本)9789819645084

Stable Diffusion (SD) models have achieved remarkable success in text-to-image synthesis, but their security vulnerabilities remain largely unexplored. In this paper, we introduce a novel semantic-guided latent space backdoor attack (SG-LSBA) that leverages the semantic information in the text input to inject stealthy and semantically coherent backdoors into SD models. Our approach outperforms existing methods by crafting context-aware semantic triggers, identifying target visual features in the latent space, and employing an adversarial optimization framework. Extensive evaluations demonstrate the high success rates, strong semantic relevance, and exceptional stealthiness of SG-LSBA. Our findings highlight the urgent need for considering the complex interplay between semantics and latent representations in developing robust defenses against back-door attacks in SD models. We make our code and datasets publicly available to facilitate further research and development of secure and reliable text-to-image synthesis models. The code is available at https://***/paoche11/SG-LSBA. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Latent space backdoor attack Semantic guidance Semantic triggers Stable Diffusion

来源：评论

学校读者我要写书评

暂无评论

Research on key technologies of edge cache in virtual data space across WAN

引用

Frontiers of computer Science 2023年第1期17卷 15-34页

作者： Jiantong HUO Yaowen XU Zhisheng HUO Limin XIAO Zhenxue HE State Key Laboratory of Software Development Environment Beihang UniversityBeijing 100191China School of Computer Science and Engineering Beihang UniversityBeijing 100191China High Performance Computing Center Beihang UniversityBeijing 100191China College of Software Beihang UniversityBeijing 100191China Hebei Key Laboratory of Agricultural Big Data Hebei Agricultural UniversityBaoding 071001China College of Computer Science and Technology Zhejiang UniversityHangZhou 310013China

The authors of this paper have previously proposed the global virtual data space system (GVDS) to aggregate the scattered and autonomous storage resources in China’s national supercomputer grid (National Supercomputing center in Guangzhou, National Supercomputing center in Jinan, National Supercomputing center in Changsha, shanghai Supercomputing center, and computer Network Information center in Chinese Academy of Sciences) into a storage system that spans the wide area network (WAN), which realizes the unified management of global storage resources in China. At present, the GVDS has been successfully deployed in the China National Grid environment. However, when accessing and sharing remote data in the WAN, the GVDS will cause redundant transmission of data and waste a lot of network bandwidth resources. In this paper, we propose an edge cache system as a supplementary system of the GVDS to improve the performance of upper-level applications accessing and sharing remote data. Specifically, we first designs the architecture of the edge cache system, and then study the key technologies of this architecture: the edge cache index mechanism based on double-layer hashing, the edge cache replacement strategy based on the GDSF algorithm, the request routing based on consistent hashing method, and the cluster member maintenance method based on the SWIM protocol. The experimental results show that the edge cache system has successfully implemented the relevant operation functions (read, write, deletion, modification, etc.) and is compatible with the POSIX interface in terms of function. Further, it can greatly reduce the amount of data transmission and increase the data access bandwidth when the accessed file is located at the edge cache system in terms of performance, i.e., its performance is close to the performance of the network file system in the local area network (LAN).

关键词： virtual data space system wide area network edge cache redundant data transmission

来源：评论

学校读者我要写书评

暂无评论

Learning to Measure the Point Cloud Reconstruction Loss in a Representation Space

Learning to Measure the Point Cloud Reconstruction Loss in a...

引用

Conference on computer Vision and Pattern Recognition (CVPR)

作者： Tianxin Huang Zhonggan Ding Jiangning Zhang Ying Tai Zhenyu Zhang Mingang Chen Chengjie Wang Yong Liu APRIL Lab Zhejiang University Tencent YouTu Lab Shanghai Development Center of Computer Software Technology

For point cloud reconstruction-related tasks, the reconstruction losses to evaluate the shape differences between reconstructed results and the ground truths are typically used to train the task networks. Most existing works measure the training loss with point-to-point distance, which may introduce extra defects as predefined matching rules may deviate from the real shape differences. Although some learning-based works have been proposed to overcome the weaknesses of manually-defined rules, they still measure the shape differences in 3D Euclidean space, which may limit their ability to capture defects in reconstructed shapes. In this work, we propose a learning-based Contrastive Adver-sarial Loss (CALoss) to measure the point cloud reconstruction loss dynamically in a non-linear representation space by combining the contrastive constraint with the adversarial strategy. Specifically, we use the contrastive constraint to help CALoss learn a representation space with shape similarity, while we introduce the adversarial strategy to help CALoss mine differences between reconstructed results and ground truths. According to experiments on reconstruction-related tasks, CALoss can help task networks improve re-construction performances and learn more representative representations.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Attribute-Based Non-Interactive Privacy-Protected Crowd-Sourcing software Testing Engineer Selection Mechanism

Attribute-Based Non-Interactive Privacy-Protected Crowd-Sour...

引用

IEEE International Conference on software Quality, Reliability and Security Companion (QRS-C)

作者： Qiliang Yang Lizhi Cai Jiayu Gong Minlu Tang Yi Lin Shanghai Development Center of Computer Software Technology Cryptographic Standard Study & Security Evaluation Laboratory Shanghai China Shanghai Development Center of Computer Software Technology Shanghai Key Laboratory of Computer Software Testing & Evaluating Shanghai China

The central management platforms in traditional crowd-sourced software testing networks are easy to become the target of attack by the enemies, and when the central management platform is attacked, it is easy to cause a single point of failure and bring the whole system down. In addition, when selecting software testing engineers for crowd-sourcing software testing tasks, most mechanisms select engineers based on their credits. This approach is too one-sided and fails to achieve fine-grained engineer selection. In order to solve above problems, we have proposed a non-interactive and fine-grained crowd-sourcing software testing engineer selection mechanism. In our mechanism, the task publisher can select engineers according to their attributes. Next, we have given an implementation of our non-interactive software testing engineer selection mechanism by applying QAP. The privacy of task publisher and engineers is protected. The security proof is also given. Simulation results show that our mechanism is feasible.

关键词： software testing Privacy Simulation software quality Reliability engineering software reliability Security

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：