检索结果-内蒙古大学图书馆

2023 IEEE International Conference on Industrial Technology, ICIT 2023

作者： Gravey, Thibaut Meddah, Karim Robert, Teo Rutovic, Emmanuel Montheard, Romain Ould-Bachir, Tarek Polytechnique Montréal Motce Laboratory Department of Computer and Software Engineering MontréalQCH3T 1J4 Canada Labèze France AESIM. Tech Montréal Canada

ISBN: (纸本)9798350336504

This paper presents a generic and software configurable overlay for the acquisition and visualization of data generated by embedded processing systems implemented on FPGA. The proposed architecture takes advantage of the coupling and interaction between the PL (programmable logic) and the PS (processing system) offered by the AMD PYNQ open-source framework on Zynq and several other platforms to provide the end-user with a high level abstraction programming interface. Results, cost, performance and design limitations of the overlay are discussed around its use for HIL simulation of high switching frequency power electronic circuits. The paper demonstrates that the overlay footprint is sufficiently small to be used on low-cost FPGA platforms, and that it provides a throughput of hundreds of millions of samples per second over up to eight 16-bit independent channels, while offering the capacity to log up to 128 MB of contiguous frames of data. © 2023 IEEE.

关键词： Python

来源：评论

学校读者我要写书评

暂无评论

Programming Education for Young People using the Falling-Puzzle Game, “Puyo Puyo”

Programming Education for Young People using the Falling-Puz...

引用

IEEE Education engineering (EDUCON)

作者： Daisuke Saito Ruochen Tian Hironori Washizaki Yoshiaki Fukazawa Global Software Engineering Laboratory Waseda University Tokyo Japan Department of Computer Science and Engineering Waseda University Tokyo Japan

This study utilizes the game rules of a falling-puzzle game, developed as a consumer-oriented digital game, in programming education for young people. When digital games are used in programming education, they are often designed specifically for that purpose. In this study, we focused on the game rules of the consumer falling-object puzzle game, “Puyo Puyo.” Learning impact was investigated on 23 Japanese elementary, junior high, and senior high school students. The results show that the concepts of branching and arraying in programming were taught effectively; thus, consumer digital game rules can be used as a case study for programming education.

关键词： Video games Conferences Education Games Writing engineering education Programming profession

来源：评论

学校读者我要写书评

暂无评论

2D-3D Feature Co-Embedding Network with Sparse Annotation for 3D Medical Image Segmentation

2D-3D Feature Co-Embedding Network with Sparse Annotation fo...

引用

2024 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2024

作者： Zhu, Mingzhu Guo, Shuyu Wang, Ziwei Jiao, Jianhang Bai, Tian Jilin University College of Computer Science and Technology Changchun China Jilin University Key Laboratory of Symbolic Computation and Knowledge Engineering Ministry of Education Changchun China Jilin University College of Software Changchun China The Second Norman Bethune Hospital Jilin University Department of Orthopedics Changchun China

ISBN: (纸本)9798350386226

Supervised methods on 3D medical image segmentation need large amounts of annotated data, but annotating is time-consuming. Also, existing 3D segmentation methods capture more global structural information but overlook local detailed features, which negatively impacts the segmentation of small tissues. In this paper, we propose a novel weakly-supervised 2D-3D Feature Co-Embedding Network (2D-3D CoENet) that includes 2D and 3D encoding layers, simultaneously extracting 2D local detailed and 3D global structural features. To reduce annotation costs, we use fewer labeled slices as ground truth and pseudo-labels are generated by 2D-3D CoENet for other slices. Additionally, multi-view learning is introduced to capture more 2D local detailed information, and a Multi-view Semantic Consistency loss (MSC loss) is proposed to constrain features from multiple perspectives. To further enhance the local detailed texture features, we propose an Edge Enhancement Module (EEM) in the 3D segmentation network to enhance the edge detail features. Our experimental results on the SKI10 dataset and OAI ZIB dataset demonstrate that our method outperforms the SOTA weakly-supervised segmentation methods. Moreover, our approach achieves results that are comparable to the fully-supervised upper bound results. © 2024 IEEE.

关键词： Medical imaging

来源：评论

学校读者我要写书评

暂无评论

Seed Feature Maps-based CNN Models for LEO Satellite Remote Sensing Services

Seed Feature Maps-based CNN Models for LEO Satellite Remote ...

引用

2023 IEEE International Conference on Web Services, ICWS 2023

作者： Lu, Zhichao Ding, Chuntao Wang, Shangguang Cheng, Ran Juefei-Xu, Felix Boddeti, Vishnu Naresh Sun Yat-sen University School of Software Engineering Zhuhai China Beijing Jiaotong University School of Computer and Information Technology Beijing China Beijing University of Posts and Telecommunications Key Laboratory of Networking and Switching Technology Beijing China Southern University of Science and Technology Department of Computer Science and Engineering Shenzhen China New York University New YorkNY United States Michigan State University Department of Computer Science and Engineering East LansingMI United States

ISBN: (纸本)9798350304855

Deploying high-performance convolutional neural network (CNN) models on low-earth orbit (LEO) satellites for rapid remote sensing image processing has attracted significant interest from industry and academia. However, the limited resources available on LEO satellites contrast with the demands of resource-intensive CNN models, necessitating the adoption of ground-station server assistance for training and updating these models. Existing approaches often require large floating-point operations (FLOPs) and substantial model parameter transmissions, presenting considerable challenges. To address these issues, this paper introduces a ground-station server-assisted framework. With the proposed framework, each layer of the CNN model contains only one learnable feature map (called the seed feature map) from which other feature maps are generated based on specific rules. The hyperparameters of these rules are randomly generated instead of being trained, thus enabling the generation of multiple feature maps from the seed feature map and significantly reducing FLOPs. Furthermore, since the random hyperparameters can be saved using a few random seeds, the ground station server assistance can be facilitated in updating the CNN model deployed on the LEO satellite. Experimental results on the ISPRS Vaihingen, ISPRS Potsdam, UAVid, and LoveDA datasets for semantic segmentation services demonstrate that the proposed framework outperforms existing state-of-the-art approaches. In particular, the SineFM-based model achieves a higher mIoU than the UNetFormer on the UAVid dataset, with 3.3 × fewer parameters and 2.2 × fewer FLOPs. © 2023 IEEE.

关键词： Neural network models

来源：评论

学校读者我要写书评

暂无评论

SEPT: Standard-Definition Map Enhanced Scene Perception and Topology Reasoning for Autonomous Driving

引用

IEEE Robotics and Automation Letters 2025年第7期10卷 7126-7133页

作者： Pei, Muleilan Shan, Jiayao Li, Peiliang Shi, Jieqi Huo, Jing Gao, Yang Shen, Shaojie Hong Kong University of Science and Technology Department of Electronic and Computer Engineering Hong Kong Zhuoyu Technology Shenzhen China Nanjing University State Key Laboratory for Novel Software Technology Nanjing China

Online scene perception and topology reasoning are critical for autonomous vehicles to understand their driving environments, particularly for mapless driving systems that endeavor to reduce reliance on costly High-Definition (HD) maps. However, recent advances in online scene understanding still face limitations, especially in long-range or occluded scenarios, due to the inherent constraints of onboard sensors. To address this challenge, we propose a Standard-Definition (SD) Map Enhanced scene Perception and Topology reasoning (SEPT) framework, which explores how to effectively incorporate the SD map as prior knowledge into existing perception and reasoning pipelines. Specifically, we introduce a novel hybrid feature fusion strategy that combines SD maps with Bird's-Eye-View (BEV) features, considering both rasterized and vectorized representations, while mitigating potential misalignment between SD maps and BEV feature spaces. Additionally, we leverage the SD map characteristics to design an auxiliary intersection-aware keypoint detection task, which further enhances the overall scene understanding performance. Experimental results on the large-scale OpenLane-V2 dataset demonstrate that by effectively integrating SD map priors, our framework significantly improves both scene perception and topology reasoning, outperforming existing methods by a substantial margin. 2016 IEEE.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Using Lock-Free Design for Throughput-Optimized Cache Eviction

引用

Proceedings of the ACM on Measurement and Analysis of Computing systems 2025年第2期9卷 1-28页

作者： Dong, Chao Wang, Fang Jiang, Hong Feng, Dan Huazhong University of Science and Technology Key Laboratory of Information Storage System Wuhan National Laboratory for Optoelectronics Engineering Research Center of data storage systems and Technology School of Computer Science and Technology Ministry of Education of China Hubei Wuhan China University of Texas at Arlington Department of Computer Science and Engineering ArlingtonTX United States

In large-scale information systems, storage device performance continues to improve while workloads expand in size and access characteristics. This growth puts tremendous pressure on caches and storage hierarchy in terms of concurrent throughput. However, existing cache eviction policies often struggle to provide adequate concurrent throughput due to their reliance on coarse-grained locking mechanisms and complex data structures. This paper presents a practical approach to cache eviction algorithm design, called Mobius, that optimizes the concurrent throughput of caches and reduces cache operation latency by utilizing lock-free data structures, while maintaining comparable hit ratios. Mobius includes two key designs. First, Mobius employs two lock-free FIFO queues to manage cache items, ensuring that all cache operations are executed efficiently in parallel. Second, Mobius integrates a consecutive detection mechanism that merges multiple modifications during eviction into a single operation, thereby reducing data races. Extensive evaluations using both synthetic and real-world workloads from high-concurrency clusters demonstrate that Mobius achieves a concurrent-throughput improvement ranging from 1.2× to 8.5× over state-of-the-art methods, while also maintaining lower latency and comparable cache hit ratios. The implementation of Mobius in CacheLib and RocksDB highlights its effectiveness in enhancing cache performance in practical scenarios. © 2025 ACM.

关键词： Keyways

来源：评论

学校读者我要写书评

暂无评论

Effective Entry-Wise Flow for Molecule Generation 40

Effective Entry-Wise Flow for Molecule Generation

引用

40th IEEE International Conference on Data engineering, ICDE 2024

作者： Zhang, Qifan Yao, Junjie Yang, Yuquan Shi, Yizhou Gao, Wei Wang, Xiaoling School of Computer Science and Technology East China Normal University China Software Engineering Institute East China Normal University China Shanghai Key Laboratory of Trustworthy Computing China University of Massachusetts Department of Chemistry Boston United States University of Michigan Ann Arbor United States

ISBN: (纸本)9798350317152

Molecule generation is a critical process in the fields of drug discovery and materials science. Recently, generative models based on normalizing flows have demonstrated significant potential in this domain. These models are particularly suited for handling the symmetrical and complex chemical structures often encountered in molecular datasets. Despite their promising nature, normalizing flow-based models for molecule generation face considerable challenges. The complexity of molecule representation, the rigorous demands of optimization, and the scarcity of training labels in molecular datasets contribute to these difficulties. Additionally, adequately and comprehensively learning the distribution of molecular datasets remains a formidable task. In this paper, we delve into the intricate entry-wise modules in vanilla flows, introducing an effective variation of flow-based models. Our proposed approach innovatively encapsulates affine coupling transformations within normalizing flows. Furthermore, we deconstruct existing invertible flow models, integrating them with newly developed entry-wise transformations. Our experimental studies demonstrate that these proposed entry-wise modules, when incorporated into standard flow-based models, surpass other generative models in performance on various representative datasets and generation tasks. Notably, in the context of low-resourced molecular graph generation, our model achieves remarkable performance compared to its counterparts. © 2024 IEEE.

关键词： Complex networks

来源：评论

学校读者我要写书评

暂无评论

BIG-MOE: BYPASS ISOLATED GATING MOE FOR GENERALIZED MULTIMODAL FACE ANTI-SPOOFING

arXiv

引用

arXiv 2024年

作者： Ma, Yingjie Yu, Zitong Lin, Xun Xie, Weicheng Shen, Linlin Great Bay University China College of Computer Science and Software Engineering Shenzhen University China National Engineering Laboratory for Big Data System Computing Technology Shenzhen University China Guangdong Provincial Key Laboratory of Intelligent Information Processing China

In the domain of facial recognition security, multimodal Face Anti-Spoofing (FAS) is essential for countering presentation attacks. However, existing technologies encounter challenges due to modality biases and imbalances, as well as domain shifts. Our research introduces a Mixture of Experts (MoE) model to address these issues effectively. We identified three limitations in traditional MoE approaches to multimodal FAS: (1) Coarse-grained experts’ inability to capture nuanced spoofing indicators;(2) Gated networks’ susceptibility to input noise affecting decision-making;(3) MoE’s sensitivity to prompt tokens leading to overfitting with conventional learning methods. To mitigate these, we propose the Bypass Isolated Gating MoE (BIG-MoE) framework, featuring: (1) Fine-grained experts for enhanced detection of subtle spoofing cues;(2) An isolation gating mechanism to counteract input noise;(3) A novel differential convolutional prompt bypass enriching the gating network with critical local features, thereby improving perceptual capabilities. Extensive experiments on four benchmark datasets demonstrate significant generalization performance improvement in multimodal FAS task. The code is released at https://***/murInJ/BIGMoE. Copyright © 2024, The Authors. All rights reserved.

关键词： HTTP

来源：评论

学校读者我要写书评

暂无评论

On the Noise Robustness of In-Context Learning for Text Generation 38

On the Noise Robustness of In-Context Learning for Text Gene...

引用

38th Conference on Neural Information Processing systems, NeurIPS 2024

作者： Gao, Hongfu Zhang, Feipeng Jiang, Wenyu Shu, Jun Zheng, Feng Wei, Hongxin Department of Statistics and Data Science Southern University of Science and Technology China School of Economics and Finance Xi'an Jiaotong University China National Key Laboratory for Novel Software Technology Nanjing University China School of Mathematics and Statistics Xi'an Jiaotong University China Department of Computer Science and Engineering Southern University of Science and Technology China

Large language models (LLMs) have shown impressive performance on downstream tasks by in-context learning (ICL), which heavily relies on the quality of demonstrations selected from a large set of annotated examples. Recent works claim that in-context learning is robust to noisy demonstrations in text classification. In this work, we show that, on text generation tasks, noisy annotations significantly hurt the performance of in-context learning. To circumvent the issue, we propose a simple and effective approach called Local Perplexity Ranking (LPR), which replaces the "noisy" candidates with their nearest neighbors that are more likely to be clean. Our method is motivated by analyzing the perplexity deviation caused by noisy labels and decomposing perplexity into inherent perplexity and matching perplexity. Our key idea behind LPR is thus to decouple the matching perplexity by performing the ranking among the neighbors in semantic space. Our approach can prevent the selected demonstrations from including mismatched input-label pairs while preserving the effectiveness of the original selection methods. Extensive experiments demonstrate the effectiveness of LPR, improving the EM score by up to 18.75 on common benchmarks with noisy annotations. Our code is available at https://***/ml-stat-Sustech/Local-Perplexity-Ranking. © 2024 Neural information processing systems foundation. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Super-resolution GANs for upscaling unplanned urban settlements from remote sensing satellite imagery - the case of Chinese urban village detection

引用

International Journal of Digital Earth 2023年第1期16卷 2623-2643页

作者： Alessandro Crivellari Hong Wei Chunzhu Wei Yuhui Shi Department of Computer Science and Engineering SouthernUniversity of Science and TechnologyShenzhenPeople’s Republic of China Ministry of Education Ecological Field Station for East Asian Migratory Birds Department of Earth System ScienceInstitute for Global Change StudiesTsinghua UniversityBeijingPeople’s Republic of China School of Geography and Planning Sun Yat-sen UniversityGuangzhouPeople’s Republic of China Southern Marine Science and Engineering Guangdong Laboratory(Zhuhai) ZhuhaiPeople’s Republic of China

The semantic segmentation of informal urban settlements represents an essential contribution towards renovation strategies and reconstruction *** this context,however,a big challenge remains unsolved when dealing with incomplete data acquisitions from multiple sensing devices,especially when study areas are depicted by images of different *** practice,traditional methodologies are directed to downgrade the higher-resolution data to the lowest-resolution measure,to define an overall homogeneous dataset,which is however ineffective in downstream segmentation activities of such crowded unplanned urban *** this purpose,we hereby tackle the problem in the opposite direction,namely upscaling the lower-resolution data to the highest-resolution measure,contributing to assess the use of cutting-edge super-resolution generative adversarial network(SR-GAN)*** experimental novelty targets the particular case involving the automatic detection of‘urban villages’,sign of the quick transformation of Chinese urban *** aligning image resolutions from two different data sources(Gaofen-2 and Sentinel-2 data),we evaluated the degree of improvement with regard to pixel-based landcover segmentation,achieving,on a 1 m resolution target,classification accuracies up to 83%,67%and 56%for 4x,8x,and 10x resolution upgrades respectively,disclosing the advantages of artificially-upscaled images for segmenting detailed characteristics of informal settlements.

关键词： SR-GAN resolution upscaling informal settlements urban villages cross-sensor analytics

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：