检索结果-内蒙古大学图书馆

arXiv 2023年

作者： Wu, Xiao-Ming Zheng, Dian Liu, Zuhao Zheng, Wei-Shi School of Computer Science and Engineering Sun Yat-sen University China Pengcheng Lab China Guangdong Province Key Laboratory of Information Security Technology China Key Laboratory of Machine Intelligence and Advanced Computing Ministry of Education China

Binarization of neural networks is a dominant paradigm in neural networks compression. The pioneering work BinaryConnect uses Straight Through Estimator (STE) to mimic the gradients of the sign function, but it also causes the crucial inconsistency problem. Most of the previous methods design different estimators instead of STE to mitigate it. However, they ignore the fact that when reducing the estimating error, the gradient stability will decrease concomitantly. These highly divergent gradients will harm the model training and increase the risk of gradient vanishing and gradient exploding. To fully take the gradient stability into consideration, we present a new perspective to the BNNs training, regarding it as the equilibrium between the estimating error and the gradient stability. In this view, we firstly design two indicators to quantitatively demonstrate the equilibrium phenomenon. In addition, in order to balance the estimating error and the gradient stability well, we revise the original straight through estimator and propose a power function based estimator, Rectified Straight Through Estimator (ReSTE for short). Comparing to other estimators, ReSTE is rational and capable of flexibly balancing the estimating error with the gradient stability. Extensive experiments on CIFAR-10 and ImageNet datasets show that ReSTE has excellent performance and surpasses the state-of-the-art methods without any auxiliary modules or losses. Copyright © 2023, The Authors. All rights reserved.

关键词： Stability

来源：评论

学校读者我要写书评

暂无评论

Estimator Meets Equilibrium Perspective: A Rectified Straight Through Estimator for Binary Neural Networks Training

Estimator Meets Equilibrium Perspective: A Rectified Straigh...

引用

International Conference on computer Vision (ICCV)

作者： Xiao-Ming Wu Dian Zheng Zuhao Liu Wei-Shi Zheng School of Computer Science and Engineering Sun Yat-sen University China Pengcheng Lab China Guangdong Province Key Laboratory of Information Security Technology China Key Laboratory of Machine Intelligence and Advanced Computing Ministry of Education China

关键词：

来源：评论

学校读者我要写书评

暂无评论

ASAG: Building Strong One-Decoder-Layer Sparse Detectors via Adaptive Sparse Anchor Generation

ASAG: Building Strong One-Decoder-Layer Sparse Detectors via...

引用

International Conference on computer Vision (ICCV)

作者： Shenghao Fu Junkai Yan Yipeng Gao Xiaohua Xie Wei-Shi Zheng School of Computer Science and Engineering Sun Yat-sen University China Guangdong Province Key Laboratory of Information Security Technology China Key Laboratory of Machine Intelligence and Advanced Computing Ministry of Education China Pengcheng Lab China

Recent sparse detectors with multiple, e.g. six, decoder layers achieve promising performance but much inference time due to complex heads. Previous works have explored using dense priors as initialization and built one-decoder-layer detectors. Although they gain remarkable acceleration, their performance still lags behind their six-decoder-layer counterparts by a large margin. In this work, we aim to bridge this performance gap while retaining fast speed. We find that the architecture discrepancy between dense and sparse detectors leads to feature conflict, hampering the performance of one-decoder-layer detectors. Thus we propose Adaptive Sparse Anchor Generator (ASAG) which predicts dynamic anchors on patches rather than grids in a sparse way so that it alleviates the feature conflict problem. For each image, ASAG dynamically selects which feature maps and which locations to predict, forming a fully adaptive way to generate image-specific anchors. Further, a simple and effective Query Weighting method eases the training instability from adaptiveness. Extensive experiments show that our method outperforms dense-initialized ones and achieves a better speed-accuracy trade-off. The code is available at https://***/iSEE-laboratory/ASAG.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Dual-View Pyramid Pooling in Deep Neural Networks for Improved Medical Image Classification and Confidence Calibration

arXiv

引用

arXiv 2024年

作者： Zhang, Xiaoqing Nie, Qiushi Xiao, Zunjie Zhao, Jilu Wu, Xiao Guo, Pengxin Li, Runzhi Liu, Jin Wei, Yanjie Pan, Yi Center for High Performance Computing Shenzhen Key Laboratory of Intelligent Bioinformatics Shenzhen Institute of Advanced Technology Chinese Academy of Sciences Guangdong Shenzhen518055 China Department of Computer Science and Engineering Southern University of Science and Technology Shenzhen518055 China Department of Statistics and Actuarial Science The University of Hong Kong 999077 Hong Kong Cooperative Innovation Center of Internet Healthcare Zhengzhou University Zhengzhou450001 China Hunan Provincial Key Lab on Bioinformatics School of Computer Science and Engineering Central South University Changsha410083 China Xinjiang Engineering Research Center of Big Data and Intelligent Software School of software Xinjiang University Wulumuqi830046 China Faculty of Computer Science and Control Engineering Shenzhen University of Advanced Technology Shenzhen China

Spatial pooling (SP) and cross-channel pooling (CCP) operators have been applied to aggregate spatial features and pixel-wise features from feature maps in deep neural networks (DNNs), respectively. Their main goal is to reduce computation and memory overhead without visibly weakening the performance of DNNs. However, SP often faces the problem of losing the subtle feature representations, while CCP has a high possibility of ignoring salient feature representations, which may lead to both miscalibration of confidence issues and suboptimal medical classification results. To address these problems, we propose a novel dual-view framework, the first to systematically investigate the relative roles of SP and CCP by analyzing the difference between spatial features and pixel-wise features. Based on this framework, we propose a new pooling method, termed dual-view pyramid pooling (DVPP), to aggregate multi-scale dual-view features. DVPP aims to boost both medical image classification and confidence calibration performance by fully leveraging the merits of SP and CCP operators from a dual-axis perspective. Additionally, we discuss how to fulfill DVPP with five parameter-free implementations. Extensive experiments on six 2D/3D medical image classification tasks show that our DVPP surpasses state-of-the-art pooling methods in terms of medical image classification results and confidence calibration across different DNNs. © 2024, CC BY.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Knowledge-Aware Design of High-Strength Aviation Aluminum Alloys Via Machine Learning

SSRN

引用

SSRN 2023年

作者： Yong-Fei, Juan Guo-Shuai, Niu Yang, Yang Yong-Bing, Dai Jiao, Zhang Yan-Feng, Han Bao-De, Sun Shanghai Key Lab of Advanced High-temperature Materials and Precision Forming State Key Lab of Metal Matrix Composites School of Materials Science and Engineering Shanghai Jiao Tong University Shanghai200240 China Department of Computer Science and Engineering Shanghai Jiao Tong University Shanghai200240 China Collaborative Innovation Center for Advanced Ship and Deep-sea Exploration Shanghai Jiao Tong University Shanghai200240 China

The development of the aviation industry is accompanied by the continuous research of high-performance aviation aluminum alloys. Stuck in vast untapped composition space and the routine trial-and-error method, efficiently discovering high-strength aluminum alloys remains a significant challenge. To address this issue, we proposed a knowledge-aware design system (KADS) using machine learning (ML) methods to facilitate the rational design of high-strength aviation aluminum alloys. An aviation aluminum alloy database containing 5113 samples was built based on Al-Zn-Mg-Cu, Al-Cu, and Al-Li series aluminum alloys. Notably, guided by the material knowledge, we constructed a feature pool (23 descriptors) to improve the interpretability and accuracy of ML models. Taking key knowledge-aware features as input, we realized the transformation from "element content to property" to "material knowledge to property" in ML modeling, which is the first time proposed in aviation aluminum alloys design. According to the predictive results, we experimentally fabricated a KADS-designed aluminum alloy (KADS-Sc) with superior mechanical strength (812 MPa for ultimate tensile strength and 792 MPa for yield strength). Furthermore, the strengthening mechanisms in KADS-Sc alloy were established quantitatively. The calculations confirmed that the precipitation strengthening ( 439 MPa) was most critical in the final strength increment, agreeing with the microstructure analysis. © 2023, The Authors. All rights reserved.

关键词： Aluminum alloys

来源：评论

学校读者我要写书评

暂无评论

PROV-IO+: A Cross-Platform Provenance Framework for Scientific Data on HPC Systems

arXiv

引用

arXiv 2023年

作者： Han, Runzhou Zheng, Mai Byna, Suren Tang, Houjun Dong, Bin Dai, Dong Chen, Yong Kim, Dongkyun Hassoun, Joseph Thorsley, David Wolf, Matthew Department of Electrical and Computer Engineering Iowa State University United States Department of Computer Science and Engineering The Ohio State University United States Scientific Data Management Group Lawrence Berkeley National Laboratory United States Computer Science Department University of North Carolina Charlotte United States Systems Architecture Lab Samsung United States Samsung Advanced Institute of Technology Samsung Korea Republic of

Data provenance, or data lineage, describes the life cycle of data. In scientific workflows on HPC systems, scientists often seek diverse provenance (e.g., origins of data products, usage patterns of datasets). Unfortunately, existing provenance solutions cannot address the challenges due to their incompatible provenance models and/or system implementations. In this paper, we analyze four representative scientific workflows in collaboration with the domain scientists to identify concrete provenance needs. Based on the first-hand analysis, we propose a provenance framework called PROV-IO+, which includes an I/O-centric provenance model for describing scientific data and the associated I/O operations and environments precisely. Moreover, we build a prototype of PROV-IO+ to enable end-to-end provenance support on real HPC systems with little manual effort. The PROV-IO+ framework can support both containerized and non-containerized workflows on different HPC platforms with flexibility in selecting various classes of provenance. Our experiments with realistic workflows show that PROV-IO+ can address the provenance needs of the domain scientists effectively with reasonable performance (e.g., less than 3.5% tracking overhead for most experiments). Moreover, PROV-IO+ outperforms a state-of-the-art system (i.e., ProvLake) in our experiments. © 2023, CC BY-NC-SA.

关键词： Life cycle

来源：评论

学校读者我要写书评

暂无评论

Optimizing execution for pipelined-based distributed deep learning in a heterogeneously networked GPU cluster

Optimizing execution for pipelined-based distributed deep le...

引用

作者： Zhang, Jinghui Zhan, Jun Li, Jiange Jin, Jiahui Qian, Lei School of Computer Science and Engineering Southeast University Nanjing China State Key Lab of Mathematical Engineering and Advanced Computing Wuxi China

Exorbitant resources (computing and memory) are required to train a deep neural network (DNN). Often researchers deploy an approach that uses distributed parallel training to acquire larger models faster on GPUs. This approach has its detriments, though;on one hand, a GPU's expanded capacity to compute also produces bigger bottlenecks in inter-GPU's communications during model training, and multi-GPU systems lead to complex connectivity. Workload schedulers then end up having to consider hardware topology and requirements for workload communication, in hopes of allocating GPU resources to optimize execution time and improve usage in a heterogeneous environment. On the other hand, the high memory requirements to train a DNN model make running the training processes on GPUs onerous. To contend with this, we introduce two execution optimization methods based on pipeline-hybrid parallelism (using both data and model parallelism) in a GPU cluster with heterogeneous networking. First, we propose a model partition algorithm that accelerates pipeline-hybrid parallelism training between heterogeneously network-connected GPUs. Second, we introduce a cost-balanced recomputing algorithm to reduce memory usage in the pipeline mode. Experiments show that our solution (Pipe-Torch) averages a speedup of 1.4× compared with data parallelism, and reduces the memory footprint while maintaining pipelined load-balanced training. © 2020 John Wiley & Sons Ltd

关键词： Pipelines

来源：评论

学校读者我要写书评

暂无评论

Short-Term Time Series State of Charge Prediction in Electric Vehicle LGM50 Batteries: A Rolling Forecasting Approach

Short-Term Time Series State of Charge Prediction in Electri...

引用

International Conference on Sensing Technology, ICST

作者： Zeyang Zhou Angelo Greco Fenix Huang Karthick Thiyagarajan Jun Li Mukesh Prasad Faulty of Engineering and Information Technology School of Computer Science University of Technology Sydney Australia Clarios Varta Hannover GmbH Hannover Germany KERF Technology Limited Taipei Taiwan Smart Sensing and Robotics Laboratory (SensR Lab) Centre for Advanced Manufacturing Technology School of Engineering Design and Built Environment Western Sydney University Penrith NSW Australia

ISBN: (数字)9798350374827

ISBN: (纸本)9798350374834

The prediction of the state of charge (SOC) for battery management systems has become increasingly important with the rapid growth of the electric vehicle industry. Traditional methods for SOC prediction often depend on extensive historical data from vehicles, which can be unreliable due to various uncontrollable factors such as driving behavior, weather, and road conditions. To overcome these limitations, we propose a rolling forecasting model that leverages month-by-month data from electric vehicles to predict the SOC for the subsequent month. This approach to short-term SOC prediction aims to enhance intelligent mechatronic monitoring systems, enabling the delivery of personalized driving and charging strategies to customers.

关键词： Mechatronics Roads Time series analysis Battery management systems Predictive models Electric vehicles State of charge Forecasting Monitoring Meteorology

来源：评论

学校读者我要写书评

暂无评论

A vision based voice controlled indoor assistant robot for visually impaired people

A vision based voice controlled indoor assistant robot for v...

引用

2020 IEEE International IOT, Electronics and Mechatronics Conference, IEMTRONICS 2020

作者： Mahmud, Saifuddin Haque Sourave, Redwanul Islam, Milon Lin, Xiangxu Kim, Jong-Hoon Kent State University Advanced Telerobotics Research Lab Computer Science KentOH United States Khulna University of Engineering Technology Computer Science and Engineering Khulna Bangladesh

ISBN: (数字)9781728196152

ISBN: (纸本)9781728196152

Due to ever-increasing number of visually impaired people, the demands of assistant robots have been growing significantly. For the visually impaired, "independent living"which is the key to rebuild the dignity and self-confidence that can be achieved by assistant robot. This paper describes the design and development of a personal assistant robot, which is controlled by voice commands to find and determine the relative location of the object in the indoor environment with a corelation factor (CRF) algorithm developed in this study. The proposed assistant robot is a semi-humanoid robot consists of several cameras on the different location of its body. The cameras are used for autonomous movement, object detection, distance measurement, and motion planning. In addition, the robot keeps the user informed about the outcomes of its actions increases the usefulness of the robot. To justify the proposed system and measure its performance, successful experiments were conducted in indoor environments. The experimental results demonstrate that the proposed assistant robot performs all of its actions with high accuracy which will make visually impaired people feel the indoor environment safe, convenient and comfortable. © 2020 IEEE.

关键词： Anthropomorphic robots

来源：评论

学校读者我要写书评

暂无评论

Data-consistent Unsupervised Diffusion Model for Metal Artifact Reduction

Data-consistent Unsupervised Diffusion Model for Metal Artif...

引用

2023 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2023

作者： Tong, Zhan Wu, Zhan Yang, Yang Mao, Weilong Wang, Shijie Li, Yinsheng Chen, Yang Southeast University Laboratory of Image Science and Technology Nanjing210096 China Southeast University Ministry of Education Key Laboratory of Computer Network and Information Integration Nanjing210096 China Chinese Academy of Sciences Research Center for Medical Artificial Intelligence Shenzhen Institutes of Advanced Technology Shenzhen518055 China School of Computer Science and Engineering Key Lab. of New Generation Artificial Intelligence Technology and Its Interdisciplinary Applications Jiangsu Provincial Joint International Research Laboratory of Medical Information Processing The Laboratory of Image Science and Technology Nanjing210096 China

ISBN: (纸本)9798350337488

Computed Tomography (CT) is an imaging technique widely used in clinical diagnosis. However, high-attenuation metallic implants result in the obstruction of low-energy Xrays and further lead to metal artifacts in the reconstructed CT images. Deep supervised model-based metal artifact reduction(MAR) approaches are limited in clinical applications due to the difficulty in obtaining paired artifact-affected and artifactfree data. Furthermore, these model-based methods lack the consideration of data consistency in the sinogram-domain to perform exact metal trace inpainting. To address these challenges, we propose a Data-consistent unsupErVised diffusiOn model for meTal artifact rEDuction, called DEVOTED-Net. First, DEVOTED-Net leverages prior knowledge to guide the conditional diffusion model for fine-grained metal trace inpainting. Second, an unsupervised MAR framework is designed in the reverse process for the unknown metal traces restoration in the sinogram domain. Third, to further enhance the sinogram-domain data consistency, physics-based consistency constraint loss including conjugateray consistency loss and accumulation-ray consistency loss is designed. Extensive experiments are carried out to verify the performance of our algorithm on the publicly available dataset and clinical experimental dataset. This efficient, accurate, and reliable MAR approach holds great potential in clinics. © 2023 IEEE.

关键词： computed tomography deep unsupervised learning denoising diffusion probabilistic model Metal artifact reduction physics-based consistency constraint

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：