检索结果-内蒙古大学图书馆

38th Conference on Neural Information Processing Systems, NeurIPS 2024

作者： Zhang, Haoran Deng, Junkai Chen, Xuhui Hou, Fei Wang, Wencheng Qin, Hong Qian, Chen He, Ying State Key Laboratory of Computer Science Institute of Software Chinese Academy of Sciences China University of Chinese Academy of Sciences China College of Computing and Data Science Nanyang Technological University Singapore Department of Computer Science Stony Brook University United States SenseTime Research Hong Kong

Traditional 3D shape reconstruction techniques from multi-view images, such as structure from motion and multi-view stereo, face challenges in reconstructing transparent objects. Recent advances in neural radiance fields and its variants primarily address opaque or transparent objects, encountering difficulties to reconstruct both transparent and opaque objects simultaneously. This paper introduces α-NeuS-an extension of NeuS-that proves NeuS is unbiased for materials from fully transparent to fully opaque. We find that transparent and opaque surfaces align with the non-negative local minima and the zero iso-surface, respectively, in the learned distance field of NeuS. Traditional iso-surfacing extraction algorithms, such as marching cubes, which rely on fixed iso-values, are ill-suited for such data. We develop a method to extract the transparent and opaque surface simultaneously based on DCUDF. To validate our approach, we construct a benchmark that includes both real-world and synthetic scenes, demonstrating its practical utility and effectiveness. Our data and code are publicly available at https://***/728388808/alpha-NeuS. © 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

FL@FM-TheWebConf’24: International Workshop on Federated Foundation Models for the Web 24

FL@FM-TheWebConf’24: International Workshop on Federated Fo...

引用

33rd Companion of the ACM World Wide Web Conference, WWW 2023

作者： King, Irwin Long, Guodong Xu, Zenglin Yu, Han Department of Computer Science and Engineering The Chinese University of Hong Kong Hong Kong Hong Kong Faculty of Engineering and IT University of Technology Sydney Australia School of Computer Science and Technology Harbin Institute of Technology Shenzhen China College of Computing and Data Science Nanyang Technological University Singapore Singapore

ISBN: (纸本)9798400701726

In the evolving landscape of machine learning research, two significant developments have emerged to prominence: foundation models and federated learning. The FL@FM-TheWebConf’24 workshop provides an exciting forum for researchers and practitioners to discuss promising works and chart potential trajectories forward for this emerging field. © 2024 Copyright held by the owner/author(s). Publication rights licensed to ACM.

关键词： Frequency modulation

来源：评论

学校读者我要写书评

暂无评论

Efficient GPU Offloading with OpenMP for a Hyperbolic Finite Volume Solver on Dynamically Adaptive Meshes 38th

Efficient GPU Offloading with OpenMP for a Hyperbolic Fin...

引用

38th International Conference on High Performance computing, ISC High Performance 2023

作者： Wille, Mario Weinzierl, Tobias Brito Gadeschi, Gonzalo Bader, Michael TUM School of Computation Information and Technology Technical University of Munich Garching Germany Department of Computer Science Institute for Data Science—Large-scale Computing Durham University Durham United Kingdom NVIDIA Munich Germany

ISBN: (纸本)9783031320408

We identify and show how to overcome an OpenMP bottleneck in the administration of GPU memory. It arises for a wave equation solver on dynamically adaptive block-structured Cartesian meshes, which keeps all CPU threads busy and allows all of them to offload sets of patches to the GPU. Our studies show that multithreaded, concurrent, non-deterministic access to the GPU leads to performance breakdowns, since the GPU memory bookkeeping as offered through OpenMP’s map clause, i.e., the allocation and freeing, becomes another runtime challenge besides expensive data transfer and actual computation. We, therefore, propose to retain the memory management responsibility on the host: A caching mechanism acquires memory on the accelerator for all CPU threads, keeps hold of this memory and hands it out to the offloading threads upon demand. We show that this user-managed, CPU-based memory administration helps us to overcome the GPU memory bookkeeping bottleneck and speeds up the time-to-solution of Finite Volume kernels by more than an order of magnitude. © 2023, The Author(s).

关键词： Graphics processing unit

来源：评论

学校读者我要写书评

暂无评论

Analysis on n-level quantum systems by means of a coordinate transformation 63

Analysis on n-level quantum systems by means of a coordinate...

引用

63rd IEEE Conference on Decision and Control, CDC 2024

作者： Xu, Huilong Miao, Zibo Gao, Qing Harbin Institute of Technology School of Mechanical Engineering and Automation Shenzhen518055 China Beijing Advanced Innovation Center for Big Data and Brain Computing Beihang University School of Automation Science and Electrical Engineering Beijing100191 China

ISBN: (纸本)9798350316339

The structural decomposition of two-level quantum systems has recently been established, related to various applications in quantum information science. As an extension to previous work on two-level quantum systems, this paper aims to investigate the structural properties of n-level quantum systems. We develop algebraic conditions under which the attainment of quantum back-action evading (BAE) measurements, the generation of decoherence-free (DF) subspaces and quantum non-demolition (QND) variables, as well as the existence of steadystate solutions for the Lindblad equations, can be realized. In particular, a specific coordinate transformation is explicitly constructed to facilitate the achievement of above-mentioned objectives, accompanied by an illustrative numerical example. © 2024 IEEE.

关键词： Quantum optics

来源：评论

学校读者我要写书评

暂无评论

Leveraging Deep Learning Models for Machine-Generated Text Detection Using Transformer-Based Models

Leveraging Deep Learning Models for Machine-Generated Text D...

引用

2024 International Conference on Innovative computing, Intelligent Communication and Smart Electrical Systems, ICSES 2024

作者： Suthanthiradevi, P. Revathy, G. Rejini, K. Muthu Lakshmi, V. School of Computing Srm institute of Science and Technology Department of Data Science and Business Systems Kattankulathur Chennai India Vels Institute of science Technology and Advanced studies Department of Computer science and engineering Chennai117 India Amrita college of Engineering and Technology Department of Computer Science Engineering Nagercoil India St. Joseph's College of Engineering Department of Computer Science and Engineering OMR Chennai India

ISBN: (纸本)9798331543617

GPT is a large language model (LLM) derived from natural language processing that can generate a human-like text using machine learning. However, these models raise questions about authenticity and reliability of material, particularly in fields such as journalism, social media, and academia, despite their usefulness for automating text-based tasks. Detecting machine-generated text is thus an important difficulty in ensuring content integrity. This study investigates the use of huge language models as a technique for recognizing machine-generated material. The author proposes a comprehensive detection model by evaluating the language patterns, syntactic structures, and stylistic traits that separate AI-generated literature from human writing. In addition, this research investigate the possibilities of fine-tuning models designed expressly for text identification tasks and evaluate their performance using LLM - Detect AI Generated Text datasets. In digital ecosystems, LLMs are effective at detecting AI-generated text, providing a novel approach for content moderation, academic integrity checks, and synthetic media detection. An increasingly AI-powered future will require a model that can discriminate between human and machine-generated writing in real-time. According to experimental findings, the CNN architecture's design combined with the use of DistilBERT embeddings allows for the effective and efficient classification of AI generated text data, achieving an exceptional 98% accuracy rate. © 2024 IEEE.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

ICPR 2024 Competition on Beyond Visible Spectrum: AI for Agriculture 27th

ICPR 2024 Competition on Beyond Visible Spectrum: AI for A...

引用

27th International Conference on Pattern Recognition, ICPR 2024

作者： Han, Liangxiu Huang, Wenjiang Zhang, Xin Dong, Yingying Sobeih, Tam Lin, Yufan Department of Computing and Mathematics Manchester Metropolitan University ManchesterM15 6BH United Kingdom Key laboratory of Digital Earth Science Aerospace Information Research Institute Chinese Academy of Sciences Beijing100094 China Institute of Data Science National Cheng Kung University Taiwan70101 China

ISBN: (纸本)9783031801389

The ICPR 2024 Competition on "Beyond Visible Spectrum: AI for Agriculture" presents an exciting opportunity for researchers and practitioners to advance computer vision techniques in agricultural crop disease monitoring. By leveraging the vast multi/hyper spectral remote sensing datasets, participants are encouraged to develop innovative machines/deep learning algorithms. The primary objective is to improve the accuracy and efficiency of crop disease identification, thereby fostering sustainable agricultural practices and facilitating global knowledge generation for enhanced food security. This challenge presents participants with the opportunity to make significant contributions to the advancement of precision farming and crop monitoring techniques. By improving the machines/deep learning models, the competition aims to drive forward the capabilities of agricultural technology, making it more efficient, accurate, and sustainable. A total of 190 people from more than 10 countries in Europe, Asia and North America entered the competition by the deadline date, with a total of 126 submissions of results. The rank1 team obtained an accuracy of 73.3% in crop disease classification task with hyperspectral dataset. In the self-supervised learning task, the rank1 team obtained 79.2% accuracy. We report the leader-boards of the competition in this report and present three innovative approaches of the participants. The ICPR 2024 Competition on "Beyond Visible Spectrum" is not just a competition;it is a call to action for the computer research community to bring about transformative changes in how agricultural data is analyze and utilized, paving the way for smarter, more sustainable farming practices that can benefit communities worldwide. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Self-supervised learning

来源：评论

学校读者我要写书评

暂无评论

Augmentation-Aware Self-Supervision for data-Efficient GAN Training 37

Augmentation-Aware Self-Supervision for Data-Efficient GAN T...

引用

37th Conference on Neural Information Processing Systems, NeurIPS 2023

作者： Hou, Liang Cao, Qi Yuan, Yige Zhao, Songtao Ma, Chongyang Pan, Siyuan Wan, Pengfei Wang, Zhongyuan Shen, Huawei Cheng, Xueqi CAS Key Laboratory of AI Safety and Security Institute of Computing Technology Chinese Academy of Sciences China CAS Key Laboratory of Network Data Science and Technology Institute of Computing Technology Chinese Academy of Sciences China University of Chinese Academy of Sciences China Kuaishou Technology China

ISBN: (纸本)9781713899921

Training generative adversarial networks (GANs) with limited data is challenging because the discriminator is prone to overfitting. Previously proposed differentiable augmentation demonstrates improved data efficiency of training GANs. However, the augmentation implicitly introduces undesired invariance to augmentation for the discriminator since it ignores the change of semantics in the label space caused by data transformation, which may limit the representation learning ability of the discriminator and ultimately affect the generative modeling performance of the generator. To mitigate the negative impact of invariance while inheriting the benefits of data augmentation, we propose a novel augmentation-aware self-supervised discriminator that predicts the augmentation parameter of the augmented data. Particularly, the prediction targets of real data and generated data are required to be distinguished since they are different during training. We further encourage the generator to adversarially learn from the self-supervised discriminator by generating augmentation-predictable real and not fake data. This formulation connects the learning objective of the generator and the arithmetic - harmonic mean divergence under certain assumptions. We compare our method with state-of-the-art (SOTA) methods using the class-conditional BigGAN and unconditional StyleGAN2 architectures on data-limited CIFAR-10, CIFAR-100, FFHQ, LSUN-Cat, and five low-shot datasets. Experimental results demonstrate significant improvements of our method over SOTA methods in training data-efficient GANs. © 2023 Neural information processing systems foundation. All rights reserved.

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

Using Simulated data to Predict Birthweight from Prenatal Ultrasound Images

Using Simulated Data to Predict Birthweight from Prenatal Ul...

引用

2023 IEEE Western New York Image and Signal Processing Workshop, WNYISPW 2023

作者： Dreisbach, Caitlin Karunanidhi, Arunaggiri Pandian Shimazaki, Yuka Rana, Neha Thornburg, Loralei Wang, Linwei Groth, Susan Hollenbach, Stefanie University of Rochester School of Nursing and Goergen Institute for Data Science RochesterNY United States University of Rochester Goergen Institute for Data Science RochesterNY United States University of Rochester Medcical Center RochesterNY United States Rochester Institute of Technology Department of Computing and Information Science RochesterNY United States Unviersity of Rochester School of Nursing RochesterNY United States

ISBN: (纸本)9798350329698

Fetal weight estimation during pregnancy is critical for monitoring growth and planning delivery, yet current ultrasound-based estimations are prone to error. This study leveraged open access ultrasound images and simulated clinical data to develop a deep learning pipeline for fetal weight prediction. The dataset consisted of n=1,570 ultrasound images from 333 pregnant individuals at 18-40 weeks' gestation. Relevant maternal and fetal attributes like body mass index, gestational age, amniotic fluid index, and newborn birth weight were simulated based on population averages. A convolutional neural network (CNN) using transfer learning was applied to extract imaging features. The pre-Trained Xception model was adapted by adding a global average pooling layer and freezing layers during feature extraction. Extracted imaging features were combined with clinical metadata and input into linear regression and random forest models. Hyperparameter tuning via randomized search identified a random forest configuration minimizing error. On a 20% test set, the pipeline achieved a mean absolute error of 328.6 grams in predicting birth weight, suggesting feasibility of the approach. While clinical conclusions are limited without real-world data, this study demonstrates a pipeline leveraging open science resources to address an important maternal-fetal health problem. Tailored CNN architectures and further model optimization on population-representative data could enhance performance and clinical utility. This work highlights the potential of open datasets to enable rapid scientific progress and proposes a deep learning methodology for improved fetal weight assessment during pregnancy. © 2023 IEEE.

关键词： Ultrasonics

来源：评论

学校读者我要写书评

暂无评论

Forte: An Interactive Visual Analytic Tool for Trust-Augmented Net Load Forecasting

Forte: An Interactive Visual Analytic Tool for Trust-Augment...

引用

2024 IEEE Power and Energy Society Innovative Smart Grid Technologies Conference, ISGT 2024

作者： Bhattacharjee, Kaustav Kundu, Soumya Chakraborty, Indrasis Dasgupta, Aritra New Jersey Institute of Technology Department of Data Science United States Pacific Northwest National Laboratory Optimization and Control Group United States Lawrence Livermore National Laboratory Center for Applied Scientific Computing United States

ISBN: (纸本)9798350313604

Accurate net load forecasting is vital for energy planning, aiding decisions on trade and load distribution. However, assessing the performance of forecasting models across diverse input variables, like temperature and humidity, remains challenging, particularly for eliciting a high degree of trust in the model outcomes. In this context, there is a growing need for data-driven technological interventions to aid scientists in comprehending how models react to both noisy and clean input variables, thus shedding light on complex behaviors and fostering confidence in the outcomes. In this paper, we present Forte, a visual analytics-based application to explore deep probabilistic net load forecasting models across various input variables and understand the error rates for different scenarios. With carefully designed visual interventions, this web-based interface empowers scientists to derive insights about model performance by simulating diverse scenarios, facilitating an informed decision-making process. We discuss observations made using Forte and demonstrate the effectiveness of visualization techniques to provide valuable insights into the correlation between weather inputs and net load forecasts, ultimately advancing grid capabilities by improving trust in forecasting models. © 2024 IEEE.

关键词： Decision making

来源：评论

学校读者我要写书评

暂无评论

Deep learning at the service of metaheuristics for solving numerical optimization problems

引用

Neural computing and Applications 2025年 1-36页

作者： Oyelade, Olaide N. Ezugwu, Absalom E. Saha, Apu K. Thieu, Nguyen V. Gandomi, Amir H. School of Electronics Electrical Engineering and Computer Science Queen’s University Belfast Bangladesh Unit for Data Science and Computing North-West University 11 Hoffman Street Potchefstroom2520 United States Department of Mathematics National Institute of Technology Agartala Tripura Agartala799046 India Faculty of Computer Science Phenikaa University Yen Nghia Hanoi Ha Dong12116 Viet Nam Department of Engineering and Information Technology University of Technology Sydney UltimoNSW2007 Australia

Integrating deep learning methods into metaheuristic algorithms has gained attention for addressing design-related issues and enhancing performance. The primary objective is to improve solution quality and convergence speed within solution search spaces. This study investigates the use of deep learning methods as a generative model to learn historical content, including global best and worst solutions, solution sequences, function evaluation patterns, solution space characteristics, population modification trajectories, and movement between local and global search processes. An LSTM-based architecture is trained on dynamic optimization data collected during the metaheuristic optimization process. The trained model generates an initial solution space and is integrated into the optimization algorithms to intelligently monitor the search process during exploration and exploitation phases. The proposed deep learning-based methods are evaluated on 55 benchmark functions of varying complexities, including CEC 2017 and compared with 13 biology-based, evolution-based, and swarm-based metaheuristic algorithms. Experimental results demonstrate that all the deep learning-based optimization algorithms achieve high-quality solutions, faster convergence rates, and significant performance improvements. These findings highlight the critical role of deep learning in addressing design issues, enhancing solution quality, trajectory, and performance speed in metaheuristic algorithms. © The Author(s) 2025.

关键词： Contrastive Learning

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：