检索结果-内蒙古大学图书馆

2023 Conference on Empirical Methods in Natural Language Processing, EMNLP 2023

作者： Cao, Tingfeng Wang, Chengyu Liu, Bingyan Wu, Ziheng Zhu, Jinhui Huang, Jun South China University of Technology China Alibaba Group China Key Laboratory of Big Data and Intelligent Robot South China University of Technology Ministry of Education China

Recently, diffusion-based deep generative models (e.g., Stable Diffusion) have shown impressive results in text-to-image synthesis. However, current text-to-image models often require multiple passes of prompt engineering by humans in order to produce satisfactory results for real-world applications. We propose BeautifulPrompt, a deep generative model to produce high-quality prompts from very simple raw descriptions, which enables diffusion-based models to generate more beautiful images. In our work, we first fine-tuned the BeautifulPrompt model over low-quality and high-quality collecting prompt pairs. Then, to ensure that our generated prompts can generate more beautiful images, we further propose a Reinforcement Learning with Visual AI Feedback technique to fine-tune our model to maximize the reward values of the generated prompts, where the reward values are calculated based on the PickScore and the Aesthetic Scores. Our results demonstrate that learning from visual AI feedback promises the potential to improve the quality of generated prompts and images significantly. We further showcase the integration of BeautifulPrompt to a cloud-native AI platform to provide better text-to-image generation service in the cloud. © 2023 Association for Computational Linguistics.

关键词： Diffusion

来源：评论

学校读者我要写书评

暂无评论

An Ultra-Wideband Cascaded Power Amplifier for Military Individual Radio 7

An Ultra-Wideband Cascaded Power Amplifier for Military Indi...

引用

7th IEEE International Conference on Electronic Information and Communication Technology, ICEICT 2024

作者： Gao, Fei Nan, Jingchang Fan, Hongji Wang, Cong Tang, Panpan Li, Zhaoqi Liaoning Technical University Liaoning Key Laboratory of Radio Frequency and Big Data for Intelligent Applications Huludao China Southeast University Nanjing China Harbin Institute of Technology Department of Microwave Engineering Harbin China

ISBN: (纸本)9798350384437

In recent years, there has been a tremendous interest in military individual radio in wireless communication. To obtain sufficient operating distance and long standby time, the output power and efficiency of power amplifiers have become the research focus by some of the research teams. GaN has higher electron mobility and forbidden bandwidth than other materials. Nowadays, GaN has become the mainstream key technology for radio frequency (RF) power amplifiers in 5G communication systems. In this work, a 500MHz~2500MHz GaN-based HEMT wideband cascaded power amplifier was designed. The output power of the driver amplifier is 36.6dBm ± 0.5dB, the input return loss is 20%, the DC power consumption is 10 dB, input voltage standing wave ratio © 2024 IEEE.

关键词： Gallium nitride

来源：评论

学校读者我要写书评

暂无评论

Advances and prospects in SAR microwave vision three-dimensional imaging

引用

National Science Open 2024年第5期3卷 53-83页

作者： Xiaolan Qiu Zekun Jiao Zhe Zhang Qiancheng Yan Chibiao Ding National Key Laboratory of Microwave Imaging Aerospace Information Research InstituteChinese Academy of SciencesBeijing 100190China School of Electronic Electrical and Communication EngineeringUniversity of Chinese Academy of SciencesBeijing 100094China Key Laboratory of Intelligent Aerospace Big Data Application Technology Suzhou 215123China

Synthetic Aperture Radar three-dimensional(3D)imaging enables the acquisition of more comprehensive information,making it a recent hotspot in radar *** 3D imaging methods have evolved from 2D and interferometric imaging,combining elevation aperture extension with signal processing *** such as long acquisition or complex system from its imaging mechanism restrict its *** recent years,rapid development of artificial intelligence has led to a swift advancement in radar,injecting new vitality into SAR 3D *** microwave vision 3D imaging theory,which is built upon advanced technologies,has emerged as a new interdisciplinary field for radar *** paper reviews SAR 3D imaging’s history and present situation,and introduces SAR microwave *** establish a theoretical framework covering representation models,computational models,processing paradigms and evaluation ***,our research progress in this area is discussed,along with future prospects for SAR microwave vision 3D imaging.

关键词： SAR microwave vision 3D imaging visual semantics scattering mechanism

来源：评论

学校读者我要写书评

暂无评论

Research on Weld Detection Based on Weighted Feature Fusion Network 23

Research on Weld Detection Based on Weighted Feature Fusion ...

引用

15th International Conference on Digital Image Processing, ICDIP 2023

作者： Wang, Mengxue Ma, Xing Mu, Chunyang Hou, Bing College of Electronic and Information Engineering North Minzu University Yinchuan China The Key Laboratory of Intelligent Information and Big Data Processing North Minzu University Yinchuan China

ISBN: (纸本)9798400708237

Weld seam grinding is a crucial process for welding cast products. Not only are the polished welds more attractive and durable, but they also have superior stress effects. However, the workplace is harsh and can significantly impact health. The first task for automated weld grinding is weld detection. This paper, a pyramid feature fusion network (YOLOv5-BiCA) learning model with embedded coordinate attention as a weighting condition that fully utilizes the shallow and deep network information. An online data augmentation strategy employing Mosaic+Mixup is proposed to address the problem of insufficient sample size. We use Focal Loss to enhance the classification function and increase the positive influence of positive samples on the loss function during the training process to address the problem of an imbalance between positive and negative sample. Our proposed YOLOv5-BiCA performs better in weld detection, mAP improves by 3.5%, and recall improves by 7.97%, according to experimental results based on homegrown datasets. © 2023 ACM.

关键词： Welds

来源：评论

学校读者我要写书评

暂无评论

Dual-view Label and Feature Supervision Network for Semi-supervised Medical Image Segmentation 24

Dual-view Label and Feature Supervision Network for Semi-sup...

引用

7th International Conference on Signal Processing and Machine Learning, SPML 2024

作者： Zhou, Zhen Li, Zuoyong Wang, Zhengyuan Teng, Shenghua Wang, Tao College of Electronic and Information Engineering Shandong University of Science and Technology Qingdao China Fujian Provincial Key Laboratory of Information Processing and Intelligent Control School of Computer and Big Data Minjiang University Fuzhou China

ISBN: (纸本)9798400717192

Semi-supervised learning has garnered significant attention, particularly in medical image segmentation, owing to its capacity to leverage a large number of unlabeled data and a limited amount of labeled data to improve performance. However, most existing semi-supervised segmentation methods exhibit shortcomings in supervising unlabeled data, both in the label space due to potential noise in pseudo-labels, and the feature space due to indistinct class boundaries. To address the issues above, we propose Dual-view Label and Feature Supervision Network, termed DLFS-Net, to enhance label and feature supervision for unlabeled data. Our approach is based on a dual-view learning strategy that incorporates two modules: the Confidence Fusion Supervision Module (CFS) and the Dual-view Prototype Learning Module (DPL). Specifically, the CFS module generates weight matrices to integrate complementary information from two model outputs, producing more accurate pseudo-labels in the label space. The DPL module reduces intra-class variations in the feature space from two different views through prototype learning to generate clear class boundaries. Experiments on the LA and Pancreas-CT datasets demonstrate that our framework show solid gains (e.g.,1.76% Dice and 2.37% Jaccard improvement on Pancreas-CT dataset with 20% labeled data) compared with the state-of-the-art methods. © 2024 ACM.

关键词： Self-supervised learning

来源：评论

学校读者我要写书评

暂无评论

3D-GRES: Generalized 3D Referring Expression Segmentation 24

3D-GRES: Generalized 3D Referring Expression Segmentation

引用

32nd ACM International Conference on Multimedia, MM 2024

作者： Wu, Changli Liu, Yihang Ji, Jiayi Ma, Yiwei Wang, Haowei Luo, Gen Ding, Henghui Sun, Xiaoshuai Ji, Rongrong Key Laboratory of Multimedia Trusted Perception and Efficient Computing Ministry of Education of China Xiamen University Xiamen China Youtu Lab Tencent Shanghai China Institute of Big Data Fudan University Shanghai China

ISBN: (纸本)9798400706868

3D Referring Expression Segmentation (3D-RES) is dedicated to segmenting a specific instance within a 3D space based on a natural language description. However, current approaches are limited to segmenting a single target, restricting the versatility of the task. To overcome this limitation, we introduce Generalized 3D Referring Expression Segmentation (3D-GRES), which extends the capability to segment any number of instances based on natural language instructions. In addressing this broader task, we propose the Multi-Query Decoupled Interaction Network (MDIN), designed to break down multi-object segmentation tasks into simpler, individual segmentations. MDIN comprises two fundamental components: Text-driven Sparse Queries (TSQ) and Multi-object Decoupling Optimization (MDO). TSQ generates sparse point cloud features distributed over key targets as the initialization for queries. Meanwhile, MDO is tasked with assigning each target in multi-object scenarios to different queries while maintaining their semantic consistency. To adapt to this new task, we build a new dataset, namely Multi3DRes. Our comprehensive evaluations on this dataset demonstrate substantial enhancements over existing models, thus charting a new path for intricate multi-object 3D scene comprehension. The benchmark and code are available at https://***/sosppxo/MDIN. © 2024 ACM.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Research on Frequency of Radial Vibration of Elastic Thin Spherical Shell

Research on Frequency of Radial Vibration of Elastic Thin Sp...

引用

2023 International Congress on Ultrasonics, ICU Beijing 2023

作者： Haidao, Zhang Long, Xu Fengming, Li College of Science China Jiliang University Zhejiang Hangzhou310018 China Key Laboratory of Intelligent Manufacturing Quality Big Data Tracing and Analysis of Zhejiang Province China Jiliang University Hangzhou310018 China

The ultrasonic frequency radial vibration of an elastic thin spherical shell composed of isotropic materials is studied, the frequency equation of its vibration is deduced, and the equivalent circuit is obtained. The finite element software COMSOL is used to verify the obtained analytical theory, and the calculated results are basically consistent with the theoretical calculated values. The relevant conclusions provide references for the application of spherical shell structure in related fields. © 2024 Institute of Physics Publishing. All rights reserved.

关键词： Shells (structures)

来源：评论

学校读者我要写书评

暂无评论

LeapGNN: accelerating distributed GNN training leveraging feature-centric model migration 25

LeapGNN: accelerating distributed GNN training leveraging fe...

引用

Proceedings of the 23rd USENIX Conference on File and Storage Technologies

作者： Weijian Chen Shuibing He Haoyang Qu Xuechen Zhang The State Key Laboratory of Blockchain and Data Security Zhejiang University and Zhejiang Lab and Hangzhou High-Tech Zone (Binjiang) Institute of Blockchain and Data Security and Zhejiang Key Laboratory of Big Data Intelligent Computing Washington State University Vancouver

ISBN: (纸本)9781939133458

Distributed training of graph neural networks (GNNs) has become a crucial technique for processing large graphs. Prevalent GNN frameworks are model-centric, necessitating the transfer of massive graph vertex features to GNN models, which leads to a significant communication bottleneck. Recognizing that the model size is often significantly smaller than the feature size, we propose LeapGNN, a feature-centric framework that reverses this paradigm by bringing GNN models to vertex features. To make it truly effective, we first propose a micrograph-based training strategy that leverages a refined structure to enhance locality, combined with the model migration technique, to minimize remote feature retrieval. Then, we devise a feature pre-gathering approach that merges multiple fetch operations into a single one to eliminate redundant feature transmissions. Finally, we employ a micrograph-based merging method that adjusts the number of micrographs for each worker to minimize kernel switches and synchronization overhead. Our experimental results demonstrate that LeapGNN achieves a performance speedup of up to 4.2× compared to the state-of-the-art method, namely P3.

关键词：

来源：评论

学校读者我要写书评

暂无评论

GBFRS: Robust Fuzzy Rough Sets via Granular-ball computing

arXiv

引用

arXiv 2025年

作者： Xia, Shuyin Lian, Xiaoyu Sang, Binbin Wang, Guoyin Gao, Xinbo Chongqing Key Laboratory of Computational Intelligence Key Laboratory of Big Data Intelligent Computing Key Laboratory of Cyberspace Big Data Intelligent Security Ministry of Education Chongqing University of Posts and Telecommunications Chongqing400065 China College of Computer and Information Science the National Center for Applied Mathematics in Chongqing Chongqing Normal University Chongqing401331 China

Fuzzy rough set theory is effective for processing datasets with complex attributes, supported by a solid mathematical foundation and closely linked to kernel methods in machine learning. Attribute reduction algorithms and classifiers based on fuzzy rough set theory exhibit promising performance in the analysis of high-dimensional multivariate complex data. However, most existing models operate at the finest granularity, rendering them inefficient and sensitive to noise, especially for high-dimensional big data. Thus, enhancing the robustness of fuzzy rough set models is crucial for effective feature selection. Muiti-garanularty granular-ball computing, a recent development, uses granular-balls of different sizes to adaptively represent and cover the sample space, performing learning based on these granular-balls. This paper proposes integrating multi-granularity granular-ball computing into fuzzy rough set theory, using granular-balls to replace sample points. The coarse-grained characteristics of granular-balls make the model more robust. Additionally, we propose a new method for generating granular-balls, scalable to the entire supervised method based on granular-ball computing. A forward search algorithm is used to select feature sequences by defining the correlation between features and categories through dependence functions. Experiments demonstrate the proposed model’s effectiveness and superiority over baseline methods. The source codes and datasets are both available on the public link: https://***/lianxiaoyu724/GBFRS Copyright © 2025, The Authors. All rights reserved.

关键词： Granular computing

来源：评论

学校读者我要写书评

暂无评论

State-of-Charge Estimation of Lithium Battery Based on Deep Residual Shrinkage Networks and a Variant Long Short Term Memory Neural Network

State-of-Charge Estimation of Lithium Battery Based on Deep ...

引用

Chinese Control and Decision Conference, CCDC

作者： Penghua Li Yihui Zhang Key Laboratory of Intelligent Computing for Big Data College of Automation Chongqing University of Posts and Telecommunications Chongqing China

Accurate state-of-charge (SOC) estimation, which is critical to ensuring the safe and reliable operation of battery management systems in electric vehicles, is still a challenging task due to sophisticated battery dynamics and ever-changing ambient conditions. This paper proposes a method combining DRSN and ASTLSTM neural networks to estimate lithium batteries' state of charge (SOC). The proposed method can not only utilize the historical information of the data but also eliminate unimportant features by inserting soft thresholding into the deep architectures. To reveal the performance of the proposed method, the results are compared with several other methods from the literature. The comparative experimental results show that the proposed method achieves a lower root mean square error (RMSE) of 0.83% with normal data and RMSE of 0.98% with noisy data, respectively.

关键词：

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：