检索结果-内蒙古大学图书馆

arXiv 2022年

作者： Song, Siyang Song, Yuxin Luo, Cheng Song, Zhiyuan Kuzucu, Selim Jia, Xi Guo, Zhijiang Xie, Weicheng Shen, Linlin Gunes, Hatice The Department of Computer Science and Technology University of Cambridge CambridgeCB3 0FT United Kingdom Baidu Inc Beijing100193 China Computer Vision Institute School of Computer Science & Software Engineering Shenzhen Institute of Artificial Intelligence and Robotics for Society Guangdong Key Laboratory of Intelligent Information Processing Shenzhen University Shenzhen518060 China Department of Computer Engineering Middle East Technical University Ankara Turkey School of Computer Science University of Birmingham Birmingham United Kingdom

Graph is powerful for representing various types of real-world data. The topology (edges’ presence) and edges’ features of a graph decides the message passing mechanism among vertices within the graph. While most existing approaches only manually define a single-value edge to describe the connectivity or strength of association between a pair of vertices, task-specific and crucial relationship cues may be disregarded by such manually defined topology and single-value edge features. In this paper, we propose the first general graph representation learning framework (called GRATIS) which can generate a strong graph representation with a task-specific topology and task-specific multi-dimensional edge features from any arbitrary input (i.e., graph or non-graph data). To learn each edge’s presence and multi-dimensional feature, our framework takes both of the corresponding vertices pair and their global contextual information into consideration, enabling the generated graph representation to have a globally optimal message passing mechanism for different down-stream tasks. The principled investigation results achieved for various graph analysis tasks (e.g., graph classification, vertex classification, and link prediction) on 11 graph and non-graph datasets show that our GRATIS can not only largely enhance pre-defined graphs but also learns a strong graph representation for non-graph data, with clear performance improvements on all tasks. In particular, the learned topology and multi-dimensional edge features provide complementary task-related cues for graph analysis tasks. Our framework is effective, robust and flexible, and is a plug-and-play module that can be combined with different backbones and Graph Neural Networks (GNNs) to generate a task-specific graph representation from various graph and non-graph data. Our code is made publicly available at https://***/SSYSteve/Learning-Graph-Representation-with-Task-specific-Topology-and-Multi-dimensional-Edge-Feature

关键词： Graph neural networks

来源：评论

学校读者我要写书评

暂无评论

Selective Multi-Scale Learning for Object Detection

arXiv

引用

arXiv 2022年

作者： Chen, Junliang Lu, Weizeng Shen, Linlin Computer Vision Institute School of Computer Science and Software Engineering Shenzhen University China Shenzhen Institute of Artificial Intelligence of Robotics of Society Shenzhen China Guangdong Key Laboratory of Intelligent Information Processing Shenzhen University Shenzhen518060 China

Pyramidal networks are standard methods for multi-scale object detection. Current researches on feature pyramid networks usually adopt layer connections to collect features from certain levels of the feature hierarchy, and do not consider the significant differences among them. We propose a better architecture of feature pyramid networks, named selective multi-scale learning (SMSL), to address this issue. SMSL is efficient and general, which can be integrated in both single-stage and two-stage detectors to boost detection performance, with nearly no extra inference cost. RetinaNet combined with SMSL obtains 1.8% improvement in AP (from 39.1% to 40.9%) on COCO dataset. When integrated with SMSL, two-stage detectors can get around 1.0% improvement in AP. © 2022, CC BY.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

Observation of the symmetry-protected signature of 3-body interactions

arXiv

引用

arXiv 2024年

作者： Zhukas, Liudmila A. Wang, Qingfeng Katz, Or Monroe, Christopher Marvian, Iman Duke Quantum Center Departments of Electrical and Computer Engineering and Physics Duke University DurhamNC27708 United States Chemical Physics Program Institute for Physical Science and Technology University of Maryland College ParkMD United States School of Applied and Engineering Physics Cornell University IthacaNY14853 United States

Identifying and characterizing multi-body interactions in quantum processes remains a significant challenge. This is partly because 2-body interactions can produce an arbitrary time evolution, a fundamental fact often called the universality of 2-local gates in the context of quantum computing. However, when an unknown Hamiltonian respects a U(1) symmetry such as charge or particle number conservation, N-body interactions exhibit a distinct symmetry-protected signature known as the N-body phase, which fewer-body interactions cannot mimic. We develop and demonstrate an efficient technique for the detection of 3-body interactions despite the presence of unknown 2-body interactions. This technique, which takes advantage of GHZ states for phase estimation, requires probing the unitary evolution and measuring its determinant in a small subspace that scales linearly with the system size, making it an efficient approach. Copyright © 2024, The Authors. All rights reserved.

关键词： Hamiltonians

来源：评论

学校读者我要写书评

暂无评论

Fusion Dynamical Systems with Machine Learning in Imitation Learning: A Comprehensive Overview

arXiv

引用

arXiv 2024年

作者： Hu, Yingbai Abu-Dakka, Fares J. Chen, Fei Luo, Xiao Li, Zheng Knoll, Alois Ding, Weiping Multi-Scale Medical Robotics Centre Ltd. The Chinese University of Hong Kong Hong Kong School of Computation Information and Technology Technical University of Munich Munich85748 Germany Electronic and Computer Science Department Faculty of Engineering Mondragon Unibertsitatea Arrasate20500 Spain Department of Mechanical and Automation Engineering The Chinese University of Hong Kong Hong Kong Department of Surgery The Chinese University of Hong Kong Hong Kong School of Information Science and Technology Nantong University Nantong226019 China

Imitation Learning (IL), also referred to as Learning from Demonstration (LfD), holds significant promise for capturing expert motor skills through efficient imitation, facilitating adept navigation of complex scenarios. A persistent challenge in IL lies in extending generalization from historical demonstrations, enabling the acquisition of new skills without re-teaching. Dynamical system-based IL (DSIL) emerges as a significant subset of IL methodologies, offering the ability to learn trajectories via movement primitives and policy learning based on experiential abstraction. This paper emphasizes the fusion of theoretical paradigms, integrating control theory principles inherent in dynamical systems into IL. This integration notably enhances robustness, adaptability, and convergence in the face of novel scenarios. This survey aims to present a comprehensive overview of DSIL methods, spanning from classical approaches to recent advanced approaches. We categorize DSIL into autonomous dynamical systems and non-autonomous dynamical systems, surveying traditional IL methods with low-dimensional input and advanced deep IL methods with high-dimensional input. Additionally, we present and analyze three main stability methods for IL: Lyapunov stability, contraction theory, and diffeomorphism mapping. Our exploration also extends to popular policy improvement methods for DSIL, encompassing reinforcement learning, deep reinforcement learning, and evolutionary strategies. The primary objective is to expedite readers' comprehension of dynamical systems' foundational aspects and capabilities, helping identify practical scenarios and charting potential future directions. By offering insights into the strengths and limitations of dynamical system methods, we aim to foster a deeper understanding among readers. Furthermore, we outline potential extensions and enhancements within the realm of dynamical systems, outlining avenues for further exploration. © 2024, CC BY.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Geometry Constrained Weakly Supervised Object Localization 16th

Geometry Constrained Weakly Supervised Object Localization

引用

16th European Conference on computer Vision, ECCV 2020

作者： Lu, Weizeng Jia, Xi Xie, Weicheng Shen, Linlin Zhou, Yicong Duan, Jinming Computer Vision Institute School of Computer Science and Software Engineering Shenzhen University Shenzhen China Shenzhen Institute of Artificial Intelligence and Robotics for Society Shenzhen China School of Computer Science University of Birmingham Birmingham United Kingdom Department of Computer and Information Science University of Macau Zhuhai China

ISBN: (纸本)9783030585730

We propose a geometry constrained network, termed GC-Net, for weakly supervised object localization (WSOL). GC-Net consists of three modules: a detector, a generator and a classifier. The detector predicts the object location defined by a set of coefficients describing a geometric shape (i.e. ellipse or rectangle), which is geometrically constrained by the mask produced by the generator. The classifier takes the resulting masked images as input and performs two complementary classification tasks for the object and background. To make the mask more compact and more complete, we propose a novel multi-task loss function that takes into account area of the geometric shape, the categorical cross-entropy and the negative entropy. In contrast to previous approaches, GC-Net is trained end-to-end and predict object location without any post-processing (e.g. thresholding) that may require additional tuning. Extensive experiments on the CUB-200-2011 and ILSVRC2012 datasets show that GC-Net outperforms state-of-the-art methods by a large margin. Our source code is available at https://***/lwzeng/GC-Net. © 2020, Springer Nature Switzerland AG.

关键词： Geometry

来源：评论

学校读者我要写书评

暂无评论

Fast Detection of Multi-Direction Remote Sensing Ship Object Based on Scale Space Pyramid

Fast Detection of Multi-Direction Remote Sensing Ship Object...

引用

International Conference on Mobile Ad-hoc and Sensor Networks, MSN

作者： Ziying Song Li Wang Guoxin Zhang Caiyan Jia Jiangfeng Bi Haiyue Wei Yongchao Xia Chao Zhang Lijun Zhao School of Computer and Information Technology Beijing Jiaotong University Beijing China School of Vehicle and Mobility Tsinghua University Beijing China State Key Laboratory of Robotics and Systems Harbin Institute of Technology Harbin China School of Information Science and Engineering Hebei University of Science and Technology Shijiazhuang China

Ships in remote sensing images are usually arranged in arbitrary direction, small in size, and densely arranged. As a result, existing object detection algorithms cannot detect ships quickly and accurately. In order to solve the above problems, a lightweight object detection network for fast detection of ships is proposed. The network is composed of backbone network, four-scale fusion network and rotation branch. First, a lightweight network unit S-LeanNet is designed and used to build a low-computing and accurate backbone network. Then, a four-scale feature fusion module is designed to generate a four-scale feature pyramid, which contains more features such as ship shape and texture, and at the same time is conducive to the detection of small ships. Finally, a novel rotation branch module is designed, using balance L1 loss function and R-NMS for post-processing, to realize the precise positioning and regression of the rotating bounding box in one step. Experimental results show that the detection precision of our method in the DOT A remote sensing data set is compared with the latest SCRDet detection method, the precision is increased by 1.1%, and the operating speed is increased by 8 times, which can meet the fast detection requirements of ships.

关键词： Sea surface Shape Object detection US Department of Transportation Feature extraction Sensors Marine vehicles

来源：评论

学校读者我要写书评

暂无评论

Probabilistic genotype-phenotype maps reveal mutational robustness of RNA folding, spin glasses, and quantum circuits

引用

Physical Review Research 2025年第1期7卷 013118-013118页

作者： Anna Sappington Vaibhav Mohanty Department of Electrical Engineering and Computer Science Massachusetts Institute of Technology Cambridge Massachusetts 02139 USA Harvard-MIT Program in Health Sciences and Technology Harvard Medical School Boston Massachusetts 02115 USA and Massachusetts Institute of Technology Cambridge Massachusetts 02139 USA Harvard/MIT MD-PhD Program Harvard Medical School Boston Massachusetts 02115 USA and Massachusetts Institute of Technology Cambridge Massachusetts 02139 USA Department of Chemistry and Chemical Biology Harvard University Cambridge Massachusetts 02138 USA

Recent studies of genotype-phenotype maps have reported universally enhanced phenotypic robustness to genotype mutations, a feature essential to evolution. Virtually all of these studies make a simplifying assumption that each genotype—represented as a sequence—maps deterministically to a single phenotype, such as a discrete structure. Here we introduce probabilistic genotype-phenotype (PrGP) maps, where each genotype maps to a vector of phenotype probabilities, as a more realistic and universal language for investigating robustness in a variety of physical, biological, and computational systems. We study three model systems to show that PrGP maps offer a generalized framework which can handle uncertainty emerging from various physical sources: (1) thermal fluctuation in RNA folding, (2) external field disorder in the spin-glass ground state search problem, and (3) superposition and entanglement in quantum circuits, which are realized experimentally on IBM quantum computers. In all three cases, we observe a biphasic robustness scaling which is enhanced relative to random expectation for more frequent phenotypes and approaches random expectation for less frequent phenotypes. We derive an analytical theory for the behavior of PrGP robustness, and we demonstrate that the theory is highly predictive of empirical robustness.

关键词： Quantum computers

来源：评论

学校读者我要写书评

暂无评论

Monolithic Germanium–Tin on Si Avalanche Photodiodes

arXiv

引用

arXiv 2024年

作者： Rudie, Justin Amoah, Sylvester Wang, Xiaoxin Kumar, Rajesh Abernathy, Grey Akwabli, Steven Grant, Perry C. Liu, Jifeng Li, Baohua Du, Wei Yu, Shui-Qing Material Science and Engineering University of Arkansas FayettevilleAR72701 United States Department of Electrical Engineering and Computer Science University of Arkansas FayettevilleAR72701 United States Thayer School of Engineering Dartmouth College HanoverNH03755 United States Arktonics LLC 1339 S. Pinnacle Dr. FayettevilleAR72701 United States Materials Science & Engineering Program University of Arkansas FayettevilleAR72701 United States Institute for Nanoscience and Engineering University of Arkansas FayettevilleAR72701 United States

We demonstrate monolithically grown germanium-tin (GeSn) on silicon avalanche photodiodes (APDs) for infrared light detection. A relatively thinner Ge buffer design was adopted to allow effective photo carriers to transport from the GeSn absorber to the Si multiplication layer such that clear punch-through behavior and a saturated primary responsivity of 0.3 A/W at 1550 nm were observed before avalanche breakdown in GeSn/Si APDs for the first time. The spectral response covers 1500 to 1700 nm. The measured punch-through and breakdown voltages are 15 and 17 V, respectively. Undisputed multiplication gain was obtained with the maximum value of 4.5 at 77 K, and 1.4 at 250 K, directly in reference to the saturated primary responsivity from the same device rather than a different GeSn p-i-n photodiode in previous reports. A peak responsivity was measured as 1.12 A/W at 1550 nm and 77 K. © 2024, CC0.

关键词： Avalanche photodiodes

来源：评论

学校读者我要写书评

暂无评论

Precise Facial Landmark Detection by Reference Heatmap Transformer

arXiv

引用

arXiv 2023年

作者： Wan, Jun Liu, Jun Zhou, Jie Lai, Zhihui Shen, Linlin Sun, Hang Xiong, Ping Min, Wenwen The School of Information and Safety Engineering Zhongnan University of Economics and Law Wuhan430073 China The Information Systems Technology and Design Pillar Singapore University of Technology and Design Singapore487372 Singapore The College of Computer Science and Software Engineering Shen zhen University Shenzhen518060 China The Shenzhen Institute of Artificial Intelligence and Robotics for Society Shenzhen518060 China College of Computer and Information Technology China Three Gorges University HuBei Yichang China The School of Information Science and Engineering Yunnan University Yunnan Kunming650091 China

Most facial landmark detection methods predict landmarks by mapping the input facial appearance features to landmark heatmaps and have achieved promising results. However, when the face image is suffering from large poses, heavy occlusions and complicated illuminations, they cannot learn discriminative feature representations and effective facial shape constraints, nor can they accurately predict the value of each element in the landmark heatmap, limiting their detection accuracy. To address this problem, we propose a novel Reference Heatmap Transformer (RHT) by introducing reference heatmap information for more precise facial landmark detection. The proposed RHT consists of a Soft Transformation Module (STM) and a Hard Transformation Module (HTM), which can cooperate with each other to encourage the accurate transformation of the reference heatmap information and facial shape constraints. Then, a Multi-Scale Feature Fusion Module (MSFFM) is proposed to fuse the transformed heatmap features and the semantic features learned from the original face images to enhance feature representations for producing more accurate target heatmaps. To the best of our knowledge, this is the first study to explore how to enhance facial landmark detection by transforming the reference heatmap information. The experimental results from challenging benchmark datasets demonstrate that our proposed method outperforms the state-of-the-art methods in the literature. Copyright © 2023, The Authors. All rights reserved.

关键词： Face recognition

来源：评论

学校读者我要写书评

暂无评论

Provably Convergent Federated Trilevel Learning

arXiv

引用

arXiv 2023年

作者： Jiao, Yang Yang, Kai Wu, Tiancheng Jian, Chengtao Huang, Jianwei Department of Computer Science and Technology Tongji University China Key Laboratory of Embedded System and Service Computing Ministry of Education Tongji University China Shanghai Research Institute for Intelligent Autonomous Systems China School of Science and Engineering The Chinese University of Hong Kong Shenzhen China Shenzhen Institute of Artificial Intelligence and Robotics for Society China

Trilevel learning, also called trilevel optimization (TLO), has been recognized as a powerful modelling tool for hierarchical decision process and widely applied in many machine learning applications, such as robust neural architecture search, hyperparameter optimization, and domain adaptation. Tackling TLO problems has presented a great challenge due to their nested decision-making structure. In addition, existing works on TLO face the following key challenges: 1) they all focus on the non-distributed setting, which may lead to privacy breach;2) they do not offer any non-asymptotic convergence analysis which characterizes how fast an algorithm converges. To address the aforementioned challenges, this paper proposes an asynchronous federated trilevel optimization method to solve TLO problems. The proposed method utilizes µ-cuts to construct a hyper-polyhedral approximation for the TLO problem and solve it in an asynchronous manner. We demonstrate that the proposed µ-cuts are applicable to not only convex functions but also a wide range of non-convex functions that meet the µ-weakly convex assumption. Furthermore, we theoretically analyze the non-asymptotic convergence rate for the proposed method by showing its iteration complexity to obtain ϵ-stationary point is upper bounded by (Formula Presented). Extensive experiments on real-world datasets have been conducted to elucidate the superiority of the proposed method, e.g., it has a faster convergence rate with a maximum acceleration of approximately 80%. Copyright © 2023, The Authors. All rights reserved.

关键词： Decision making

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：