检索结果-内蒙古大学图书馆

SA-ConvONet: Sign-agnostic optimization of convolutional occupancy networks

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Tang, Jiapeng Lei, Jiabao Xu, Dan Ma, Feiying Jia, Kui Zhang, Lei School of Electronic and Information Engineering South China University of Technology Department of Computer Science and Engineering HKUST Hong Kong Department of Computing The Hong Kong Polytechnic University Hong Kong DAMO Academy Alibaba Group Pazhou Lab Guangzhou China Peng Cheng Laboratory Shenzhen China

Surface reconstruction from point clouds is a fundamental problem in the computer vision and graphics community. Recent state-of-the-arts solve this problem by individually optimizing each local implicit field during inference. Without considering the geometric relationships between local fields, they typically require accurate normals to avoid the sign conflict problem in overlapped regions of local fields, which severely limits their applicability to raw scans where surface normals could be unavailable. Although SAL breaks this limitation via sign-agnostic learning, further works still need to explore how to extend this technique for local shape modeling. To this end, we propose to learn implicit surface reconstruction by sign-agnostic optimization of convolutional occupancy networks, to simultaneously achieve advanced scalability to large-scale scenes, generality to novel shapes, and applicability to raw scans in a unified framework. Concretely, we achieve this goal by a simple yet effective design, which further optimizes the pre-trained occupancy prediction networks with an unsigned cross-entropy loss during inference. The learning of occupancy fields is conditioned on convolutional features from an hourglass network architecture. Extensive experimental comparisons with previous state-of-the-arts on both object-level and scene-level datasets demonstrate the superior accuracy of our approach for surface reconstruction from un-orientated point clouds. The code is available at https://***/tangjiapeng/SA-ConvONet. Copyright © 2021, The Authors. All rights reserved.

关键词： Convolution

AstroLLaMA-Chat: Scaling AstroLLaMA with Conversational and Diverse Datasets

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Perkowski, Ernest Pan, Rui Nguyen, Tuan Dung Ting, Yuan-Sen Kruk, Sandor Zhang, Tong O’Neill, Charlie Jablonska, Maja Sun, Zechang Smith, Michael J. Liu, Huiling Schawinski, Kevin Iyer, Kartheik Ciucă, Ioana Camino Bajo del Castillo s/n Villanueva de la Cañada Madrid28692 Spain Department of Computer Science and Engineering Hong Kong University of Science and Technology Hong Kong Department of Computer and Information Science University of Pennsylvania PhiladelphiaPA19104 United States Research School of Astronomy & Astrophysics Australian National University Cotter Rd. WestonACT2611 Australia School of Computing Australian National University ActonACT2601 Australia Department of Astronomy The Ohio State University ColumbusOH43210 United States The Ohio State University ColumbusOH43210 United States Department of Computer Science University of Illinois Urbana-Champaign United States Mathematical Science Institute Australian National University ActonACT2601 Australia Department of Astronomy MongManWai Building Tsinghua University Beijing100084 China Aspia Space Tremough Innovation Centre PenrynTR10 9TA United Kingdom Department of Modern Physics University of Science and Technology of China Anhui Hefei230026 China Modulos Technoparkstrasse 1 Zurich8005 Switzerland Columbia Astrophysics Laboratory Columbia University New YorkNY10027 United States

We explore the potential of enhancing LLM performance in astronomy-focused question-answering through targeted, continual pre-training. By employing a compact 7B-parameter LLaMA-2 model and focusing exclusively on a curated set of astronomy corpora—comprising abstracts, introductions, and conclusions—we achieve notable improvements in specialized topic comprehension. While general LLMs like GPT-4 excel in broader question-answering scenarios due to superior reasoning capabilities, our findings suggest that continual pre-training with limited resources can still enhance model performance on specialized topics. Additionally, we present an extension of AstroLLaMA: the fine-tuning of the 7B LLaMA model on a domain-specific conversational dataset, culminating in the release of the chat-enabled AstroLLaMA for community use. Comprehensive quantitative benchmarking is currently in progress and will be detailed in an upcoming full paper. The model, AstroLLaMA-Chat, is now available at https://***/universeTBD, providing the first open-source conversational AI tool tailored for the astronomy community. Copyright © 2024, The Authors. All rights reserved.

关键词：

Anomaly detection on attributed networks via contrastive self-supervised learning

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Liu, Yixin Li, Zhao Pan, Shirui Gong, Chen Zhou, Chuan Karypis, George The Department of Data Science and AI Faculty of Information Technology Monash University ClaytonVIC3800 Australia The Alibaba Group Hangzhou310000 China The PCA Laboratory Key Laboratory of Intelligent Perception and Systems for High-Dimensional Information Ministry of Education School of Computer Science and Engineering Nanjing University of Science and Technology Nanjing210094 China The Department of Computing The Hong Kong Polytechnic University Hong Kong The Academy of Mathematics and Systems Science Chinese Academy of Sciences Beijing100093 China The Department of Computer Science and Engineering University of Minnesota MinneapolisMN55455 United States

Anomaly detection on attributed networks attracts considerable research interests due to wide applications of attributed networks in modeling a wide range of complex systems. Recently, the deep learning-based anomaly detection methods have shown promising results over shallow approaches, especially on networks with high-dimensional attributes and complex structures. However, existing approaches, which employ graph autoencoder as their backbone, do not fully exploit the rich information of the network, resulting in suboptimal performance. Furthermore, these methods do not directly target anomaly detection in their learning objective and fail to scale to large networks due to the full graph training mechanism. To overcome these limitations, in this paper, we present a novel Contrastive self-supervised Learning framework for Anomaly detection on attributed networks (CoLA for abbreviation). Our framework fully exploits the local information from network data by sampling a novel type of contrastive instance pair, which can capture the relationship between each node and its neighboring substructure in an unsupervised way. Meanwhile, a well-designed graph neural network-based contrastive learning model is proposed to learn informative embedding from high-dimensional attributes and local structure and measure the agreement of each instance pairs with its outputted scores. The multi-round predicted scores by the contrastive learning model are further used to evaluate the abnormality of each node with statistical estimation. In this way, the learning model is trained by a specific anomaly detection-aware target. Furthermore, since the input of the graph neural network module is batches of instance pairs instead of the full network, our framework can adapt to large networks flexibly. Experimental results show that our proposed framework outperforms the state-of-the-art baseline methods on all seven benchmark datasets. © 2021, CC BY.

关键词： Anomaly detection

Achieving Privacy-Preserving Iris Identification Via El Gamal

学校读者我要写书评

暂无评论

computers, Materials & Continua 2019年第8期61卷 727-738页

作者： Yong Ding Lei Tian Bo Han Huiyong Wang Yujue Wang James Xi Zheng Guangxi Key Laboratory of Cryptography and Information Security School of Computer and Information SecurityGuilin University of Electronic TechnologyGuilin541004China School of Mathematics and Computer Science Guilin University of Electronic TechnologyGuilin541004China Software Engineering Department of Computing Macquarie UniversitySydneyNSW 2109 Australia

Currently,many biometric systems maintain the user’s biometrics and templates in plaintext format,which brings great privacy risk to uses’biometric *** are unique and almost unchangeable,which means it is a great concern for users on whether their biometric information would be *** address this issue,this paper proposes a confidential comparison algorithm for iris feature vectors with masks,and develops a privacy-preserving iris verification scheme based on the El Gamal encryption *** our scheme,the multiplicative homomorphism of encrypted features is used to compare of iris features and their mask ***,this paper improves the Hamming distance of iris features,which makes the similarity matching work better than existing *** results confirm the practicality of our proposed schemes in real world applications,that is,for the iris feature vectors and masks of 2048 bits,nearly 12 comparisons can be performed per second.

关键词： Homomorphic encryption template matching Hamming distance

Quantum generative training using rényi divergences

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Kieferová, Mária Marrero, Carlos Ortiz Wiebe, Nathan Centre for Quantum Computation and Communication Technology Centre for Quantum Software and Information University of Technology Sydney Data Sciences & Analytics Group Department of Electrical & Computer Engineering Pacific Northwest National Laboratory North Carolina State University Department of Computer Science Department of Physics High Performance Computing Group University of Toronto University of Washington Pacific Northwest National Laboratory

Quantum neural networks (QNNs) are a framework for creating quantum algorithms that promises to combine the speedups of quantum computation with the widespread successes of machine learning. A major challenge in QNN development is a concentration of measure phenomenon known as a barren plateau that leads to exponentially small gradients for a range of QNNs models. In this work, we examine the assumptions that give rise to barren plateaus and show that an unbounded loss function can circumvent the existing no-go results. We propose a training algorithm that minimizes the maximal Rényi divergence of order two and present techniques for gradient computation. We compute the closed form of the gradients for Unitary QNNs and Quantum Boltzmann Machines and provide sufficient conditions for the absence of barren plateaus in these models. We demonstrate our approach in two use cases: thermal state learning and Hamiltonian learning. In our numerical experiments, we observed rapid convergence of our training loss function and frequently archived a 99% average fidelity in fewer than 100 epochs. © 2021, CC BY.

关键词： Quantum computers

Outage Performance of Uplink Rate Splitting Multiple Access with Randomly Deployed Users

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Lu, Huabing Xie, Xianzhong Shi, Zhaoyuan Lei, Hongjiang Zhao, Nan Cai, Jun The Key Laboratory of Intelligent Control and Optimization for Industrial Equipment of Ministry of Education Dalian University of Technology Dalian116024 China The School of Computer Science and Technology Chongqing University of Posts and Telecommunications Chongqing400065 China The Key Laboratory of Intelligent Perception and Computing of Anhui Province Anqing Normal University Anqing246011 China The School of Communication and Information Engineering Chongqing University of Posts and Telecommunications Chongqing400065 China Department of Electrical and Computer Engineering Concordia University MontrealQCH3G 1M8 Canada

With the rapid proliferation of smart devices in wireless networks, more powerful technologies are expected to fulfill the network requirements of high throughput, massive connectivity, and diversify quality of service. To this end, rate splitting multiple access (RSMA) is proposed as a promising solution to improve spectral efficiency and provide better fairness for the next-generation mobile networks. In this paper, the outage performance of uplink RSMA transmission with randomly deployed users is investigated, taking both user scheduling schemes and power allocation strategies into consideration. Specifically, the greedy user scheduling (GUS) and cumulative distribution function (CDF) based user scheduling (CUS) schemes are considered, which could maximize the rate performance and guarantee scheduling fairness, respectively. Meanwhile, we re-investigate cognitive power allocation (CPA) strategy, and propose a new rate fairness-oriented power allocation (FPA) strategy to enhance the scheduled users' rate fairness. By employing order statistics and stochastic geometry, an analytical expression of the outage probability for each scheduling scheme combining power allocation is derived to characterize the performance. To get more insights, the achieved diversity order of each scheme is also derived. Theoretical results demonstrate that both GUS and CUS schemes applying CPA or FPA strategy can achieve full diversity orders, and the application of CPA strategy in RSMA can effectively eliminate the secondary user's diversity order constraint from the primary user. Simulation results corroborate the accuracy of the analytical expressions, and show that the proposed FPA strategy can achieve excellent rate fairness performance in high signal-to-noise ratio region. Copyright © 2022, The Authors. All rights reserved.

关键词： Wireless networks

Cramér-rao bound optimization for joint radar-communication design

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Liu, Fan Liu, Ya-Feng Li, Ang Masouros, Christos Eldar, Yonina C. The Department of Electrical and Electronic Engineering Southern University of Science and Technology Shenzhen518055 China The State Key Laboratory of Scientific and Engineering Computing Institute of Computational Mathematicsand Scientific/Engineering Computing Academy of Mathematics and Systems Science Chinese Academy of Sciences Beijing100190 China The School of Information and Communications Engineering Faculty of Electronic and Information Engineering Xi’an Jiaotong University Xi’anShaanxi710049 China The Department of Electronic and Electrical Engineering University College London LondonWC1E 7JE United Kingdom The Faculty of Mathematics and Computer Science Weizmann Institute of Science Rehovot Israel

In this paper, we propose multi-input multi-output (MIMO) beamforming designs towards joint radar sensing and multi-user communications. We employ the Cramér-Rao bound (CRB) as a performance metric of target estimation, under both point and extended target scenarios. We then propose minimizing the CRB of radar sensing while guaranteeing a pre-defined level of signal-to-interference-plus-noise ratio (SINR) for each communication user. For the single-user scenario, we derive a closed form for the optimal solution for both cases of point and extended targets. For the multi-user scenario, we show that both problems can be relaxed into semidefinite programming by using the semidefinite relaxation approach, and prove that the global optimum can always be obtained. Finally, we demonstrate numerically that the globally optimal solutions are reachable via the proposed methods, which provide significant gains in target estimation performance over state-of-the-art benchmarks. Copyright © 2021, The Authors. All rights reserved.

关键词： Signal to noise ratio

EdgeLens: Deep Learning based Object Detection in Integrated IoT, Fog and Cloud computing Environments 4

学校读者我要写书评

暂无评论

EdgeLens: Deep Learning based Object Detection in Integrated...

4th International Conference on information Systems and computer Networks, ISCON 2019

作者： Tuli, Shreshth Basumatary, Nipam Buyya, Rajkumar CLOUDS Laboratory School of Computing and Information Systems University of Melbourne Australia Department of Computer Science and Engineering Delhi India Madras India

ISBN: (纸本)9781728136516

Data-intensive applications are growing at an increasing rate and there is a growing need to solve scalability and high-performance issues in them. By the advent of Cloud computing paradigm, it became possible to harness remote resources to build and deploy these applications. In recent years, new set of applications and services based on Internet of Things (IoT) paradigm, require to process large amount of data in very less time. Among them surveillance and object detection have gained prime importance, but cloud is unable to bring down the network latencies to meet the response time requirements. This problem is solved by Fog computing which harnesses resources in the edge of the network along with remote cloud resources as required. However, there is still a lack of frameworks that are successfully able to integrate sophisticated software and applications, especially deep learning, with fog and cloud computing environments. In this work, we propose a framework to deploy deep learning-based applications in fog-cloud environments to harness edge and cloud resources to provide better service quality for such applications. Our proposed framework, called EdgeLens, adapts to the application or user requirements to provide high accuracy or low latency modes of services. We also tested the performance of the software in terms of accuracy, response time, jitter, network bandwidth and power consumption and show how EdgeLens adapts to different service requirements. © 2019 IEEE.

关键词： Object detection

Evaluating Large Language Models for Radiology Natural Language Processing

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Liu, Zhengliang Zhong, Tianyang Li, Yiwei Zhang, Yutong Pan, Yi Zhao, Zihao Dong, Peixin Cao, Chao Liu, Yuxiao Shu, Peng Wei, Yaonai Wu, Zihao Ma, Chong Wang, Jiaqi Wang, Sheng Zhou, Mengyue Jiang, Zuowei Li, Chunlin Holmes, Jason Xu, Shaochen Zhang, Lu Dai, Haixing Zhang, Kai Zhao, Lin Chen, Yuanhao Liu, Xu Wang, Peilong Yan, Pingkun Liu, Jun Ge, Bao Sun, Lichao Zhu, Dajiang Li, Xiang Liu, Wei Cai, Xiaoyan Hu, Xintao Jiang, Xi Zhang, Shu Zhang, Xin Zhang, Tuo Zhao, Shijie Li, Quanzheng Zhu, Hongtu Shen, Dinggang Liu, Tianming School of Computing University of Georgia GA United States School of Automation Northwestern Polytechnical University Xi'An710072 China Department of Radiology Massachusetts General Hospital Harvard Medical School MA United States Department of Computer Science and Engineering University of Texas ArlingtonTX United States School of Life Science and Technology University of Electronic Science and Technology of China Chengdu611731 China Glasgow College University of Electronic Science and Technology of China Chengdu611731 China Department of Radiation Oncology Mayo Clinic PhoenixAZ United States Institute of Medical Research Northwestern Polytechnical University Xi'An710072 China School of Physics and Information Technology Shaanxi Normal University Xi'An710119 China School of Computer Science Northwestern Polytechnical University Xi'An710072 China School of Biomedical Engineering ShanghaiTech University Shanghai Clinical Research and Trial Center Shanghai201210 China Shanghai United Imaging Intelligence Co. Ltd. China Department of Biostatistics University of North Carolina at Chapel Hill Chapel HillNC27599 United States Department of Biomedical Engineering Center for Biotechnology Interdisciplinary Studies Rensselaer Polytechnic Institute TroyNY12180 United States Department of Radiology Second Xiangya Hospital Changsha410011 China Shanghai Clinical Research Trial Center China School of Biomedical Engineering Shanghai Jiao Tong University Shanghai200240 China Department of Computer Science and Engineering Lehigh University PA United States Department of Linguistics Department of Computer Science Dartmouth College NH United States Lingang Laboratory Shanghai200031 China

The rise of large language models (LLMs) has marked a pivotal shift in the field of natural language processing (NLP). LLMs have revolutionized a multitude of domains, and they have made a significant impact in the medical field. Large language models are now more abundant than ever, and many of these models exhibit bilingual capabilities, proficient in both English and Chinese. However, a comprehensive evaluation of these models remains to be conducted. This lack of assessment is especially apparent within the context of radiology NLP. This study seeks to bridge this gap by critically evaluating thirty two LLMs in interpreting radiology reports, a crucial component of radiology NLP. Specifically, the ability to derive impressions from radiologic findings is assessed. The outcomes of this evaluation provide key insights into the performance, strengths, and weaknesses of these LLMs, informing their practical applications within the medical domain. © 2023, CC BY.

关键词： Radiology