检索结果-内蒙古大学图书馆

Animating turbulent fluid with a robust and efficient high-order advection method

学校读者我要写书评

暂无评论

Animating turbulent fluid with a robust and efficient high-o...

作者： Zhu, Jian Li, Silong Cai, Ruichu Hao, Zhifeng Huang, Guoheng Sheng, Bin Wu, Enhua School of Computers Guangdong University of Technology Guangzhou China School of Mathematics and Big Data Foshan University Foshan China Department of Computer Science & Engineering Shanghai Jiao Tong University Shanghai China State Key Laboratory of Computer Science Institute of Software Chinese Academy of Sciences Beijing China

The accuracy of advection has a great influence on the visual effect of fluid simulation. Constrained interpolation profile (CIP) method has been an important advection scheme because of its third-order accuracy and the fact that it only needs to be performed over a compact stencil, but extending it to high-dimensional advection equations is not easy, because it involves complex calculations and large memory overheads, and is usually unstable. In this article, we propose a stable and efficient three-dimensional (3D) CIP scheme which can maintain high accuracy but requires low computation and memory cost. We first construct an efficient two-dimensional (2D) CIP scheme based on dimensional splitting and local Taylor expansions, and then propose an effective way to extend it for 3D applications without decreasing the computational accuracy or affecting the stability. The experimental results show the advantages of our method over the state-of-the-art advection schemes. © 2020 John Wiley & Sons, Ltd.

关键词： Advection

Diff9D: Diffusion-Based Domain-Generalized Category-Level 9-DoF Object Pose Estimation

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Liu, Jian Sun, Wei Yang, Hui Deng, Pengchao Liu, Chongpei Sebe, Nicu Rahmani, Hossein Mian, Ajmal National Engineering Research Center for Robot Visual Perception and Control Technology College of Electrical and Information Engineering School of Robotics State Key Laboratory of Advanced Design and Manufacturing for Vehicle Body Hunan University Changsha410082 China Institute of Artificial Intelligence and Robotics Xi’an Jiaotong University Xi’an710049 China Department of Information Engineering and Computer Science University of Trento Trento38123 Italy School of Computing and Communications Lancaster University LA1 4YW United Kingdom Department of Computer Science The University of Western Australia WA6009 Australia

Nine-degrees-of-freedom (9-DoF) object pose and size estimation is crucial for enabling augmented reality and robotic manipulation. Category-level methods have received extensive research attention due to their potential for generalization to intra-class unknown objects. However, these methods require manual collection and labeling of large-scale real-world training data. To address this problem, we introduce a diffusion-based paradigm for domain-generalized category-level 9-DoF object pose estimation. Our motivation is to leverage the latent generalization ability of the diffusion model to address the domain generalization challenge in object pose estimation. This entails training the model exclusively on rendered synthetic data to achieve generalization to real-world scenes. We propose an effective diffusion model to redefine 9-DoF object pose estimation from a generative perspective. Our model does not require any 3D shape priors during training or inference. By employing the Denoising Diffusion Implicit Model, we demonstrate that the reverse diffusion process can be executed in as few as 3 steps, achieving near real-time performance. Finally, we design a robotic grasping system comprising both hardware and software components. Through comprehensive experiments on two benchmark datasets and the real-world robotic system, we show that our method achieves state-of-the-art domain generalization performance. Our code will be made public at https://***/CNJianLiu/Diff9D. Copyright © 2025, The Authors. All rights reserved.

关键词： Augmented reality

Test-Time Domain Adaptation by Learning Domain-Aware Batch Normalization

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Wu, Yanan Chi, Zhixiang Wang, Yang Plataniotis, Konstantinos N. Feng, Songhe Key Laboratory of Big Data & Artificial Intelligence in Transportation Ministry of Education Beijing Jiaotong University Beijing100044 China School of Computer and Information Technology Beijing Jiaotong University Beijing100044 China The Edward S Rogers Sr. ECE Department University of Toronto TorontoM5S3G8 Canada Department of Computer Science and Software Engineering Concordia University MontrealH3G2J1 Canada

Test-time domain adaptation aims to adapt the model trained on source domains to unseen target domains using a few unlabeled images. Emerging research has shown that the label and domain information is separately embedded in the weight matrix and batch normalization (BN) layer. Previous works normally update the whole network naively without explicitly decoupling the knowledge between label and domain. As a result, it leads to knowledge interference and defective distribution adaptation. In this work, we propose to reduce such learning interference and elevate the domain knowledge learning by only manipulating the BN layer. However, the normalization step in BN is intrinsically unstable when the statistics are re-estimated from a few samples. We find that ambiguities can be greatly reduced when only updating the two affine parameters in BN while keeping the source domain statistics. To further enhance the domain knowledge extraction from unlabeled data, we construct an auxiliary branch with label-independent self-supervised learning (SSL) to provide supervision. Moreover, we propose a bi-level optimization based on meta-learning to enforce the alignment of two learning objectives of auxiliary and main branches. The goal is to use the auxiliary branch to adapt the domain and benefit main task for subsequent inference. Our method keeps the same computational cost at inference as the auxiliary branch can be thoroughly discarded after adaptation. Extensive experiments show that our method outperforms the prior works on five WILDS real-world domain shift datasets. Our method can also be integrated with methods with label-dependent optimization to further push the performance boundary. Our code is available at https://***/ynanwu/MABN. © 2023, CC BY.

关键词： Time domain analysis

MigrationAdvisor: Recommending Library Migrations from Large-Scale Open-Source Data

学校读者我要写书评

暂无评论

MigrationAdvisor: Recommending Library Migrations from Large...

International Conference on software Engineering - Companion, ICSE, Companion

作者： Hao He Yulin Xu Xiao Cheng Guangtai Liang Minghui Zhou Department of Computer Science and Technology Peking University Beijing China Software Analysis Lab Huawei Technologies Co. Ltd. China Key Laboratory of High Confidence Software Technologies Ministry of Education China

During software maintenance, developers may need to migrate an already in-use library to another library with similar functionalities. However, it is difficult to make the optimal migration decision with limited information, knowledge, or expertise. In this paper, we present MigrationAdvisor, an evidence-based tool to recommend library migration targets through intelligent analysis upon a large number of GitHub repositories and Java libraries. The migration advisories are provided through a search engine style web service where developers can seek migration suggestions for a specific library. We conduct systematic evaluations on the correctness of results, and evaluate the usefulness of the tool by collecting usage feedback from industry developers. Video: https://***/4I75W22TqwQ.

关键词： Java software maintenance Systematics Web services Tools Libraries software development management

NLocalSAT: Boosting local search with solution prediction

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Zhang, Wenjie Sun, Zeyu Zhu, Qihao Li, Ge Cai, Shaowei Xiong, Yingfei Zhang, Lu MoESoftware Institute Department of Computer Science and Technology Peking University State Key Laboratory of Computer Science Institute of Software Chinese Academy of Sciences School of Computer Science and Technology University of Chinese Academy of Sciences

The boolean satisfiability problem is a famous NP-complete problem in computer science. An effective way for this problem is the stochastic local search (SLS). However, in this method, the initialization is assigned in a random manner, which impacts the effectiveness of SLS solvers. To address this problem, we propose NLocalSAT. NLocalSAT combines SLS with a solution prediction model, which boosts SLS by changing initialization assignments with a neural network. We evaluated NLocalSAT on five SLS solvers (CCAnr, Sparrow, CPSparrow, YalSAT, and probSAT) with problems in the random track of SAT Competition 2018. The experimental results show that solvers with NLocalSAT achieve 27% ∼ 62% improvement over the original SLS solvers. Copyright © 2020, The Authors. All rights reserved.

关键词： Stochastic systems

GRATIS: Deep Learning Graph Representation with Task-specific Topology and Multi-dimensional Edge Features

学校读者我要写书评

暂无评论

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

Improving Heterogeneous Model Reuse by Density Estimation

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Tang, Anke Luo, Yong Hu, Han He, Fengxiang Su, Kehua Du, Bo Chen, Yixin Tao, Dacheng School of Computer Science National Engineering Research Center for Multimedia Software Institute of Artificial Intelligence Hubei Key Laboratory of Multimedia and Network Communication Engineering Wuhan University China Hubei Luojia Laboratory Wuhan China School of Information and Electronics Beijing Institute of Technology China JD Explore Academy *** Inc. China Department of CSE Washington University in St. Louis United States The University of Sydney Australia

This paper studies multiparty learning, aiming to learn a model using the private data of different participants. Model reuse is a promising solution for multiparty learning, assuming that a local model has been trained for each party. Considering the potential sample selection bias among different parties, some heterogeneous model reuse approaches have been developed. However, although pre-trained local classifiers are utilized in these approaches, the characteristics of the local data are not well exploited. This motivates us to estimate the density of local data and design an auxiliary model together with the local classifiers for reuse. To address the scenarios where some local models are not well pre-trained, we further design a multiparty cross-entropy loss for calibration. Upon existing works, we address a challenging problem of heterogeneous model reuse from a decision theory perspective and take advantage of recent advances in density estimation. Experimental results on both synthetic and benchmark data demonstrate the superiority of the proposed method. Copyright © 2023, The Authors. All rights reserved.

关键词： Decision theory

A survey of orthogonal moments for image representation: Theory, implementation, and evaluation

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Qi, Shuren Zhang, Yushu Wang, Chao Zhou, Jiantao Cao, Xiaochun College of Computer Science and Technology Nanjing University of Aeronautics and Astronautics Nanjing China Collaborative Innovation Center of Novel Software Technology and Industrialization Nanjing China State Key Laboratory of Internet of Things for Smart City University of Macau China Department of Computer and Information Science University of Macau China School of Cyber Science and Technology Sun Yat-sen University Shenzhen China

Image representation is an important topic in computer vision and pattern recognition. It plays a fundamental role in a range of applications towards understanding visual contents. Moment-based image representation has been reported to be effective in satisfying the core conditions of semantic description due to its beneficial mathematical properties, especially geometric invariance and independence. This paper presents a comprehensive survey of the orthogonal moments for image representation, covering recent advances in fast/accurate calculation, robustness/invariance optimization, definition extension, and application. We also create a software package for a variety of widely-used orthogonal moments and evaluate such methods in a same base. The presented theory analysis, software implementation, and evaluation results can support the community, particularly in developing novel techniques and promoting real-world applications. Copyright © 2021, The Authors. All rights reserved.

关键词： Image representation

μAFL: Non-intrusive Feedback-driven Fuzzing for Microcontroller Firmware

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Li, Wenqiang Lin, Jingqiang Shi, Jiameng Wang, Wei Li, Fengjun Guan, Le State Key Laboratory of Information Security Institute of Information Engineering Chinese Academy of Sciences School of Cyber Security UCAS Beijing China School of Cyber Security University of Science and Technology of China Hefei Anhui China Department of Computer Science the University of Georgia AthensGA United States State Key Laboratory of Information Security Institute of Information Engineering Chinese Academy of Sciences Beijing China Department of Electrical Engineering and Computer Science the University of Kansas LawrenceKS United States

Fuzzing is one of the most effective approaches to finding software flaws. However, applying it to microcontroller firmware incurs many challenges. For example, rehosting-based solutions cannot accurately model peripheral behaviors and thus cannot be used to fuzz the corresponding driver code. In this work, we present μAFL, a hardware-in-the-loop approach to fuzzing microcontroller firmware. It leverages debugging tools in existing embedded system development to construct an AFL-compatible fuzzing framework. Specifically, we use the debug dongle to bridge the fuzzing environment on the PC and the target firmware on the microcontroller device. To collect code coverage information without costly code instrumentation, μAFL relies on the ARM ETM hardware debugging feature, which transparently collects the instruction trace and streams the results to the PC. However, the raw ETM data is obscure and needs enormous computing resources to recover the actual instruction flow. We therefore propose an alternative representation of code coverage, which retains the same path sensitivity as the original AFL algorithm, but can directly work on the raw ETM data without matching them with disassembled instructions. To further reduce the workload, we use the DWT hardware feature to selectively collect runtime information of interest. We evaluated μAFL on two real evaluation boards from two major vendors: NXP and STMicroelectronics. With our prototype, we discovered ten zero-day bugs in the driver code shipped with the SDK of STMicroelectronics and three zero-day bugs in the SDK of NXP. Eight CVEs have been allocated for them. Considering the wide adoption of vendor SDKs in real products, our results are alarming. Copyright © 2022, The Authors. All rights reserved.

关键词： Firmware