检索结果-内蒙古大学图书馆

arXiv 2024年

作者： Meng, Zheling Peng, Bo Dong, Jing Center for Research on Intelligent Perception and Computing State Key Laboratory of Multimodal Artificial Intelligence Systems Institute of Automation Chinese Academy of Sciences China

Watermarking is a tool for actively identifying and attributing the images generated by latent diffusion models. Existing methods face the dilemma of image quality and watermark robustness. Watermarks with superior image quality usually have inferior robustness against attacks such as blurring and JPEG compression, while watermarks with superior robustness usually significantly damage image quality. This dilemma stems from the traditional paradigm where watermarks are injected and detected in pixel space, relying on pixel perturbation for watermark detection and resilience against attacks. In this paper, we highlight that an effective solution to the problem is to both inject and detect watermarks in the latent diffusion space, and propose Latent Watermark with a progressive training strategy. It weakens the direct connection between quality and robustness and thus alleviates their contradiction. We conduct evaluations on two datasets and against 10 watermark attacks. Six metrics measure the image quality and watermark robustness. Results show that compared to the recently proposed methods such as StableSignature, StegaStamp, RoSteALS, LaWa, TreeRing, and DiffuseTrace, LW not only surpasses them in terms of robustness but also offers superior image quality. Our code will be available at https://***/RichardSunnyMeng/LatentWatermark. Copyright © 2024, The Authors. All rights reserved.

关键词： Pixels

来源：评论

学校读者我要写书评

暂无评论

Makespan and Security-Aware Workflow Scheduling for Cloud Service Cost Minimization Using Firefly Optimizer 22nd

Makespan and Security-Aware Workflow Scheduling for Cloud ...

引用

22nd International Conference on Algorithms and architectures for Parallel Processing, ICA3PP 2022

作者： Zhou, Chengliang Wang, Tian Li, Liying Sun, Jin Zhou, Junlong School of Computer Science and Engineering Nanjing University of Science and Technology Nanjing210094 China State Key Laboratory of Computer Architecture Institute of Computing Technology Chinese Academy of Sciences Beijing100190 China National Trusted Embedded Software Engineering Technology Research Center East China Normal University Shanghai200062 China

ISBN: (纸本)9783031226762

As efficient commercial information technology, cloud computing has attracted more and more users to submit their requests to the cloud platform and pay for them based on the amount and quality of services. One of the most important concerns of cloud service providers is to minimize the monetary cost for completing users’ requests while meeting constraints on the quality of services such as makespan and security. To solve this concern, this paper proposes a makespan and security-aware workflow scheduling method based on an improved firefly optimizer that consists of a new solution initialization scheme, a firefly position updating scheme, a firefly-to-solution mapping operator, and two task-to-virtual machine assignment schemes. We carry out extensive simulation experiments on real-world workflows to validate our proposed workflow scheduling method. The results reveal that the monetary cost reduction achieved by our method can be up to 54.0% compared to a baseline and two state-of-the-art approaches. © 2023, Springer Nature Switzerland AG.

关键词： Cloud computing

来源：评论

学校读者我要写书评

暂无评论

Word frequency approximation for Chinese without using manually-annotated corpus

Word frequency approximation for Chinese without using manua...

引用

7th International Conference on Computational Linguistics and intelligent Text Processing, CICLing 2006

作者： Sun, Maosong Zhang, Zhengcao T'sou, Benjamin Ka-Yin Lu, Huaming State Key Laboratory of Intelligent Technology and Systems Department of Computer Science and Technology Tsinghua University Beijing 100084 China Language Information Sciences Research Center City University of Hong Kong Hong Kong School of Business Beijing Institute of Machinery Beijing 100085 China

ISBN: (纸本)3540322051

Word frequencies play important roles in a variety of NLP-related applications. Word frequency estimation for Chinese is a big challenge due to characteristics of Chinese, in particular word-formation and word segmentation. This paper concerns the issue of word frequency estimation in the condition that we only have a Chinese wordlist and a raw Chinese corpus with arbitrarily large size, and do not perform any manual annotation to the corpus. Several realistic schemes for approximating word frequencies under the framework of STR (frequency of string of characters as an approximation of word frequency) and MM (Maximal matching) are presented. Large-scale experiments indicate that the proposed scheme, MinMaxMM, can significantly benefit the estimation of word frequencies, though its performance is still not very satisfactory in some cases. © Springer-Verlag Berlin Heidelberg 2006.

关键词： Word processing

来源：评论

学校读者我要写书评

暂无评论

Generative artificial intelligence and its applications in materials science:Current situation and future perspectives

引用

Journal of Materiomics 2023年第4期9卷 798-816页

作者： Yue Liu Zhengwei Yang Zhenyao Yu Zitu Liu Dahui Liu Hailong Lin Mingqing Li Shuchang Ma Maxim Avdeev Siqi Shi School of Computer Engineering and Science Shanghai UniversityShanghai200444China State Key Laboratory of Advanced Special Steel School of Materials Science and EngineeringShanghai UniversityShanghai200444China Materials Genome Institute Shanghai UniversityShanghai200444China Shanghai Engineering Research Center of Intelligent Computing System Shanghai200444China Australian Nuclear Science and Technology Organisation Sydney2232Australia School of Chemistry The University of SydneySydney2006Australia

Generative Artificial Intelligence(GAI)is attracting the increasing attention of materials community for its excellent capability of generating required *** the introduction of Prompt paradigm and reinforcement learning from human feedback(RLHF),GAI shifts from the task-specific to general pattern gradually,enabling to tackle multiple complicated tasks involved in resolving the structure-activity ***,we review the development status of GAI comprehensively and analyze pros and cons of various generative models in the view of *** applications of task-specific generative models involving materials inverse design and data augmentation are also *** ChatGPT as an example,we explore the potential applications of general GAI in generating multiple materials content,solving differential equation as well as querying materials ***,we summarize six challenges encountered for the use of GAI in materials science and provide the corresponding *** work paves the way for providing effective and explainable materials data generation and analysis approaches to accelerate the materials research and development.

关键词： Machine learning Artificial intelligence Generative artificial intelligence Materials science Novel materials discovery Deep learning

来源：评论

学校读者我要写书评

暂无评论

Multiscale Bilateral Attention Fusion Network for Pansharpening

IEEE Transactions on Artificial Intelligence

引用

IEEE Transactions on Artificial Intelligence 2024年第11期5卷 5828-5843页

作者： Guo, Zhongyuan Li, Jiawei Lei, Jia Liu, Jinyuan Zhou, Shihua Wang, Bin Kasabov, Nikola K. Dalian University Key Laboratory of Advanced Design and Intelligent Computing Ministry of Education School of Software Engineering Dalian116622 China University of the Science and Technology Beijing School of Computer and Communication Engineering Beijing100083 China Dalian University of Technology School of Mechanical Engineering Dalian116024 China Auckland University of Technology Knowledge Engineering and Discovery Research Institute Auckland1061 New Zealand University of Ulster Intelligent Systems Research Center LondonderryBT48 7JL United Kingdom Bulgarian Academy of Sciences IICT Sofia1000 Bulgaria

High-resolution multispectral (HRMS) images combine spatial and spectral information originating from panchromatic (PAN) and reduced-resolution multispectral (LRMS) images. Pansharpening performs well and is widely used to obtain HRMS images. However, most pansharpening approaches determine the ratio of PAN and LRMS images through direct interpolation, which may introduce artifacts and distort the color of the fused results. To address this issue, an unsupervised progressive pansharpening framework, MSBANet, is proposed, which adopts a multistage fusion strategy. Each stage contains an attention interactive extraction module (AIEM) and a multiscale bilateral fusion module (MBFM). The AIEM extracts spatial and spectral features from input images and captures the correlations between features. The MBFM can efficiently integrate information from the AIEM and improve MSBANet context awareness. We design a hybrid loss function that enhances the ability of the fusion network to store spectral and texture details. In qualitative and quantitative experimental studies on four datasets, MSBANet outperformed state-of-the-art pansharpening techniques. The code will be released. © 2024 IEEE.

关键词： Data mining

来源：评论

学校读者我要写书评

暂无评论

Communication Lower Bound in Convolution Accelerators

Communication Lower Bound in Convolution Accelerators

引用

IEEE Symposium on High-Performance computer architecture

作者： Xiaoming Chen Yinhe Han Yu Wang Center for Intelligent Computing Systems State Key Laboratory of Computer Architecture Institute of Computing Technology Chinese Academy of Sciences Beijing China University of Chinese Academy of Sciences Beijing China Department of Electronic Engineering Tsinghua University Beijing China

ISBN: (数字)9781728161495

ISBN: (纸本)9781728161501

In current convolutional neural network (CNN) accelerators, communication (i.e., memory access) dominates the energy consumption. This work provides comprehensive analysis and methodologies to minimize the communication for CNN accelerators. For the off-chip communication, we derive the theoretical lower bound for any convolutional layer and propose a dataflow to reach the lower bound. This fundamental problem has never been solved by prior studies. The on-chip communication is minimized based on an elaborate workload and storage mapping scheme. We in addition design a communication-optimal CNN accelerator architecture. Evaluations based on the 65nm technology demonstrate that the proposed architecture nearly reaches the theoretical minimum communication in a three-level memory hierarchy and it is computation dominant. The gap between the energy efficiency of our accelerator and the theoretical best value is only 37-87%.

关键词： System-on-chip Convolution Random access memory Convolutional codes Memory management Microsoft Windows Kernel

来源：评论

学校读者我要写书评

暂无评论

Freespace Optical Flow Modeling for Automated Driving

arXiv

引用

arXiv 2023年

作者： Feng, Yi Zhang, Ruge Du, Jiayuan Chen, Qijun Fan, Rui College of Electronics & Information Engineering Shanghai Research Institute for Intelligent Autonomous Systems The State Key Laboratory of Intelligent Autonomous Systems Frontiers Science Center for Intelligent Autonomous Systems Tongji University Shanghai201804 China High-Performance Computer Research Center Institute of Computing Technology Chinese Academy of Sciences Beijing100190 China

— Optical flow and disparity are two informative visual features for autonomous driving perception. They have been used for a variety of applications, such as obstacle and lane detection. The concept of "U-V-Disparity" has been widely explored in the literature, while its counterpart in optical flow has received relatively little attention. Traditional motion analysis algorithms estimate optical flow by matching correspondences between two successive video frames, which limits the full utilization of environmental information and geometric constraints. Therefore, we propose a novel strategy to model optical flow in the collision-free space (also referred to as drivable area or simply freespace) for intelligent vehicles, with the full utilization of geometry information in a 3D driving environment. We provide explicit representations of optical flow and deduce the quadratic relationship between the optical flow component and the vertical coordinate. Through extensive experiments on several public datasets, we demonstrate the high accuracy and robustness of our model. Additionally, our proposed freespace optical flow model boasts a diverse array of applications within the realm of automated driving, providing a geometric constraint in freespace detection, vehicle localization, and more. We have made our source code publicly available at https://***/FSOF. Copyright © 2023, The Authors. All rights reserved.

关键词： Autonomous vehicles

来源：评论

学校读者我要写书评

暂无评论

Communication lower bound in convolution accelerators

arXiv

引用

arXiv 2019年

作者： Chen, Xiaoming Han, Yinhe Wang, Yu Center for Intelligent Computing Systems State Key Laboratory of Computer Architecture Institute of Computing Technology Chinese Academy of Sciences Beijing China University of Chinese Academy of Sciences Beijing China Department of Electronic Engineering Tsinghua University Beijing China

In current convolutional neural network (CNN) accelerators, communication (i.e., memory access) dominates the energy consumption. This work provides comprehensive analysis and methodologies to minimize the communication for CNN accelerators. For the off-chip communication, we derive the theoretical lower bound for any convolutional layer and propose a dataflow to reach the lower bound. This fundamental problem has never been solved by prior studies. The on-chip communication is minimized based on an elaborate workload and storage mapping *** in addition design a communication-optimal CNN accelerator architecture. Evaluations based on the 65nm technology demonstrate that the proposed architecture nearly reaches the theoretical minimum communication in a threelevel memory hierarchy and it is computation dominant. The gap between the energy efficiency of our accelerator and the theoretical best value is only 37-87%. Copyright © 2019, The Authors. All rights reserved.

关键词： Acceleration

来源：评论

学校读者我要写书评

暂无评论

Self-supervised fast reconstruction method for diffusion MRI based on multi-directional assistance 17

Self-supervised fast reconstruction method for diffusion MRI...

引用

17th IEEE International Conference on Signal Processing, ICSP 2024

作者： Wu, Yuxin Zhang, Jian Wang, Lihui Cao, Ying Wu, Linhai Wu, Yunjia Ye, Chen Zhu, Yuemin Guizhou University Key Laboratory of Intelligent Medical Image Analysis and Precise Diagnosis of Guizhou Province Engineering Research Center of Text Computing & Cognitive Intelligence Ministry of Education State Key Laboratory of Public Big Data College of Computer Science and Technology Guiyang China Univ Lyon Insa Lyon Cnrs Inserm Creatis Umr 5220 U1206 France

ISBN: (纸本)9798350387384

Diffusion MRI (dMRI) is widely used for the detection and diagnosis of various pathologies due to its non-invasive nature. However, its signal acquisition process is relatively slow and susceptible to motions. In order to accelerate reconstruction process, many deep learning-based methods have been developed in recent years to achieve promising results, while most of them are supervised based methods and require fully sampled data which are difficult to obtain in practical applications to train the network. Self-supervised based methods were proposed to deal with this problem to a certain extent, however, they are devoted only to conventional MRI data, ignoring the correlation between the directions of dMRI data. To address this issue, we propose a self-supervised fast reconstruction method for dMRI based on multi-directional assistance. The method better utilizes the information between dMRI data directions by Partition-Replace operation, cleverly constructing data pairs and designing effective self-supervised strategy for bi-directional prediction, which can overcome the problem of data incompleteness and guide the model to reconstruct unsampled signals in spite of the difficulty of acquiring fully sampled data. Experimental results show that our method achieves better reconstruction in the absence of fully sampled data, even with an 8-fold acceleration factor. © 2024 IEEE.

关键词： Self-supervised learning

来源：评论

学校读者我要写书评

暂无评论

Penta-Encoder with Medical Transformer for Incomplete Multimodal Learning of Brain Tumor Segmentation 17

Penta-Encoder with Medical Transformer for Incomplete Multim...

引用

17th IEEE International Conference on Signal Processing, ICSP 2024

作者： Yu, Guohui Wang, Lihui Chen, Qijian Wang, Li Tang, Kun Cheng, Xinyu Zhu, Yuemin Guizhou University Key Laboratory of Intelligent Medical Image Analysis and Precise Diagnosis of Guizhou Province Engineering Research Center of Text Computing & Cognitive Intelligence Ministry of Education State Key Laboratory of Public Big Data College of Computer Science and Technology Guiyang China Univ Lyon Insa Lyon Cnrs Inserm Creatis Umr 5220 U1206 Lyon France

ISBN: (纸本)9798350387384

Accurate brain tumor segmentation of magnetic resonance imaging (MRI) images requires the integration of multimodal data in effective collaborative learning. However, clinical scenarios often face missing modalities, significantly impacting segmentation performance. In this paper, we propose the penta-encoder with medical transformer (Penta-MedTrans) for incomplete multimodal learning, which consists of four main components: a modality-specific encoder (MSE), a modality-dynamic encoder (MDE), a multimodal fusion module (MMFM) and a convolutional decoder. The MSE extracts unique features for each modality, while the MDE captures inter-modal semantics to address missing modalities. The MMFM establishes and aligns long-range correlations between modal-invariant features and global semantics of tumor regions. The convolutional decoder generates robust segmentation results by progressively upsampling and fusing modality-invariant features. We extensively validated our method on the BraTS 2020 and BraTS 2021 datasets for brain tumor segmentation. Results showed that our method outperforms SOTA for incomplete multimodal brain tumor segmentation across most subsets. © 2024 IEEE.

关键词： Semantic Segmentation

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：