检索结果-内蒙古大学图书馆

arXiv 2024年

作者： Jiang, Xiruo Yao, Yazhou Liu, Sheng Shen, Fumin Nie, Liqiang Hua, Xian-Sheng The School of Computer Science and Engineering Nanjing University of Science and Technology Nanjing China The State Key Laboratory of Virtual Reality Technology and Systems School of Computer Science and Engineering Beihang University Beijing China The School of Computer Science and Engineering University of Electronic Science and Technology Chengdu China Shenzhen China The Terminus Group Beijing China

Loss functions and sample mining strategies are essential components in deep metric learning algorithms. However, the existing loss function or mining strategy often necessitate the incorporation of additional hyperparameters, notably the threshold, which defines whether the sample pair is informative. The threshold provides a stable numerical standard for determining whether to retain the pairs. It is a vital parameter to reduce the redundant sample pairs participating in training. Nonetheless, finding the optimal threshold can be a time-consuming endeavor, often requiring extensive grid searches. Because the threshold cannot be dynamically adjusted in the training stage, we should conduct plenty of repeated experiments to determine the threshold. Therefore, we introduce a novel approach for adjusting the thresholds associated with both the loss function and the sample mining strategy. We design a static Asymmetric Sample Mining Strategy (ASMS) and its dynamic version Adaptive Tolerance ASMS (AT-ASMS), tailored for sample mining methods. ASMS utilizes differentiated thresholds to address the problems (too few positive pairs and too many redundant negative pairs) caused by only applying a single threshold to filter samples. AT-ASMS can adaptively regulate the ratio of positive and negative pairs during training according to the ratio of the currently mined positive and negative pairs. This meta-learning-based threshold generation algorithm utilizes a single-step gradient descent to obtain new thresholds. We combine these two threshold adjustment algorithms to form the Dual Dynamic Threshold Adjustment Strategy (DDTAS). Experimental results show that our algorithm achieves competitive performance on CUB200, Cars196, and SOP datasets. Our codes are available at https://***/NUST-Machine-Intelligence-laboratory/DDTAS. Copyright © 2024, The Authors. All rights reserved.

关键词： Image retrieval

来源：评论

学校读者我要写书评

暂无评论

Keynote Talk: Qualitative model based diagnosis of complex systems using decomposition 22

Keynote Talk: Qualitative model based diagnosis of complex s...

引用

Proceedings of the 7th International Conference on Sustainable Information engineering and Technology

作者： Katalin M. Hangos Systems and Control Laboratory Institute for Computer Science and Control Hungary and Department of Electrical Engineering and Information Systems University of Pannonia Hungary

ISBN: (纸本)9781450397117

Decomposition offers the potential to reduce the complexity of model-based optimization, prediction, control and diagnosis by accounting for the structure and sparsity of the describing model. Motivated by this fact, a rich and powerful collection of decomposition methods are available for model based diagnosis of large-scale complex dynamic systems, too. At the same time, one usually does not have enough information about a large-scale complex dynamic system to construct its precise enough model, so a kind of qualitative dynamic model is often used for the diagnosis [1]. Two structural decomposition based qualitative diagnostic methods are presented in this lecture, together with their component-driven system decomposition ***, a model-based diagnostic method is described that is able to detect and isolate non-technical losses (illegal loads) in low voltage electrical grids of one transformer area [2]. As a preliminary off-line step of the diagnosis, a powerful electrical decomposition method is proposed, which breaks down the overall network to subsystems with one feeder layout enabling to make the necessary computations efficient. The diagnostic method is based on analyzing the differences between the measured and model-predicted voltages. The uncertainty in the model parameters together with the measurement uncertainties are also taken into account to make the approach applicable in real-world cases. The proposed method is able to detect and localize multiple illegal loads, and the amount of the illegal consumption can also be *** a second case study, a high level decomposition approach for process system fault diagnosis using event traces is given [3], [4]. Using a simple component graph model behind the process system and the measured trace applied for the diagnosis, the method can find the root cause(s) of propagating failures between separate components. The method can connect individually operating lower-level component-specific diag

关键词：

来源：评论

学校读者我要写书评

暂无评论

Efficient and high precision target-driven fluid simulation based on spatial geometry features

Efficient and high precision target-driven fluid simulation ...

引用

作者： Zhou, Xiangyang Liu, Sinuo Zeng, Haokai Wang, Xiaokun Ban, Xiaojuan Beijing Advanced Innovation Center for Materials Genome Engineering University of Science and Technology Beijing Beijing China School of Intelligence Science and Technology University of Science and Technology Beijing Beijing China Key Laboratory of Intelligent Bionic Unmanned Systems University of Science and Technology Beijing Beijing China School of Computer Science Peking University Beijing China National Centrefor Computer Animation Bournemouth University Poole United Kingdom Institute of Materials Intelligent Technology Liaoning Academy of Materials Shenyang China

We proposed a novel target-driven fluid simulation method based on the weighted control model derived from the spatial geometric features of the target shape. First, the spatial geometric characteristics of the target model are taken into account to set the color field weights of control particles. This enabled the full expression of geometric characteristics of the target model, and improve the shape accuracy of controlled fluid. Then, the fluid is controlled to form the target shape under driving constraints, wherein we proposed a new adaptive constraint mechanism that enables efficient target shape generation. Finally, a new density constraint between the control particles and the controlled fluid particles is proposed to ensure the incompressibility of fluid during control. Compared to the state-of-the-art target-driven fluid control methods, our method achieves higher precision fluid control with higher efficiency. © 2023 John Wiley & Sons Ltd.

关键词： Hydrodynamics

来源：评论

学校读者我要写书评

暂无评论

Disentangling Spatio-Temporal Knowledge for Weakly Supervised Object Detection and Segmentation in Surgical Video

Disentangling Spatio-Temporal Knowledge for Weakly Supervise...

引用

IEEE Workshop on Applications of computer Vision (WACV)

作者： Guiqiu Liao Matjaz Jogan Sai Koushik Eric Eaton Daniel A. Hashimoto Department of Surgery PCASO Laboratory University of Pennsylvania Department of Electrical and Systems Engineering University of Pennsylvania Department of Computer and Information Science University of Pennsylvania

ISBN: (数字)9798331510831

ISBN: (纸本)9798331510848

Weakly supervised video object segmentation (WSVOS) enables the identification of segmentation maps without requiring extensive annotations of object masks, relying instead on coarse video labels indicating object presence. WSVOS in surgical videos is, however, more challenging due to the complex interaction of multiple transient objects, such as surgical tools moving in and out of the surgical field. In this scenario, state-of-the-art WSVOS methods struggle to learn accurate segmentation maps. We address this problem by introducing ViDeo Spatio-Temporal disentanglement Networks (VDST-Net), a framework to disentangle complex spatio-temporal object interactions using semi-decoupled knowledge distillation to predict high-quality class activation maps (CAMs). A teacher network is designed to help a temporal-reasoning student network resolve activation conflicts, as the student leverages temporal dependencies when specifics about object location and timing in the video are not provided. We demonstrate the efficacy of our framework on a challenging surgical video dataset where objects are, on average, present in less than 60% of annotated frames, and compare our method to state-of-the-art methods on surgical data and on a public dataset commonly used to benchmark WSVOS. Our method outperforms state-of-the-art techniques and generates accurate segmentation masks under video-level weak supervision. Our code is available at: https://***/PCASOlab/VDST-net.

关键词： Accuracy Weak supervision Surgery Object segmentation Object detection Streaming media Real-time systems Timing Object recognition Transient analysis

来源：评论

学校读者我要写书评

暂无评论

Reinforcement Learning Based Vertical Scaling for Hybrid Deployment in Cloud Computing 1

引用

17th International Conference on Bio-Inspired Computing: Theories and Applications, BIC-TA 2022

作者： Cao, Jianqi Li, Guiying Yang, Peng Guangdong Provincial Key Laboratory of Brain-Inspired Intelligent Computation Department of Computer Science and Engineering Southern University of Science and Technology Shenzhen518055 China Research Institute of Trustworthy Autonomous Systems Southern University of Science and Technology Shenzhen518055 China Department of Statistics and Data Science Southern University of Science and Technology Shenzhen518055 China

ISBN: (数字)9789819915491

ISBN: (纸本)9789819915484

To maximize the CPU utilization of the server, offline tasks are usually deployed to the same server where the online service is running. Considering the necessity to ensure the service quality of online services, it is common practice to isolate the resources of online services. How to set the resource quota for online services not only affects the service quality of online services, but also affects the number and the stability of offline tasks that can be run on the server. Traditional rule-based methods or prediction-based methods will cause over-provision and fail to consider the stability of offline tasks, which often cannot achieve stability and efficiency. In this paper, reinforcement learning is proposed for the first time to solve the hybrid deployment of online services and offline tasks and dynamically adjust the resource quota of online services more effectively. Compared with the original state of the server, our proposed method reduces CPU idleness rate by 35.32% and increases CPU resource utilization rate by 3.84%. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Transforming Vision Transformer: Towards Efficient Multi-Task Asynchronous Learning

arXiv

引用

arXiv 2025年

作者： Zhong, Hanwen Chen, Jiaxin Zhang, Yutong Huang, Di Wang, Yunhong State Key Laboratory of Virtual Reality Technology and Systems Beihang University China School of Computer Science and Engineering Beihang University Beijing China

Multi-Task Learning (MTL) for Vision Transformer aims at enhancing the model capability by tackling multiple tasks simultaneously. Most recent works have predominantly focused on designing Mixture-of-Experts (MoE) structures and integrating Low-Rank Adaptation (LoRA) to efficiently perform multi-task learning. However, their rigid combination hampers both the optimization of MoE and the effectiveness of reparameterization of LoRA, leading to sub-optimal performance and low inference speed. In this work, we propose a novel approach dubbed Efficient Multi-Task Learning (EMTAL) by transforming a pre-trained Vision Transformer into an efficient multi-task learner during training, and reparameterizing the learned structure for efficient inference. Specifically, we firstly develop the MoEfied LoRA structure, which decomposes the pre-trained Transformer into a low-rank MoE structure and employ LoRA to fine-tune the parameters. Subsequently, we take into account the intrinsic asynchronous nature of multi-task learning and devise a learning Quality Retaining (QR) optimization mechanism, by leveraging the historical high-quality class logits to prevent a well-trained task from performance degradation. Finally, we design a router fading strategy to integrate the learned parameters into the original Transformer, archiving efficient inference. Extensive experiments on public benchmarks demonstrate the superiority of our method, compared to the state-of-the-art multi-task learning approaches. The project page is available at https://***/Yewen1486/EMTAL. Copyright © 2025, The Authors. All rights reserved.

关键词： Multi-task learning

来源：评论

学校读者我要写书评

暂无评论

Assessing the Robustness of nnU-Net in the Detection of Prostate Lesions via Bi-Parametric MRI

Assessing the Robustness of nnU-Net in the Detection of Pros...

引用

2023 IEEE EMBS Special Topic Conference on Data science and engineering in Healthcare, Medicine and Biology, IEEECONF 2023

作者： Zaridis, Dimitrios I. Mylona, Eugenia Tachos, Nikolaos Kalantzopoulos, Charalampos Pezoulas, Vasileios C. Koutsouris, Dimitrios D. Matsopoulos, George K. Marias, Kostas Tsiknakis, Manolis Fotiadis, Dimitrios I. National Technical University of Athens School of Electrical and Computer Engineering Biomedical Engineering Laboratory AthensGR15773 Greece Forth Biomedical Research Institute Ioannina Greece University of Ioannina Ioannina Greece Forth Institute of Computer Science Heraklion Greece Hellenic Mediterranean University Department of Electrical and Computer Engineering Crete Heraklion Greece FORTH-IMBB Ioannina Greece University of Ioannina Unit of Medical Technology and Intelligent Information Systems Materials Science and Engineering Department IoanninaGR 45110 Greece

ISBN: (纸本)9798350383386

Within the scope of prostate cancer diagnostic imaging, distinguishing lesions is challenging due to their subtle appearance and the prostate gland's complexity. This study employed the nnU-Net, a state-of-the-art medical image segmentation model, on a dataset of 301 patients from 2 openly available datasets to identify whether lesion sizes are affecting the model's performance. By applying t-SNE dimensionality reduction algorithm among dice score and respective lesion sizes, we found that nnU-Net behaves differently for lesions smaller than 9mm compared to lesions larger than 15mm. These insights can inform specialized training approaches for future deep learning models in prostate lesion *** Relevance: The main contributions of this study is, to investigate whether lesion sizes affects nnU-Net's deficiency leading to the development of more specialized models in respect to these factors. © 2023 IEEE.

关键词： Urology

来源：评论

学校读者我要写书评

暂无评论

Language-Inspired Relation Transfer for Few-shot Class-Incremental Learning

arXiv

引用

arXiv 2025年

作者： Zhao, Yifan Li, Jia Song, Zeyin Tian, Yonghong State Key Laboratory of Virtual Reality Technology and Systems School of Computer Science and Engineering Beihang University Beijing100191 China School of Electronic and Computer Engineering Peking University Shenzhen518055 China School of Computer Science Peking University Beijing100871 China Pengcheng Laboratory Shenzhen518055 China

Depicting novel classes with language descriptions by observing few-shot samples is inherent in human-learning systems. This lifelong learning capability helps to distinguish new knowledge from old ones through the increase of open-world learning, namely Few-Shot Class-Incremental Learning (FSCIL). Existing works to solve this problem mainly rely on the careful tuning of visual encoders, which shows an evident trade-off between the base knowledge and incremental ones. Motivated by human learning systems, we propose a new Language-inspired Relation Transfer (LRT) paradigm to understand objects by joint visual clues and text depictions, composed of two major steps. We first transfer the pretrained text knowledge to the visual domains by proposing a graph relation transformation module and then fuse the visual and language embedding by a text-vision prototypical fusion module. Second, to mitigate the domain gap caused by visual finetuning, we propose context prompt learning for fast domain alignment and imagined contrastive learning to alleviate the insufficient text data during alignment. With collaborative learning of domain alignments and text-image transfer, our proposed LRT outperforms the state-of-the-art models by over 13% and 7% on the final session of miniImageNet and CIFAR-100 FSCIL benchmarks. Copyright © 2025, The Authors. All rights reserved.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

Gradient Projection Differential Neural Solution for Quadratic Optimization with Quadratic Constraints: An ACP Perspective

Gradient Projection Differential Neural Solution for Quadrat...

引用

2023 IEEE International Conference on systems, Man, and Cybernetics, SMC 2023

作者： Liufu, Ying Liu, Mei Jin, Long Wang, Feiyue School of Information Science and Engineering Lanzhou University Lanzhou China College of Computer Qinghai Normal University Xining China Institute of Automation The State Key Laboratory for Management and Control of Complex Systems Chinese Academy of Sciences Beijing China

ISBN: (纸本)9798350337020

In recent years, quadratic optimizations have become increasingly popular in engineering. However, conventional methods that investigate this problem from the perspective of a canonical form with linear constraints are not effective in dealing with the significant challenges posed by quadratic constraints in practice. This paper proposes a solution framework for the quadratic optimization with quadratic constraints (QOQC) based on innovative artificial societies, computational experiments, and parallel execution (ACP) framework. Then, a gradient projection differential neural solution (GPDNS) is proposed to address this. To illustrate the effectiveness of the GPDNS model in solving the QOQC system, numerical simulations are provided. Overall, this paper presents the potential of innovative approaches like the ACP framework to enhance our capabilities in addressing challenging optimization systems. © 2023 IEEE.

关键词： ACP constraints differential neural solution numerical simulation Quadratic optimization with quadratic

来源：评论

学校读者我要写书评

暂无评论

FDCPNet: Feature Discrimination and Context Propagation Network for 3D Shape Representation

SSRN

引用

SSRN 2024年

作者： Shi, Weimin Xiong, Yuan Wang, Qianwen Jiang, Han Zhou, Zhong State Key Laboratory of Virtual Reality Technology and Systems School of Computer Science and Engineering Beihang University Beijing100191 China Zhongguancun Laboratory Beijing China

3D shape representation using mesh data is essential in various applications, such as virtual reality and simulation technologies. Current methods extracting features from mesh edges or faces struggle with complex 3D models due to edge-based approaches missing global context and face-based methods overlooking variations in adjacent areas, which affects overall precision. To address these issues, we propose the Feature Discrimination and Context Propagation Network (FDCPNet), a novel approach that synergistically integrates local and global features in mesh datasets. FDCPNet is composed of two modules: 1) Feature Discrimination Module (FDM), which employs an attention mechanism to enhance the identification of key local features, 2) Context Propagation Module (CPM) enriches key local features by integrating global contextual information, facilitating a more detailed and comprehensive representation of crucial areas within the mesh model. Experiments on the Manifold40 dataset validate FDCPNet's effectiveness, showing a 1.9% improvement in classification accuracy over the baseline MeshNet, achieving 90.3%. Furthermore, even with reduced mesh face numbers and limited training data, FDCPNet achieves promising results, showing its robustness in variable complexity scenarios. © 2024, The Authors. All rights reserved.

关键词： Complex networks

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：