检索结果-内蒙古大学图书馆

arXiv 2025年

作者： Li, Tanzhe Li, Caoshuo Lyu, Jiayi Pei, Hongjuan Zhang, Baochang Jin, Taisong Ji, Rongrong Key Laboratory of Multimedia Trusted Perception and Effcient Computing Ministry of Education of China Xiamen University China School of Informatics Xiamen University China School of Engineering Science University of Chinese Academy of Sciences China School of Artificial Intelligence Beihang University China

State space models (SSMs) have recently garnered significant attention in computer vision. However, due to the unique characteristics of image data, adapting SSMs from natural language processing to computer vision has not outperformed the state-of-the-art convolutional neural networks (CNNs) and Vision Transformers (ViTs). Existing vision SSMs primarily leverage manually designed scans to flatten image patches into sequences locally or globally. This approach disrupts the original semantic spatial adjacency of the image and lacks flexibility, making it difficult to capture complex image structures. To address this limitation, we propose Dynamic Adaptive Scan (DAS), a data-driven method that adaptively allocates scanning orders and regions. This enables more flexible modeling capabilities while maintaining linear computational complexity and global modeling capacity. Based on DAS, we further propose the vision backbone DAMamba, which significantly outperforms current state-of-the-art vision Mamba models in vision tasks such as image classification, object detection, instance segmentation, and semantic segmentation. Notably, it surpasses some of the latest state-of-the-art CNNs and ViTs. Code will be available at https://***/ltzovo/DAMamba. Copyright © 2025, The Authors. All rights reserved.

关键词： Semantic Segmentation

来源：评论

学校读者我要写书评

暂无评论

Counting Mobile Devices With Physical Layer Measurements in the 2.4GHz ISM Band 19

Counting Mobile Devices With Physical Layer Measurements in ...

引用

2022 IEEE SmartWorld, 19th IEEE International Conference on Ubiquitous Intelligence and computing, 2022 IEEE International Conference on Autonomous and Trusted Vehicles Conference, 22nd IEEE International Conference on Scalable computing and Communications, 2022 IEEE International Conference on Digital Twin, 8th IEEE International Conference on Privacy computing and 2022 IEEE International Conference on Metaverse, SmartWorld/UIC/ATC/ScalCom/DigitalTwin/PriComp/Metaverse 2022

作者： Zhang, Zhaoyan Huang, Baoqi Zhang, Chaowei Jia, Bing Li, Wuyungerile Xu, Gang Engineering Research Center of Ecological Big Data Ministry of Education China Inner Mongolia Key Laboratory of Wireless Networking and Mobile Computing Hohhot China Inner Mongolia University College of Computer Science Hohhot China Inner Mongolia Power Marketing Service and Operation Management Center China

ISBN: (纸本)9798350346558

In general, the more mobile devices are operating in space, the more wireless communications are produced, leading to significant changes in the wireless spectrum, which can be utilized to infer the number of mobile devices conversely. Inspired by this idea, we pioneered present a novel mobile device counting method of measuring the wireless signals of the 2. 4GHz ISM band in which most WiFi-and Bluetooth-enabled mobile devices operate. Precisely, the in-phase (I) and quadrature (Q) components from the wireless signals are measured through a software-defined radio (SDR) platform and are then converted into spectrograms. On this ground, we propose a dual attention network based on EfficientNet-B4 (EANet) to estimate the number of mobile devices with the aforementioned spectrograms as inputs. In addition, a cross-domain estimation method is proposed to enhance the generalizability of our model. Experiments are conducted in real environments to validate our method. It is shown that the proposed regression model EANet outperforms the models based on popular convolutional neural networks (CNNs), and the proposed cross-domain method can effectively reduce the training time without sacrificing the estimation accuracy. This study preliminarily verifies the idea's feasibility and the validity of the proposed methods, paving the way for future research. © 2022 IEEE.

关键词： Network layers

来源：评论

学校读者我要写书评

暂无评论

Exploring the State-of-the-Practices in Smart Expressway: Multi-Country Comparison

Exploring the State-of-the-Practices in Smart Expressway: Mu...

引用

IEEE International Conference on Intelligent Transportation engineering (ICITE)

作者： Song Yang Yueyi Yang Xinghua Li Ziqi Yang Yuntao Guo Chao Yang ZheJiang Scientific Research Institute of Transport Hangzhou China Department of Traffic Engineering Key Laboratory of Road and Traffic Engineering Ministry of Education Tongji University Shanghai China Urban Mobility Institute Tongji University Shanghai China

ISBN: (数字)9798350314212

ISBN: (纸本)9798350314229

Expressway has always played a critical role in a country's economic and societal development but is facing challenges such as increasing traffic congestion, accidents, and pollution. Various countries and regions attempt to develop smart expressways to address these issues. However, the understanding and the applications of smart expressway vary among policymakers across the globe. This study aims to provide a comprehensive understanding of the state-of-the-practice in smart expressway practices around the world. It analyzed current multi-country smart expressway pilot projects that have been carried out in China, Europe, the United States, the United Kingdom, and Japan through extensive online data mining, semi-structured interview, and field investigation. The lessons learned, findings, and insights of this study can potentially be used to support developing smart expressway standards at both national and regional-level and serve as a blueprint for ongoing and future smart expressway projects.

关键词： Economics Pollution Transportation Europe Traffic control Reliability engineering Safety Interviews Traffic congestion Standards

来源：评论

学校读者我要写书评

暂无评论

GALOPA: graph transport learning with optimal plan alignment 23

GALOPA: graph transport learning with optimal plan alignment

引用

Proceedings of the 37th International Conference on Neural Information Processing Systems

作者： Yejiang Wang Yuhai Zhao Zhengkui Wang Ling Li School of Computer Science and Engineering Northeastern University China and Key Laboratory of Intelligent Computing in Medical Image of Ministry of Education Northeastern University China InfoComm Technology Cluster Singapore Institute of Technology Singapore

Self-supervised learning on graphs aims to learn graph representations in an unsupervised manner. While graph contrastive learning (GCL - relying on graph augmentation for creating perturbation views of anchor graphs and maximizing/minimizing similarity for positive/negative pairs) is a popular self-supervised method, it faces challenges in finding label-invariant augmented graphs and determining the exact extent of similarity between sample pairs to be achieved. In this work, we propose an alternative self-supervised solution that (i) goes beyond the label invariance assumption without distinguishing between positive/negative samples, (ii) can calibrate the encoder for preserving not only the structural information inside the graph, but the matching information between different graphs, (iii) learns isometric embeddings that preserve the distance between graphs, a by-product of our objective. Motivated by optimal transport theory, this scheme relies on an observation that the optimal transport plans between node representations at the output space, which measure the matching probability between two distributions, should be consistent with the plans between the corresponding graphs at the input space. The experimental findings include: (i) The plan alignment strategy significantly outperforms the counterpart using the transport distance; (ii) The proposed model shows superior performance using only node attributes as calibration signals, without relying on edge information; (iii) Our model maintains robust results even under high perturbation rates; (iv) Extensive experiments on various benchmarks validate the effectiveness of the proposed method.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Error Analysis of Virtual Element Method for the Poisson-Boltzmann Equation

arXiv

引用

arXiv 2023年

作者： Huang, Linghan Shu, Shi Yang, Ying Guangxi Guilin541004 China School of Mathematics and Computational Science Xiangtan University Hunan Key Laboratory for Computation and Simulation in Science and Engineering Key Laboratory of Intelligent Computing and Information Processing Ministry of Education Hunan Xiangtan411105 China Guangxi541004 China

The Poisson-Boltzmann equation is a nonlinear elliptic equation with Dirac distribution sources, which has been widely applied to the prediction of electrostatics potential of biological biomolecular systems in solution. In this paper, we discuss and analysis the virtual element method for the Poisson-Boltzmann equation on general polyhedral meshes. Under the low regularity of the solution of the whole domain, nearly optimal error estimates in both L2-norm and H1-norm for the virtual element approximation are obtained. The numerical experiment on different polyhedral meshes shows the efficiency of the virtual element method and verifies the proposed theoretical prediction. Copyright © 2023, The Authors. All rights reserved.

关键词： Poisson equation

来源：评论

学校读者我要写书评

暂无评论

Space Engage: Collaborative Space Supervision for Contrastive-based Semi-Supervised Semantic Segmentation

Space Engage: Collaborative Space Supervision for Contrastiv...

引用

International Conference on Computer Vision (ICCV)

作者： Changqi Wang Haoyu Xie Yuhui Yuan Chong Fu Xiangyu Yue School of Computer Science and Engineering Northeastern University Shenyang China Microsoft Research Asia Key Laboratory of Intelligent Computing in Medical Image Ministry of Education NEU China The Chinese University of Hong Kong

Semi-Supervised Semantic Segmentation (S4) aims to train a segmentation model with limited labeled images and a substantial volume of unlabeled images. To improve the robustness of representations, powerful methods introduce a pixel-wise contrastive learning approach in latent space (i.e., representation space) that aggregates the representations to their prototypes in a fully supervised manner. However, previous contrastive-based S4 methods merely rely on the supervision from the model’s output (logits) in logit space during unlabeled training. In contrast, we utilize the outputs in both logit space and representation space to obtain supervision in a collaborative way. The supervision from two spaces plays two roles: 1) reduces the risk of over-fitting to incorrect semantic information in logits with the help of representations; 2) enhances the knowledge exchange between the two spaces. Furthermore, unlike previous approaches, we use the similarity between representations and prototypes as a new indicator to tilt training those under-performing representations and achieve a more efficient contrastive learning process. Results on two public benchmarks demonstrate the competitive performance of our method compared with state-of-the-art methods.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Releasing Inequality Phenomena in L∞-Adversarial Training via Input Gradient Distillation

arXiv

引用

arXiv 2023年

作者： Chen, Junxi Dong, Junhao Xie, Xiaohua School of Computer Science and Engineering Sun Yat-sen University Guangzhou510006 China Guangdong Province Key Laboratory of Information Security Technology Guangzhou510006 China Key Laboratory of Machine Intelligence and Advanced Computing Ministry of Education Guangzhou510006 China

Since adversarial examples appeared and showed the catastrophic degradation they brought to DNN, many adversarial defense methods have been devised, among which adversarial training is considered the most effective. However, a recent work showed the inequality phenomena in l∞-adversarial training and revealed that the l∞-adversarially trained model is vulnerable when a few important pixels are perturbed by i.i.d. noise or occluded. In this paper, we propose a simple yet effective method called Input Gradient Distillation (IGD) to release the inequality phenomena in l∞-adversarial training. Experiments show that while preserving the model’s adversarial robustness, compared to PGDAT, IGD decreases the l∞adversarially trained model’s error rate to inductive noise and inductive occlusion by up to 60% and 16.53%, and to noisy images in Imagenet-C by up to 21.11%. Moreover, we formally explain why the equality of the model’s saliency map can improve such robustness. Copyright © 2023, The Authors. All rights reserved.

关键词： Distillation

来源：评论

学校读者我要写书评

暂无评论

Strain controlled thermal regulator realized in two-dimensional black and blue phosphorene in-plane heterostructure

引用

Physical Review B 2024年第10期109卷 104106-104106页

作者： Mingyue Xia Luneng Zhao Yuan Chang Hongsheng Liu Gang Zhang Wuxing Zhou Jijun Zhao Junfeng Gao State Key Laboratory of Structural Analysis for Industrial Equipment Dalian University of Technology Dalian 116024 China Laboratory of Materials Modification by Laser Ion and Electron Beams Ministry of Education Dalian University of Technology Dalian 116024 China Institute of High Performance Computing A*STAR Singapore 138632 Singapore School of Materials Science and Engineering Hunan University of Science and Technology Xiangtan 411201 China

The reversible phase transition of two-dimensional material allotropes induced by strain engineering has promising applications in nanoelectromechanical systems and memories. Here, we report a series of black and blue phosphorene superlattice (BBPS) can be formed by reversible phase transition between them. The phase transition is with low-energy barrier and can be well regulated by strain engineering, until black phosphorene phase is fully transformed into blue phosphorene phase under strain of ε = 23%. At room temperature, BBPS exhibits a high phase transition rate of about 106 Hz, which enables reversible phase transition rapidly. Beyond, the unique in-plane heterostructure of BBPS suppresses phonon transmission, lowering thermal conductivity to only 25.6% of black phosphorene. Beyond, nonequilibrium Green's function calculations indicate the thermal conductivity crossing the black-blue phosphorene heterojunction suddenly drops to only 1/3 that of black phosphorene. Therefore, strain engineering can not only achieve reversible phase transition but also modulate the thermal conductivity in very large range, which is excellent in the field of heat flow manipulation and thermal management.

关键词： Electrical properties Phase transitions Thermal conductivity 2-dimensional systems Phosphorene Strain engineering

来源：评论

学校读者我要写书评

暂无评论

APRF: Anti-Aliasing Projection Representation Field for Inverse Problem in Imaging

arXiv

引用

arXiv 2023年

作者： Chen, Zixuan Yang, Lingxiao Lai, Jianhuang Xie, Xiaohua The School of Computer Science and Engineering Sun Yat-sen University Guangzhou510006 China The Guangdong Province Key Laboratory of Information Security Technology Guangzhou510006 China The Key Laboratory of Machine Intelligence and Advanced Computing Ministry of Education Guangzhou510006 China

Sparse-view Computed Tomography (SVCT) reconstruction is an ill-posed inverse problem in imaging that aims to acquire high-quality CT images based on sparsely-sampled measurements. Recent works use Implicit Neural Representations (INRs) to build the coordinate-based mapping between sinograms and CT images. However, these methods have not considered the correlation between adjacent projection views, resulting in aliasing artifacts on SV sinograms. To address this issue, we propose a self-supervised SVCT reconstruction method – Anti-Aliasing Projection Representation Field (APRF), which can build the continuous representation between adjacent projection views via the spatial constraints. Specifically, APRF only needs SV sinograms for training, which first employs a line-segment sampling module to estimate the distribution of projection views in a local region, and then synthesizes the corresponding sinogram values using a center-based line integral module. After training APRF on a single SV sinogram itself, it can synthesize the corresponding dense-view (DV) sinogram with consistent continuity. High-quality CT images can be obtained by applying re-projection techniques on the predicted DV sinograms. Extensive experiments on CT images demonstrate that APRF outperforms state-of-the-art methods, yielding more accurate details and fewer artifacts. Our code will be publicly available soon. Copyright © 2023, The Authors. All rights reserved.

关键词： Inverse problems

来源：评论

学校读者我要写书评

暂无评论

Visible Light Positioning Method for Indoor Line-of-Sight Scene Based on Time Series Coding

Visible Light Positioning Method for Indoor Line-of-Sight Sc...

引用

IEEE International Conference on Data Science in Cyberspace (DSC)

作者： Yonghao Yu Yongde Guo Dawei Zhao Kexue Fu Yongwei Tang Qinyuan Wang Faculty of Data Science City University of Macau China Key Laboratory of Computing Power Network and Information Security Ministry of Education Shandong Computer Science Center(National Supercomputer Center in Jinan) Qilu University of Technology (Shandong Academy of Sciences) Jinan China Shandong Fundamental Research Center for Computer Science Shandong Provincial Key Laboratory of Computer Networks Jinan China School of Mechanical Engineering Key Laboratory of High Efficiency and Clean Mechanical Manufacture Ministry of Education Shandong University Jinan China

ISBN: (数字)9798350391367

ISBN: (纸本)9798350391374

Existing indoor visible light positioning methods, such as those based on fingerprint database algorithms, are complex to construct and consume significant resources. In response to this issue, the text proposes an end-to-end indoor visible light positioning method that samples continuous signals at a small number of random coordinate positions in indoor environments. Through a deep learning method based on attention mechanism, a nonlinear mapping between the received signal and spatial position coordinates is constructed, and the time series properties in the received signal are encoded as a feature in the data. The method is further improved by combining residual networks to improve accuracy. Through simulation experiments, it has been verified that the deep learning based localization method described in this article can achieve sub meter level accuracy on small sample datasets, and it has been proven that time series features have a significant impact on localization accuracy in indoor visible light positioning algorithms based on deep learning.

关键词： Location awareness Deep learning Meters Training Accuracy Attention mechanisms Time series analysis Training data Encoding Data models

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：