检索结果-内蒙古大学图书馆

Enhancing the transferability of adversarial attacks via Scale Enriching

Neural Networks 2025年 189卷 107549页

作者： Zhao, Yuhang Zheng, Jun Gao, Xianfeng Liu, Lu Zhang, Yaoyuan Zhang, Quanxin School of Cyberspace Science and Technology Beijing Institute of Technology Beijing100081 China School of Control and Computer Engineering North China Electric Power University Beijing102206 China School of Computer Science and Technology Beijing Institute of Technology Beijing100081 China

Deep learning models are vulnerable to adversarial attacks. Transfer-based adversarial examples are crafted against surrogate models and transferred to victim models. However, under the black-box settings, most adversaries have poor transferability on models with different input sizes. In this work, we propose the Scale Enriching Method (SEM) to enhance the transferability of adversarial examples using an input scale-enriching framework. By scaling the surrogate model's input in a specific range, our method enriches the attention areas that the surrogate model perceives and enlarges the tolerance of the distinction among different models, significantly improving the transferability. Notably, SEM avoids introducing extraneous noise during perturbation generation, thereby preserving the inherent textural features corresponding to different scales within the original images. Experiments on ImageNet show that our method successfully mitigates the gap of transferability between models with different input sizes. Furthermore, we demonstrate that our method can integrate with existing methods and bypass a variety of defense methods with over 90% success rate. © 2025 Elsevier Ltd

关键词： Adversarial attack Adversarial example Transfer attack

来源：评论

学校读者我要写书评

暂无评论

Machine Learning for Detecting Steering in Qutrit-Pair States

arXiv

引用

arXiv 2025年

作者： Wang, Pu Li, Zhongyan Meng, Huixian School of Control and Computer Engineering North China Electric Power University Beijing102206 China School of Mathematics and Physics North China Electric Power University Beijing102206 China

Only a few states in high-dimensional systems can be identified as (un)steerable using existing theoretical or experimental methods. We utilize semidefinite programming (SDP) to construct a dataset for steerability detection in qutrit-qutrit systems. For the full-information feature F1, artificial neural networks achieve high classification accuracy and generalization, and preform better than the support vector machine. As feature engineering playing a pivotal role, we introduce a steering ellipsoid-like feature F2, which significantly enhances the performance of each of our models. Given the SDP method provides only a sufficient condition for steerability detection, we establish the first rigorously constructed, accurately labeled dataset based on theoretical foundations. This dataset enables models to exhibit outstanding accuracy and generalization capabilities, independent of the choice of features. As applications, we investigate the steerability boundaries of isotropic states and partially entangled states, and find new steerable states. This work not only advances the application of machine learning for probing quantum steerability in high-dimensional systems but also deepens the theoretical understanding of quantum steerability itself. Copyright © 2025, The Authors. All rights reserved.

关键词： Support vector machines

来源：评论

学校读者我要写书评

暂无评论

Pose-graph optimization for efficient tie-point matching and 3D scene reconstruction from oblique UAV images

引用

ISPRS Journal of Photogrammetry and Remote Sensing 2025年 225卷 461-491页

作者： Xu, Zhihua Niu, Yongze Jiang, Jincheng Qin, Rongjun Cui, Ximin College of Geoscience and Surveying Engineering China University of Mining and Technology-Beijing Beijing100083 China North Automatic Control Technology Institute Shanxi Taiyuan030006 China School of Intelligent Systems Engineering Sun Yat-sen University Guangdong Shenzhen518107 China Department of Civil Environmental and Geodetic Engineering The Ohio State University 2036 Neil Avenue ColumbusOH43210 United States Department of Electrical and Computer Engineering The Ohio State University Dreese Laboratories 205 2015 Neil Ave ColumbusOH43210 United States Translational Data Analytics Institute The Ohio State University 1760 Neil Ave ColumbusOH43210 United States

Oblique photogrammetry using unmanned aerial vehicles (UAV) is crucial to 3D scene reconstruction. Nevertheless, oblique images are generally acquired with large overlaps, and sometimes with multiple views. Although this increases the level of data completeness, it introduces additional and sometimes redundant computations in tie-point matching, creating overly dense camera connections in the pose graph for bundle adjustment (BA). This study optimizes the pose graph of oblique UAV images by removing redundant image connections to guide tie-point matching. Assuming a five-camera system for oblique image collection, a pose graph called a topologically connected camera network (TCN) was initially constructed using position and orientation system (POS) data to determine the spatial connectivity among oblique images. Second, five geometric meta-parameters of overlapping images were constructed, and their influence on tie-point matching was analyzed using a data-driven approach to generate a weighted pose graph. Third, the weighted pose graph was simplified to a degree-bounded skeletal camera network (D-SCN) using the proposed two-stage multi-objective graph optimization approach. Finally, the D-SCN was embedded into a structure from motion (SfM) pipeline to produce a novel D-SCN–SfM method to reduce the required computations for tie-point matching. The proposed D-SCN-SfM method was tested using data from three large sites, each containing over 5,000 images. In addition, the D-SCN-SfM method was compared with three state-of-the-art methods. The experimental results indicate that our method can significantly reduce the required computations for tie-point matching to 1/14–1/20 as compared to a method that uses only topological constraints, that is, TCN, saving 89–92% of the time expenditure. Furthermore, the accuracy and completeness of the 3D geometry produced by the proposed method were comparable to those produced by standard SfM methods. The source code of our approach

关键词： Drones

来源：评论

学校读者我要写书评

暂无评论

SPMNet: A Siamese Pyramid Mamba Network for Very-High-Resolution Remote Sensing Change Detection

引用

IEEE Transactions on Geoscience and Remote Sensing 2025年 63卷

作者： Wang, Jiashu Song, Jinze Zhang, Hao Zhang, Zekai Ji, Yunlong Zhang, Wenyin Zhang, Jinglin Wang, Xing Linyi University School of Computer Science and Engineering Linyi276000 China Shandong University Department of Control Science and Engineering Jinan250061 China Linyi University School of Information Science and Engineering China

Very-High-Resolution (VHR) remote sensing images are characterized by extremely high spatial resolution, incorporating higher pixel density and larger image sizes, which pose challenges for existing methods to extract complex texture features. Furthermore, due to the wide-area and high-resolution imaging strategy, VHR change detection images suffer from a severe imbalance between change pixels and non-change pixels, increasing the difficulty of handling change detection tasks. To address these challenges, we introduced the Omnidirectional Selective Scan Module (OSSM), which has the capability to process long sequences. By integrating it with the lightweight Siamese Feature Pyramid Network (SFPN), we designed a hybrid CNN-Mamba backbone, referred to as SPMamba. This backbone captures both global and local information within bitemporal feature maps at each stage, enhancing the precision of texture feature extraction. Additionally, to integrate the semantic features from each branch in SPMamba and reduce noise interference from non-target change areas, we developed a Hybrid Fusion Module (HFM). The HFM consists of two fusion modules: the High-Low Channel Fusion Module (HLM) and the Bilateral Channel Fusion Module (BCM), which facilitates both feature-level and channel-level integration, enhancing the sensitivity of the model to subtle changes. Extensive experimental results demonstrate that SPMNet achieves the highest F1-score of 91.80%, 90.99%, and 96.04% on the WHU-CD, LEVIR-CD, and CDD-CD datasets, respectively, outperforming eleven state-of- the-art methods. Moreover, the effects of varying image sizes on model training are thoroughly analyzed. © 1980-2012 IEEE.

关键词： Change detection

来源：评论

学校读者我要写书评

暂无评论

GrasOpen: Biometric Authentication via Reach-and-Grasp for Smart Door Access Using Smartwatch

引用

IEEE Internet of Things Journal 2025年

作者： Ding, Lei Shi, Jiale Wu, Yuan Hu, Xinrong Bi, Hongliang Chen, Yanjiao Wuhan Textile University School of Computer Science and Artificial Intelligence Engineering Research Center of Hubei Province for Clothing Information 430200 China China University of Mining and Technology School of Information and Control Engineering Jiangsu Xuzhou221116 China Zhejiang University College of Electrical Engineering Hangzhou310027 China

In the domain of smart devices, biometric identity authentication has become a leading and crucial technology, mainly because of its improved security and user convenience. Traditional methods frequently depend on complex activities, facial recognition, or passwords, which can be cumbersome and error-prone. This paper presents GrasOpen, an innovative biometric authentication system tailored for door-opening scenarios, utilizing the natural reach-and-grasp motion linked to door handles. The system employs smartwatches with accelerometers and gyroscopes to track and analyze arm movements, ensuring a seamless and intuitive user experience. GrasOpen tackles key challenges by leveraging the unique characteristics of the reach-and-grasp motion, eliminating the necessity for users to remember complex motions, and avoiding redundant actions like waiting for facial recognition. Specifically, GrasOpen initially proposes a lightweight model to discern door-opening actions from daily activities. Then, to realize the robust authentication system, GrasOpen integrates a complementary filter (CF) method to capture diversity-dependent features in door-opening actions. These features are subsequently processed through a modified ConvBoost model for precise user authentication. Experimental results reveal an impressive accuracy of 98.78% for activity recognition and 98.65% for identity authentication, highlighting GrasOpen’s excellence in function and performance. The system’s security and robustness are validated across diverse authentication environments. © 2014 IEEE.

关键词： Biometrics

来源：评论

学校读者我要写书评

暂无评论

FPGA-based accelerator for YOLOv5 object detection with optimized computation and data access for edge deployment

引用

Parallel Computing 2025年 124卷

作者： Qian, Wei Zhu, Zhengwei Zhu, Chenyang Zhu, Yanping School of Microelectronics and Control Engineering Changzhou University Changzhou213146 China School of Computer Science and Artificial Intelligence Changzhou University Changzhou213146 China

In the realm of object detection, advancements in convolutional neural networks have been substantial. However, their high computational and data access demands complicate the deployment of these algorithms on edge devices. To mitigate these challenges, field-programmable gate arrays have emerged as an ideal hardware platform for executing the parallel computations inherent in convolutional neural networks, owing to their low power consumption and rapid response capabilities. We have developed a field-programmable gate array-based accelerator for the You Only Look Once version 5 (YOLOv5) object detection network, implemented using Verilog Hardware Description Language on the Xilinx XCZU15EG chip. This accelerator efficiently processes the convolutional layers, batch normalization fusion layers, and tensor addition operations of the Yolov5 network. Our architecture segregates the convolution computations into two computing units: multiplication and addition. The addition operations are significantly accelerated by the introduction of compressor adders and ternary adder trees. Additionally, off-chip bandwidth pressure is alleviated through the use of dual-input single-output buffers and dedicated data access units. Experimental results demonstrate that the power consumption of the accelerator is 13.021 watts at a central frequency of 200 megahertz. Experiment results indicate that our accelerator outperforms Amazon Web Services Graviton2 central processing units and Jetson Nano graphics processing units. Ablation experiments validate the enhancements provided by our innovative designs. Ultimately, our approach significantly boosts the inference speed of the Yolov5 network, with improvements of 61.88%, 69.1%, 59.36%, 64.07%, and 65.92%, thereby dramatically enhancing the performance of the accelerator and surpassing existing methods. © 2025 Elsevier B.V.

关键词： System-on-chip

来源：评论

学校读者我要写书评

暂无评论

Cluster-Refined Optimal Transport for Unsupervised Action Segmentation

Cluster-Refined Optimal Transport for Unsupervised Action Se...

引用

International Conference on Acoustics, Speech, and Signal Processing (ICASSP)

作者： Shijie Wang Jinrong Zhang Yule Liu Shiyao Li Lin Feng School of Computer Science and Technology Dalian University of Technology Dalian China School of Control Science and Engineering Dalian University of Technology Dalian China School of Innovation and Entrepreneurship Dalian University of Technology Dalian China

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

Action segmentation in untrimmed videos is essential for comprehensive video understanding. Despite significant progress in unsupervised methods, capturing both long-range dependencies and short-duration actions simultaneously remains a challenging task. To address this challenge, this paper introduces the Cluster-Refined Optimal Transport (CROT) method, combining hierarchical clustering and optimal transport for unsupervised action segmentation. We first hierarchically cluster video frame representations to capture long-range dependencies and generate pseudo-boundaries. Initial pseudo-labels are then obtained via optimal transport, ensuring short-duration actions are recognized. Finally, these pseudo-labels are refined using the pseudo-boundaries, resulting in the final segmentation output. Extensive experiments on three public datasets, i.e., YouTube Instructions, Breakfast, and 50Salads, demonstrate that our method performs on par with or better than previous approaches.

关键词： Video on demand Signal processing Acoustics Web sites Speech processing Videos

来源：评论

学校读者我要写书评

暂无评论

Language-Queried Target Sound Extraction Without Parallel Training Data

Language-Queried Target Sound Extraction Without Parallel Tr...

引用

2025 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2025

作者： Ma, Hao Peng, Zhiyuan Li, Xu Li, Yukai Shao, Mingjie Kong, Qiuqiang Liu, Ju School of Information Science and Engineering Shandong University Qingdao China Department of Computer Science North Carolina State University NC United States ARC Lab Tencent PCG China Key Laboratory of System and Control AMSS Chinese Academy of Sciences Beijing China The Chinese University of Hong Kong Hong Kong

ISBN: (纸本)9798350368741

Language-queried target sound extraction (TSE) aims to extract specific sounds from mixtures based on language queries. Traditional fully-supervised training schemes require extensively annotated parallel audio-text data, which are labor-intensive. We introduce a parallel-data-free training scheme, requiring only unlabelled audio clips for TSE model training by utilizing the contrastive language-audio pre-trained model (CLAP). In a vanilla parallel-data-free training stage, target audio is encoded using the pre-trained CLAP audio encoder to form a condition embedding, while during testing, user language queries are encoded by CLAP text encoder as the condition embedding. This vanilla approach assumes perfect alignment between text and audio embeddings, which is unrealistic. Two major challenges arise from training-testing mismatch: the persistent modality gap between text and audio and the risk of overfitting due to the exposure of rich acoustic details in target audio embedding during training. To address this, we propose a retrieval-augmented strategy. Specifically, we create an embedding cache using audio captions generated by a large language model (LLM). During training, target audio embeddings retrieve text embeddings from this cache to use as condition embeddings, ensuring consistent modalities between training and testing and eliminating information leakage. Extensive experiment results show that our retrieval-augmented approach achieves consistent and notable performance improvements over existing state-of-the-art with better generalizability. © 2025 IEEE.

关键词： contrastive language-audio pre-training retrieval-augmented strategy target sound extraction uni-modal training for multi-modal tasks

来源：评论

学校读者我要写书评

暂无评论

MASS FLOW DETECTION TECHNOLOGY FOR SEED AND FERTILISER PARTICLES AND ITS APPLICATION IN UAV-BASED SPREADING

引用

INMATEH - Agricultural engineering 2025年第1期75卷 584-599页

作者： Wang, Yanshuang Song, Cancan Gao, Yongqi Lan, Yubin Wang, Guobin Ming, Rui College of Agricultural Engineering and Food Science Shandong University of Technology Zibo China Shandong University of Technology Sub-center of National Center for International Collaboration Research on Precision Agricultural Aviation Pesticide Spraying Technology Zibo China Research of Institute of Ecological Unmanned Farm Shandong University of Technology Zibo China School of Computer and Big Data Minjiang University Fujian Provincial Key Laboratory of Information Processing and Intelligent Control Fuzhou China

The processes of sowing and fertiliser application represent a significant aspect of agricultural production. In order to achieve efficient and precise seeding and fertiliser application, mass flow detection of seed and fertiliser particles can facilitate real-time monitoring and precise decision-making for intelligent seeding and fertiliser application. However, the diversity of seed and fertiliser particle types and particle flow modes presents a challenge for existing detection methods, particularly in meeting the varying operational requirements, especially for particle mass flow detection in low-altitude and high-speed sowing operations of agricultural drones. In such cases, the overlap and flow rate will have a significant impact on the detection results due to the large displacement and the continuous high-throughput dense phase of the particle flow. This paper provides a summary of the existing seed and fertiliser particle mass flow detection techniques and their underlying working principles. It compares the direct detection based on mass with the indirect detection methods based on velocity and concentration, and analyses their respective advantages, disadvantages and applicability. It also explores the possibility of optimising the existing detection methods for the specific needs of agricultural UAVs and considers the potential introduction of cutting-edge science and technology in order to develop an efficient, accurate and convenient detection system to meet the growing market demand. © (2025), (INMA Bucharest). All Rights Reserved.

关键词： Precision agriculture

来源：评论

学校读者我要写书评

暂无评论

LoBee: Bidirectional Communication between LoRa and ZigBee based on Physical-Layer CTC

引用

IEEE Transactions on Wireless Communications 2025年

作者： Gao, Demin Wang, Haoyu Chen, YongRui Ye, Qiaolin Wang, Weizheng Guo, Xiuzhen Wang, Shuai Liu, Yunhuai He, Tian Nanjing Forestry University College of Information Science and Technology Artificial Intelligence Nanjing210037 China University of Minnesota The Department of Computer Science and Engineering 55414 United States University of Chinese Academy of Sciences School of Electronic Electrical and Communication Engineering Beijing100049 China Southeast University The School of Computer Science and Engineering Nanjing211189 China City University of Hong Kong Department of Computer Science 999077 Hong Kong College of Control Science and Engineering Zhejiang 310027 China Peking University The Department of Computer Science and Engineering Beijing100871 China University of Minnesota The Department of Computer Science and Engineering Minneapolis55414 United States

LoRa networks operating in a star topology, this configuration creates a single point of failure and may limit scalability and reliability in areas that are large and geographically dispersed. In order to improve the overall transmission capabilities of the network, recent studies show that adding LoRa to the ZigBee devices effectively disseminates network management. By doing so, the strengths of both technologies can be leveraged, with LoRa serving as the long-range transmitter and ZigBee functioning as the mesh network. In this study, we present LoBee, a novel bidirectional communication method between LoRa and ZigBee that relies on Physical-Layer Cross-Technology Communication. Despite the fact that LoRa and ZigBee utilize different modulation techniques, ZigBee devices can detect and recognize LoRa chirps through the process of sampling the received signal strength. For the transmissions from ZigBee to LoRa devices, we carefully select the input chips to generate specific waveforms, where LoBee detects the preamble of a ZigBee frame based on the locations of the repeated peaks. Our evaluation, which was conducted using USRP and commodity devices, demonstrates that LoBee is capable of achieving concurrent bidirectional wireless communications, with a data rate of approximately 639.38 bits per second from LoRa to ZigBee and from ZigBee to LoRa with more than 90% frame reception rate in the 2.4 GHz frequency band. © 2002-2012 IEEE.

关键词： Zigbee

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：