检索结果-内蒙古大学图书馆

arXiv 2024年

作者： Mao, Xiaojun Wang, Hengfang Wang, Zhonglei Yang, Shu School of Mathematical Sciences Ministry of Education Key Laboratory of Scientific and Engineering Computing Shanghai Jiao Tong University China School of Mathematics and Statistics Fujian Provincial Key Laboratory of Statistics and Artificial Intelligence Fujian Normal University China Wang Yanan Institute for Studies in Economics School of Economics Xiamen University China Department of Statistics North Carolina State University United States

Modern surveys with large sample sizes and growing mixed-type questionnaires require robust and scalable analysis methods. In this work, we consider recovering a mixed dataframe matrix, obtained by complex survey sampling, with entries following different canonical exponential distributions and subject to heterogeneous missingness. To tackle this challenging task, we propose a two-stage procedure: in the first stage, we model the entry-wise missing mechanism by logistic regression, and in the second stage, we complete the target parameter matrix by maximizing a weighted log-likelihood with a low-rank constraint. We propose a fast and scalable estimation algorithm that achieves sublinear convergence, and the upper bound for the estimation error of the proposed method is rigorously derived. Experimental results support our theoretical claims, and the proposed estimator shows its merits compared to other existing methods. The proposed method is applied to analyze the National Health and Nutrition Examination Survey data. Copyright © 2024, The Authors. All rights reserved.

关键词： Machine learning

来源：评论

学校读者我要写书评

暂无评论

Estimator Meets Equilibrium Perspective: A Rectified Straight Through Estimator for Binary Neural Networks Training

arXiv

引用

arXiv 2023年

作者： Wu, Xiao-Ming Zheng, Dian Liu, Zuhao Zheng, Wei-Shi School of Computer Science and Engineering Sun Yat-sen University China Pengcheng Lab China Guangdong Province Key Laboratory of Information Security Technology China Key Laboratory of Machine Intelligence and Advanced Computing Ministry of Education China

Binarization of neural networks is a dominant paradigm in neural networks compression. The pioneering work BinaryConnect uses Straight Through Estimator (STE) to mimic the gradients of the sign function, but it also causes the crucial inconsistency problem. Most of the previous methods design different estimators instead of STE to mitigate it. However, they ignore the fact that when reducing the estimating error, the gradient stability will decrease concomitantly. These highly divergent gradients will harm the model training and increase the risk of gradient vanishing and gradient exploding. To fully take the gradient stability into consideration, we present a new perspective to the BNNs training, regarding it as the equilibrium between the estimating error and the gradient stability. In this view, we firstly design two indicators to quantitatively demonstrate the equilibrium phenomenon. In addition, in order to balance the estimating error and the gradient stability well, we revise the original straight through estimator and propose a power function based estimator, Rectified Straight Through Estimator (ReSTE for short). Comparing to other estimators, ReSTE is rational and capable of flexibly balancing the estimating error with the gradient stability. Extensive experiments on CIFAR-10 and ImageNet datasets show that ReSTE has excellent performance and surpasses the state-of-the-art methods without any auxiliary modules or losses. Copyright © 2023, The Authors. All rights reserved.

关键词： Stability

来源：评论

学校读者我要写书评

暂无评论

Lombard-VLD: Voice Liveness Detection Based on Human Auditory Feedback

Lombard-VLD: Voice Liveness Detection Based on Human Auditor...

引用

IEEE Symposium on Security and Privacy

作者： Hongcheng Zhu Zongkun Sun Yanzhen Ren Kun He Yongpeng Yan Zixuan Wang Wuyang Liu Yuhong Yang Weiping Tu School of Cyber Science and Engineering Wuhan University Wuhan China State Grid Wuhan Electric Power Supply Company Key Laboratory of Aerospace Information Security and Trusted Computing Ministry of Education Wuhan China National Engineering Research Center for Multimedia Software School of Computer Science Wuhan University Hubei Key Laboratory of Multimedia and Network Communication Engineering Wuhan

ISBN: (数字)9798331522360

ISBN: (纸本)9798331522377

Voice Liveness Detection (VLD) aims to protect speaker authentication from speech spoofing by determining whether speeches come from live speakers or loudspeakers. Previous methods mainly focus on their differences at the signal level. In this paper, we propose the first VLD that uses the human auditory feedback mechanism (i.e., the Lombard effect), called Lombard-VLD. The key idea is that live speakers can physiologically and involuntarily adjust their speaking patterns in a noisy background but loudspeakers cannot. Moreover, we design a reference-based dual input mode and a differential SE-ResBlock to model the acoustic differences caused by the Lombard effect. Experimental results show that Lombard-VLD achieves 0% and 0.24% EER in two datasets, outperforming the state-of-the-art methods. It is robust to various environmental factors, including different distances, postures of the speaker, and environmental noise, with an average accuracy of over 98.51%. It also has a good generalization to unseen speakers, genders, and datasets, with EER lower than 2.68%, 3.44%, and 7.32%, respectively. This work shows the advantages of the Lombard effect in VLD, which has fewer user limitations and better detection performance.

关键词： Loudspeakers Privacy Accuracy Working environment noise Authentication Physiology Environmental factors Acoustics Security Noise measurement

来源：评论

学校读者我要写书评

暂无评论

Progressive Human Motion Generation Based on Text and Few Motion Frames

引用

IEEE Transactions on Circuits and Systems for Video Technology 2025年

作者： Zeng, Ling-An Wu, Gaojie Wu, Ancong Hu, Jian-Fang Zheng, Wei-Shi Sun Yat-sen University School of Artificial Intelligence Guangdong Zhuhai519082 China Sun Yat-sen University School of Computer Science and Engineering Guangdong Guangzhou510275 China Sun Yat-sen University School of Computer Science and Engineering China Guangdong Key Laboratory of Information Security Technology China Ministry of Education Key Laboratory of Machine Intelligence and Advanced Computing China Peng Cheng Laboratory China

Although existing text-to-motion (T2M) methods can produce realistic human motion from text description, it is still difficult to align the generated motion with the desired postures since using text alone is insufficient for precisely describing diverse postures. To achieve more controllable generation, an intuitive way is to allow the user to input a few motion frames describing precise desired postures. Thus, we explore a new Text-Frame-to-Motion (TF2M) generation task that aims to generate motions from text and very few given frames. Intuitively, the closer a frame is to a given frame, the lower the uncertainty of this frame is when conditioned on this given frame. Hence, we propose a novel Progressive Motion Generation (PMG) method to progressively generate a motion from the frames with low uncertainty to those with high uncertainty in multiple stages. During each stage, new frames are generated by a Text-Frame Guided Generator conditioned on frame-aware semantics of the text, given frames, and frames generated in previous stages. Additionally, to alleviate the train-test gap caused by multi-stage accumulation of incorrectly generated frames during testing, we propose a Pseudo-frame Replacement Strategy for training. Experimental results show that our PMG outperforms existing T2M generation methods by a large margin with even one given frame, validating the effectiveness of our PMG. Code is available here. © 1991-2012 IEEE.

关键词： Controllable Motion Generation Human Motion Text2Motion Generation

来源：评论

学校读者我要写书评

暂无评论

Service Migration in Mec: An Approach Based on Deep Reinforcement Learning and Fuzzy Logic

SSRN

引用

SSRN 2023年

作者： Zhang, Xinyang Bu, Chao Wang, Jinsong Key Laboratory of Computer Vision System of Ministry of Education School of Computer Science and Engineering Tianjin University of Technology China Tianjin Key Laboratory of Intelligence Computing and Novel Software Technology Tianjin University of Technology Tianjin300384 China

As a new computing paradigm, Mobile Edge computing (MEC) sinks resources to the network edge to support real-time re-sponses of services. Facing the demand for migrating services caused by the frequent movement of the mobile device, it is a great challenge to reduce the operation costs of migrating services with user requirements satisfied, especially for the continu-ous optimization of services deployed in hot spot areas. In order to address the above challenge, we propose the mechanism of dynamically migrating and optimally deploying services, which optimizes the latency and energy consumption of the service mi-gration. Firstly, we introduce Markov Decision Process (MDP) to model changes of deployment locations of the single-user ser-vice, and devise the approach to determine whether to migrate a service at the current network status based on the dueling Deep Q-Network (DQN). Secondly, we propose the service pre-migration decision approach to determine where to migrate a ser-vice by combining the Long Short-Term Memory (LSTM) network and the attention mechanism, so as to determine the future moving area of the user and perform the migration decision in advance with the impact of migration service on service quality considered. Finally, we devise the distance-weighted matching algorithm based on the fuzzy logic to further optimize the selec-tion of the most appropriate services to migrate in hotspot areas and the corresponding service migration regions, thus, the load pressure of the edge computing node caused by the imbalanced deployment density of service among multiple regions. Simula-tion results show that the proposed mechanism has significant improvements in overall operating costs compared with the cur-rent state of the art. © 2023, The Authors. All rights reserved.

关键词： Fuzzy logic

来源：评论

学校读者我要写书评

暂无评论

Benchmarking Deep Models on Salient Object Detection

SSRN

引用

SSRN 2023年

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

Deep network-based methods have continuously refreshed state-of-the-art performance on the Salient Object Detection (SOD) task. However, the performance discrepancy caused by different implementation details may conceal the real progress. In this paper, we construct a SALient Object Detection (SALOD) benchmark to ensure a fair and comprehensive evaluation by unifying the implementation settings of SOD methods. We aim to reveal the reasons behind recent progress by conducting a comprehensive examination of the impact of the network structure, training strategy, and loss function on accuracy. Based on the experimental results, first, we find that U-shaped networks, both older and more recent, still achieve better performance than other recently proposed structures. Second, the ablation study on training strategy proves its significant impact on SOD performance. Third, we provide a comprehensive analysis on existing loss functions and propose a new Edge-Aware (EA) loss function in response. At last, an objectness shifting experiment stands on a new perspective to validate the generalizability of SOD methods. Code is available at https://***/moothes/SALOD. © 2023, The Authors. All rights reserved.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Enhancing IoT Flow Anomaly Detection with Differential Optimal Feature Subspace

Enhancing IoT Flow Anomaly Detection with Differential Optim...

引用

IEEE International Conference on Data Science in Cyberspace (DSC)

作者： Weidong Shi Mingrui Fan Jiaqi Gao Jiahao Qi Daoqi Han Yueming Lu Key Laboratory of Trustworthy Distributed Computing and Service (BUPT) Ministry of Education School of Cyberspace Security The State Key Laboratory of Information Photonics and Optical Communications School of Information and Communication Engineering Beijing University of Posts and Telecommunications Beijing China

With the continuous expansion of network scale and increasing complexity, the application of the Internet of Things (IoT) is becoming more extensive. However, it is also vulnerable to various abnormal attacks, making security problems increasingly significant. Typically, traffic data dimensions are relatively large, and selecting features effectively is a key research issue. Addressing the aforementioned problems, this paper analyzes network traffic data and proposes a method(DOFS) to select the optimal feature subspace for different types of attacks, and verifies its effectiveness by comparative experiments. Then the T-S feature selection algorithm is improved, and DOFS is applied to the improved T-S feature selection algorithm, and the usability of the method is verified by experiments. By obtaining feature importance scores, the best feature subspace is selected for each type of traffic category. The method is verified using the network flow dataset CIC2018 and a real-world flow dataset. Experimental evaluations on diverse datasets demonstrate that the proposed method outperforms existing feature selection algorithms under different evaluation metrics, while exhibiting efficient time over-head and strong generalization ability. The results highlight the effectiveness and practicality of the proposed approach in IoT flow anomaly detection.

关键词：

来源：评论

学校读者我要写书评

暂无评论

ASAG: Building Strong One-Decoder-Layer Sparse Detectors via Adaptive Sparse Anchor Generation

ASAG: Building Strong One-Decoder-Layer Sparse Detectors via...

引用

International Conference on Computer Vision (ICCV)

作者： Shenghao Fu Junkai Yan Yipeng Gao Xiaohua Xie Wei-Shi Zheng School of Computer Science and Engineering Sun Yat-sen University China Guangdong Province Key Laboratory of Information Security Technology China Key Laboratory of Machine Intelligence and Advanced Computing Ministry of Education China Pengcheng Lab China

Recent sparse detectors with multiple, e.g. six, decoder layers achieve promising performance but much inference time due to complex heads. Previous works have explored using dense priors as initialization and built one-decoder-layer detectors. Although they gain remarkable acceleration, their performance still lags behind their six-decoder-layer counterparts by a large margin. In this work, we aim to bridge this performance gap while retaining fast speed. We find that the architecture discrepancy between dense and sparse detectors leads to feature conflict, hampering the performance of one-decoder-layer detectors. Thus we propose Adaptive Sparse Anchor Generator (ASAG) which predicts dynamic anchors on patches rather than grids in a sparse way so that it alleviates the feature conflict problem. For each image, ASAG dynamically selects which feature maps and which locations to predict, forming a fully adaptive way to generate image-specific anchors. Further, a simple and effective Query Weighting method eases the training instability from adaptiveness. Extensive experiments show that our method outperforms dense-initialized ones and achieves a better speed-accuracy trade-off. The code is available at https://***/iSEE-laboratory/ASAG.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Robust Graph Structure Learning with the Alignment of Features and Adjacency Matrix

arXiv

引用

arXiv 2023年

作者： Lv, Shaogao Wen, Gang Liu, Shiyu Wei, Linsen Li, Ming Department of Statistics and Data Science Nanjing Audit University China University of Electronic Science and Technology of China China School of Astronautics Northwestern Polytechnical University China Key Laboratory of Intelligent Education Technology and Application of Zhejiang Province Zhejiang Normal University Jinhua China Key Laboratory of Scientific and Engineering Computing Ministry of Education Shanghai Jiao Tong University China

To improve the robustness of graph neural networks (GNN), graph structure learning (GSL) has attracted great interest due to the pervasiveness of noise in graph data. Many approaches have been proposed for GSL to jointly learn a clean graph structure and corresponding representations. To extend the previous work, this paper proposes a novel regularized GSL approach, particularly with an alignment of feature information and graph information, which is motivated mainly by our derived lower bound of node-level Rademacher complexity for GNNs. Additionally, our proposed approach incorporates sparse dimensional reduction to leverage low-dimensional node features that are relevant to the graph structure. To evaluate the effectiveness of our approach, we conduct experiments on real-world graphs. The results demonstrate that our proposed GSL method outperforms several competitive baselines, especially in scenarios where the graph structures are heavily affected by noise. Overall, our research highlights the importance of integrating feature and graph information alignment in GSL, as inspired by our derived theoretical result, and showcases the superiority of our approach in handling noisy graph structures through comprehensive experiments on real-world datasets. Copyright © 2023, The Authors. All rights reserved.

关键词： Graphic methods

来源：评论

学校读者我要写书评

暂无评论

ASAG: Building Strong One-Decoder-Layer Sparse Detectors via Adaptive Sparse Anchor Generation

arXiv

引用

arXiv 2023年

作者： Fu, Shenghao Yan, Junkai Gao, Yipeng Xie, Xiaohua Zheng, Wei-Shi School of Computer Science and Engineering Sun Yat-sen University China Pengcheng Lab China Guangdong Province Key Laboratory of Information Security Technology China Key Laboratory of Machine Intelligence and Advanced Computing Ministry of Education China

Recent sparse detectors with multiple, e.g. six, decoder layers achieve promising performance but much inference time due to complex heads. Previous works have explored using dense priors as initialization and built one-decoder-layer detectors. Although they gain remarkable acceleration, their performance still lags behind their six-decoder-layer counterparts by a large margin. In this work, we aim to bridge this performance gap while retaining fast speed. We find that the architecture discrepancy between dense and sparse detectors leads to feature conflict, hampering the performance of one-decoder-layer detectors. Thus we propose Adaptive Sparse Anchor Generator (ASAG) which predicts dynamic anchors on patches rather than grids in a sparse way so that it alleviates the feature conflict problem. For each image, ASAG dynamically selects which feature maps and which locations to predict, forming a fully adaptive way to generate image-specific anchors. Further, a simple and effective Query Weighting method eases the training instability from adaptiveness. Extensive experiments show that our method outperforms dense-initialized ones and achieves a better speed-accuracy tradeoff. The code is available at https://***/iSEE-laboratory/ASAG. Copyright © 2023, The Authors. All rights reserved.

关键词： Decoding

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：