检索结果-内蒙古大学图书馆

arXiv 2025年

作者： Ning, Zhiyuan Wang, Zaitian Zhang, Ran Xu, Ping Liu, Kunpeng Wang, Pengyang Chen, Chong Wang, Pengfei Zhou, Yuanchun Cambria, Erik The Computer Network Information Center Chinese Academy of Sciences University of Chinese Academy of Sciences China The Department of Computer Science Portland State University United States Department of Computer and Information Science The State Key Laboratory of Internet of Things for Smart City University of Macau China The Future City Lab Terminus Group China The School of Computer Science and Engineering Nanyang Technological University Singapore

Graph clustering aims to divide the graph into different clusters. The recently emerging deep graph clustering approaches are largely built on graph neural networks (GNN). However, GNN is designed for general graph encoding and there is a common issue of representation collapse in existing GNN-based deep graph clustering algorithms. We attribute two main reasons for such issue: (i) the inductive bias of GNN models: GNNs tend to generate similar representations for proximal nodes. Since graphs often contain a non-negligible amount of inter-cluster links, the bias results in error message passing and leads to biased clustering;(ii) the clustering guided loss function: most traditional approaches strive to make all samples closer to pre-learned cluster centers, which cause a degenerate solution assigning all data points to a single label thus make all samples and less discriminative. To address these challenges, we investigate graph clustering from a graph cut perspective and propose an innovative and non-GNN-based Deep Cut-informed Graph embedding and Clustering framework, namely DCGC. This framework includes two modules: (i) cut-informed graph encoding;(ii) self-supervised graph clustering via optimal transport. For the encoding module, we derive a cut-informed graph embedding objective to fuse graph structure and attributes by minimizing their joint normalized cut. For the clustering module, we utilize the optimal transport theory to obtain the clustering assignments, which can balance the guidance of "proximity to the pre-learned cluster center". With the above two tailored designs, DCGC is more suitable for the graph clustering task, which can effectively alleviate the problem of representation collapse and achieve better performance. We conduct extensive experiments to demonstrate that our method is simple but effective compared with benchmarks. © 2025, CC BY.

关键词： Graph embeddings

来源：评论

学校读者我要写书评

暂无评论

Exploiting Noise as a Resource for Computation and Learning in Spiking Neural Networks

arXiv

引用

arXiv 2023年

作者： Ma, Gehua Yan, Rui Tang, Huajin College of Computer Science and Technology Zhejiang University The State Key Lab of Brain-Machine Intelligence Hangzhou China College of Computer Science and Technology Zhejiang University of Technology Hangzhou China

Networks of spiking neurons underpin the extraordinary information-processing capabilities of the brain and have become pillar models in neuromorphic artificial intelligence. Despite extensive research on spiking neural networks (SNNs), most studies are established on deterministic models, overlooking the inherent non-deterministic, noisy nature of neural computations. This study introduces the noisy spiking neural network (NSNN) and the noise-driven learning rule (NDL) by incorporating noisy neuronal dynamics to exploit the computational advantages of noisy neural processing. NSNN provides a theoretical framework that yields scalable, flexible, and reliable computation. We demonstrate that NSNN leads to spiking neural models with competitive performance, improved robustness against challenging perturbations than deterministic SNNs, and better reproducing probabilistic computation in neural coding. This study offers a powerful and easy-to-use tool for machine learning, neuromorphic intelligence practitioners, and computational neuroscience researchers. Copyright © 2023, The Authors. All rights reserved.

关键词： Dynamical systems

来源：评论

学校读者我要写书评

暂无评论

Transferable Waveform-level Adversarial Attack against Speech Anti-spoofing Models

Transferable Waveform-level Adversarial Attack against Speec...

引用

IEEE International Conference on Multimedia and Expo (ICME)

作者： Bingyuan Huang Sanshuai Cui Xiangui Kang Enping Li Guangdong Key Lab of Information Security School of Computer Science and Engineering Sun Yat-Sen University Guangzhou China Computer Science Department Bridgewater State University Massachusetts USA

Speech anti-spoofing models protect media from malicious fake speech but are vulnerable to adversarial attacks. Studies of adversarial attacks are conducive to developing robust speech anti-spoofing systems. Existing transfer-based attack methods mainly craft adversarial speech examples at the handcrafted-feature level, which have limited attack ability against the real-world anti-spoofing systems, as these systems only have raw waveform input interfaces. In this work, we propose a waveform-level input data transformation, called the temporal smoothing method, to generate more transferable adversarial speech examples. In the optimization iterations of the adversarial perturbation, we randomly smooth input waveforms to prevent the adversarial examples from overfitting white-box surrogate models. The proposed transformation can be combined with any iterative gradient-based attack method. Extensive experiments demonstrate that our method significantly enhances the transferability of waveform-level adversarial speech examples.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Robust Tiny Object Detection in Aerial Images amidst label Noise

arXiv

引用

arXiv 2024年

作者： Zhu, Haoran Xu, Chang Yang, Wen Zhang, Ruixiang Zhang, Yan Xia, Gui-Song School of Electronic Information Wuhan University Wuhan430072 China School of Computer Science The State Key Lab LIESMARS Wuhan University Wuhan430072 China

Precise detection of tiny objects in remote sensing imagery remains a significant challenge due to their limited visual information and frequent occurrence within scenes. This challenge is further exacerbated by the practical burden and inherent errors associated with manual annotation—annotating tiny objects is laborious and prone to errors (i.e., label noise). Training detectors for such objects using noisy labels often leads to suboptimal performance, with networks tending to overfit on noisy labels. In this study, we address the intricate issue of tiny object detection under noisy label supervision. We systematically investigate the impact of various types of noise on network training, revealing the vulnerability of object detectors to class shifts and inaccurate bounding boxes for tiny objects. To mitigate these challenges, we propose a DeNoising Tiny Object Detector (DN-TOD), which incorporates a Class-aware label Correction (CLC) scheme to address class shifts and a Trend-guided Learning Strategy (TLS) to handle bounding box noise. CLC mitigates inaccurate class supervision by identifying and filtering out class-shifted positive samples, while TLS reduces noisy box-induced erroneous supervision through sample reweighting and bounding box regeneration. Additionally, Our method can be seamlessly integrated into both one-stage and two-stage object detection pipelines. Comprehensive experiments conducted on synthetic (i.e., noisy AI-TOD-v2.0 and DOTA-v2.0) and real-world (i.e., AI-TOD) noisy datasets demonstrate the robustness of DN-TOD under various types of label noise. Notably, when applied to the strong baseline RFLA, DN-TOD exhibits a noteworthy performance improvement of 4.9 points under 40% mixed noise. Datasets, codes, and models will be made publicly available. © 2024, CC BY.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

Power-scheduled Routing Strategy for Quantum key Distribution over Classical Optical Networks

Power-scheduled Routing Strategy for Quantum Key Distributio...

引用

International Conference on Computing, Networking and Communications (ICNC)

作者： Yuhang Liu Xiaosong Yu Yongli Zhao Avishek Nag State Key Lab of Information Photonics and Optical Communications Beijing University of Posts and Telecommunications Beijing China School of Computer Science University College Dublin Ireland

In this work, we study a power-scheduled routing strategy for quantum key distribution (QKD) over classical optical networks. The average secret key rate can be improved by 59.4% and 152.8% at maximum with the propose... 详细信息

ISBN: (数字)9798350370997

ISBN: (纸本)9798350371000

关键词： Integrated optics Correlation Network topology Navigation Telecommunication traffic Optical fiber networks Routing

来源：评论

学校读者我要写书评

暂无评论

StyleTalk++: A Unified Framework for Controlling the Speaking Styles of Talking Heads

arXiv

引用

arXiv 2024年

作者： Wang, Suzhen Ma, Yifeng Ding, Yu Hu, Zhipeng Fan, Changjie Lv, Tangjie Deng, Zhidong Yu, Xin Fuxi AI Lab Netease Zhejiang Hangzhou China Department of Computer Science and Technology BNRist THUAI State Key Laboratory of Intelligent Technology and Systems Tsinghua University China The School of Computer Science The University of Queensland Brisbane Australia

Individuals have unique facial expression and head pose styles that reflect their personalized speaking styles. Existing one-shot talking head methods cannot capture such personalized characteristics and therefore fail to produce diverse speaking styles in the final videos. To address this challenge, we propose a one-shot style-controllable talking face generation method that can obtain speaking styles from reference speaking videos and drive the one-shot portrait to speak with the reference speaking styles and another piece of audio. Our method aims to synthesize the style-controllable coefficients of a 3D Morphable Model (3DMM), including facial expressions and head movements, in a unified framework. Specifically, the proposed framework first leverages a style encoder to extract the desired speaking styles from the reference videos and transform them into style codes. Then, the framework uses a style-aware decoder to synthesize the coefficients of 3DMM from the audio input and style codes. During decoding, our framework adopts a two-branch architecture, which generates the stylized facial expression coefficients and stylized head movement coefficients, respectively. After obtaining the coefficients of 3DMM, an image renderer renders the expression coefficients into a specific person's talking-head video. Extensive experiments demonstrate that our method generates visually authentic talking head videos with diverse speaking styles from only one portrait image and an audio clip. Copyright © 2024, 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

Skyrmionic spin textures in nonparaxial light

引用

Advanced Photonics 2025年第1期7卷 85-92页

作者： Xinrui Lei Aiping Yang Xusheng Chen Luping Du Peng Shi Qiwen Zhan Xiaocong Yuan Shenzhen University Institute of Microscale Optoelectronics and State Key Laboratory of Radio Frequency Heterogeneous IntegrationNanophotonics Research CenterShenzhen Key Laboratory of Micro-Scale Optical Information TechnologyShenzhenChina University of Shanghai for Science and Technology School of Optical-Electrical and Computer EngineeringShanghaiChina Dongguan University of Technology Research Institute of Interdisciplinary Sciences and School of Materials Science and EngineeringDongguanChina Research Centre for Frontier Fundamental Studies Zhejiang LabHangzhouChina

Topological textures in optics such as skyrmions and merons are increasingly studied for their potential functions in light–matter interactions,deep-subwavelength imaging,and ***,they were previously generated either in strongly confined guided waves or in paraxial *** has posed a significant challenge in constructing skyrmions in nonparaxial propagating waves due to the lack of symmetry-breaking in the optical field and difficulty in characterizing the full three-dimensional spin textures at the *** theoretically propose and experimentally demonstrate the generation of skyrmionic spin textures in nonparaxial light,where skyrmionic textures with a Bloch-type scheme,including isolated skyrmioniums,skyrmion,and meron lattices are generated in free *** introduce the interplay between the Hertz potentials to break the dual symmetry of light and build well-defined domains of *** experimentally realized the topological textures by applying a hybrid polarized optical vortex and observed the complete three-dimensional spin distributions by a dual-mode waveguide *** bridging the gap in the skyrmionic group,we present a topologic diagram,showing how spin–orbit coupling of light governs the spin *** findings offer new insights into optical quasiparticles and electron–photon correspondence,potentially facilitating advanced applications in optical metrology,sensing,and storage.

关键词： spin topology photonic skyrmion spin–orbit coupling of light

来源：评论

学校读者我要写书评

暂无评论

Model-enabled complexity measurement for aerospace equipment architectures

引用

IEEE Access 2024年

作者： Yaodong, Wang Wangbin, Cao Houman, Yu Yusheng, Liu Wenqiang, Yuan Yue, Cao Zhejiang University State Key Lab of CADandCG Hangzhou310058 China China Academy of Space Technology Beijing100094 China Hangzhou Dianzi University School of Computer Science Hangzhou310018 China Zhejiang University of Technology College of Computer Science and Technology Hangzhou310023 China

Digital models have been extensively used in the development of aerospace equipment, among which the architecture model is the core of the development process. The architecture model of aerospace equipment is large and complex so that many problems such as budget overrun and schedule delay are essentially caused by its high complexity. To address these issues, complexity needs to be measured quantificationally to guide the development process. Although there are existing methods for calculating architecture complexity, theses methods are too general and do not consider the particularity of aerospace equipment. In this study, a method to calculate the architecture complexity specific to the characteristics of aerospace equipment is proposed. First, the definition of complexity is improved by taking into account the architectural topology and factors reflecting reliability. Then, formulas for calculating architecture complexity are proposed by improving existing methods. Case studies from various domains are used to illustrate the effectiveness of the proposed method. © 2013 IEEE.

关键词： Budget control

来源：评论

学校读者我要写书评

暂无评论

Communication-Efficient Distributed Learning with Local Immediate Error Compensation

arXiv

引用

arXiv 2024年

作者： Cheng, Yifei Shen, Li Xu, Linli Qian, Xun Wu, Shiwei Zhou, Yiming Zhang, Tie Tao, Dacheng Chen, Enhong The Anhui Province Key Lab of Big Data Analysis and Application State Key Laboratory of Cognitive Intelligence School of Data Science School of Computer Science University of Science and Technology China The JD Explore Academy China The Shanghai Artificial Intelligence Laboratory China

Gradient compression with error compensation has attracted significant attention with the target of reducing the heavy communication overhead in distributed learning. However, existing compression methods either perform only unidirectional compression in one iteration with higher communication cost, or bidirectional compression with slower convergence rate. In this work, we propose the Local Immediate Error Compensated SGD (LIEC-SGD) optimization algorithm to break the above bottlenecks based on bidirectional compression and carefully designed compensation approaches. Specifically, the bidirectional compression technique is to reduce the communication cost, and the compensation technique compensates the local compression error to the model update immediately while only maintaining the global error variable on the server throughout the iterations to boost its efficacy. Theoretically, we prove that LIEC-SGD is superior to previous works in either the convergence rate or the communication cost, which indicates that LIEC-SGD could inherit the dual advantages from unidirectional compression and bidirectional compression. Finally, experiments of training deep neural networks validate the effectiveness of the proposed LIEC-SGD algorithm. Copyright © 2024, The Authors. All rights reserved.

关键词： Error compensation

来源：评论

学校读者我要写书评

暂无评论

Grid4D: 4D decomposed hash encoding for high-fidelity dynamic Gaussian splatting 24

Grid4D: 4D decomposed hash encoding for high-fidelity dynami...

引用

Proceedings of the 38th International Conference on Neural Information Processing Systems

作者： Jiawei Xu Zexin Fan Jian Yang Jij Xie PCA Lab VCIP College of Computer Science Nankai University State Key Laboratory for Novel Software Technology Nanjing University Nanjing China and School of Intelligence Science and Technology Nanjing University Suzhou China

ISBN: (纸本)9798331314385

Recently, Gaussian splatting has received more and more attention in the field of static scene rendering. Due to the low computational overhead and inherent flexibility of explicit representations, plane-based explicit methods are popular ways to predict deformations for Gaussian-based dynamic scene rendering models. However, plane-based methods rely on the inappropriate low-rank assumption and excessively decompose the space-time 4D encoding, resulting in overmuch feature overlap and unsatisfactory rendering quality. To tackle these problems, we propose Grid4D, a dynamic scene rendering model based on Gaussian splatting and employing a novel explicit encoding method for the 4D input through the hash encoding. Different from plane-based explicit representations, we decompose the 4D encoding into one spatial and three temporal 3D hash encodings without the low-rank assumption. Additionally, we design a novel attention module that generates the attention scores in a directional range to aggregate the spatial and temporal features. The directional attention enables Grid4D to more accurately fit the diverse deformations across distinct scene components based on the spatial encoded features. Moreover, to mitigate the inherent lack of smoothness in explicit representation methods, we introduce a smooth regularization term that keeps our model from the chaos of deformation prediction. Our experiments demonstrate that Grid4D significantly outperforms the state-of-the-art models in visual quality and rendering speed. Project page: https://***/Grid4D-web/.

关键词：

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：