检索结果-内蒙古大学图书馆

arXiv 2024年

作者： Zhang, Beichen Li, Liang Zha, Zheng-Jun Luo, Jiebo Huang, Qingming The School of Computer Science and Technology University of Chinese Academy of Sciences Beijing101408 China The Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences Beijing100190 China The School of Information Science and Technology University of Science and Technology of China Hefei230027 China The Department of Computer Science University of Rochester RochesterNY14627 United States

Active learning (AL) is designed to construct a high-quality labeled dataset by iteratively selecting the most informative samples. Such sampling heavily relies on data representation, while recently pre-training is popular for robust feature learning. However, as pre-training utilizes low-level pretext tasks that lack annotation, directly using pre-trained representation in AL is inadequate for determining the sampling score. To address this problem, we propose a downstream-pretext domain knowledge traceback (DOKT) method that traces the data interactions of downstream knowledge and pre-training guidance for selecting diverse and instructive samples near the decision boundary. DOKT consists of a traceback diversity indicator and a domain-based uncertainty estimator. The diversity indicator constructs two feature spaces based on the pre-training pretext model and the downstream knowledge from annotation, by which it locates the neighbors of unlabeled data from the downstream space in the pretext space to explore the interaction of samples. With this mechanism, DOKT unifies the data relations of low-level and high-level representations to estimate traceback diversity. Next, in the uncertainty estimator, domain mixing is designed to enforce perceptual perturbing to unlabeled samples with similar visual patches in the pretext space. Then the divergence of perturbed samples is measured to estimate the domain uncertainty. As a result, DOKT selects the most diverse and important samples based on these two modules. The experiments conducted on ten datasets show that our model outperforms other state-of-the-art methods and generalizes well to various application scenarios such as semantic segmentation and image captioning. Copyright © 2024, The Authors. All rights reserved.

关键词： Domain Knowledge

来源：评论

学校读者我要写书评

暂无评论

Fully utilized pilot-aided digital signal processing with state pruning MLSD assisted adaptive symbol detection for symbol-rate sampling coherent optical interconnects

引用

Optics Express 2025年第14期33卷 29026-29043页

作者： Chenchen Wang Zhipei Li Ze Dong Ran Gao Jiayi Hao Junyuan Song Dong Guo Fu Wang Tianlei Mai Xiaolong Pan Huan Chang Sitong Zhou Xiangjun Xin School of Information and Electronics Beijing Institute of Technology (BIT) Beijing 100081 China National Key Laboratory of Science and Technology on Space-Born Intelligent Information Processing Beijing 100081 China School of Electronic Engineering Beijing University of Posts and Telecommunications (BUPT) Beijing 100876 China Beijing Key Laboratory of Space-Ground Interconnection and Convergence BUPT Beijing 100876 China State Key Laboratory of Information Photonics and Optical Communications BUPT Beijing 100876 China

In high-speed coherent optical interconnects, symbol-rate sampling serves as a critical strategy for reducing digital signal processing (DSP) power consumption, yet its implementation faces significant challenges due to the sensitivity to analog-to-digital converter (ADC) sampling phase error and signal degradation under Nyquist constraints. This paper presents a hardware-efficient DSP architecture for FTN-shaped 16QAM systems that fully exploits pilot-aided processing to enable power-efficient, symbol-rate sampled coherent optical interconnects. The proposed design features a polarization-joint misaligned pilot scheme for enhanced carrier recovery (CR) and a pilot-aided adaptive symbol detection framework (PA-SDF) with state pruning MLSD. The PA-SDF dynamically switches between single-symbol (SSD) and multi-symbol detection (MSD) via a predefined mode-switching decision metric (MSDM), achieving an optimal BER-complexity trade-off. Experimental results at 80/90/100 Gbaud demonstrate a 0.7 dB receiver sensitivity improvement, while the proposed carrier recovery scheme reduces multiplier and adder usage by over 95%. Furthermore, the decoding architecture achieves a remarkable reduction in MLSD complexity to just 7.72% of conventional approaches, with 74% of symbols being processed through low-complexity SSD. The proposed fully utilized pilot-aided symbol-rate sampling DSP architecture presents a viable solution for next-generation, power-constrained data centers.

关键词： Analog to digital converters Optical interconnects Phase recovery Quadrature amplitude modulation Quadrature phase shift keying Signal recovery

来源：评论

学校读者我要写书评

暂无评论

Toward a Unified Framework for Unsupervised Complex Tabular Reasoning

Toward a Unified Framework for Unsupervised Complex Tabular ...

引用

International Conference on Data Engineering

作者： Zhenyu Li Xiuxing Li Zhichao Duan Bowen Dong Ning Liu Jianyong Wang Department of Computer Science and Technology Tsinghua University Beijing China Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences (ICT/CAS) University of Chinese Academy of Sciences School of Software Shandong University Jinan China

Structured tabular data exist across nearly all fields. Reasoning task over these data aims to answer questions or determine the truthiness of hypothesis sentences by understanding the semantic meaning of a table. While previous works have devoted significant efforts to the tabular reasoning task, they always assume there are sufficient labeled data. However, constructing reasoning samples over tables (and related text) is labor-intensive, especially when the reasoning process is complex. When labeled data is insufficient, the performance of models will suffer an unendurable decline. In this paper, we propose a unified framework for unsupervised complex tabular reasoning (UCTR), which generates sufficient and diverse synthetic data with complex logic for tabular reasoning tasks, assuming no human-annotated data at all. Specifically, we first utilize a random sampling strategy to collect diverse programs of different types and execute them on tables based on a "Program-Executor" module. To bridge the gap between the programs and natural language sentences, we design a powerful "NL-Generator" module to generate natural language sentences with complex logic from these programs. Since a table often occurs with its surrounding texts, we further propose novel "Table-to-Text" and "Text-to-Table" operators to handle joint table-text reasoning scenarios. This way, we can adequately exploit the unlabeled table resources to obtain a well-performed reasoning model under an unsupervised setting. Our experiments cover different tasks (question answering and fact verification) and different domains (general and specific), showing that our unsupervised methods can achieve at most 93% performance compared to supervised models. The impressive performance demonstrates that UCTR can significantly reduce the dependence on manual annotation. Moreover, we also find that it can substantially boost the supervised performance in low-resourced domains as a data augmentation technique.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Dual-Band HRRP Fusion Recognition via Wavelet Decomposition Embedded Autoencoder

Dual-Band HRRP Fusion Recognition via Wavelet Decomposition ...

引用

Signal, information and Data processing (ICSIDP), IEEE International Conference on

作者： Weijia Wang Zhuchang Qi Lue Wang Wei Yang Liang Zhang Yanhua Wang Radar Technology Research Institute Beijing Institute of Technology Beijing China Xi'an Institute of Modern Control Technology Xi'an China Zhengzhou Academy of Intelligent Technology Beijing Institute of Technology Zhengzhou China Beijing Key Laboratory of Embedded Real-Time Information: Processing Technology Beijing China Chongqing Innovation Center Beijing Institute of Technology China

ISBN: (数字)9798331515669

ISBN: (纸本)9798331515676

High-resolution range profile (HRRP) is a crucial technique for radar target recognition. Due to the coupling of azimuthal scattering information and aspect sensitivity, fine target recognition using HRRP remains challenging. One way to mitigate HRRP aspect sensitivity is through enhancing the dimensionality of radar information acquisition. Therefore, this paper proposes a Dual-Band HRRP Fusion Recognition Model via Wavelet Decomposition Embedded Autoencoder (DF-WD-AENet). The method we proposed mainly comprises two modules. Firstly, the autoencoder model based on wavelet decomposition (WD-AEM) achieves constraint on feature information, making it better suited for dual-band fusion. Next is the dual-band information fusion module (DFM), in which we achieved the interaction and fusion of feature information through convolutional block attention module (CBAM) and omni-dimensional dynamic convolution (ODConv), and used a fusion loss function to train the model. Experiment shows that the recognition rate of our method is 7.73% higher than that of single-band, proving the effectiveness of the proposed method.

关键词： Sensitivity Target recognition Convolution Fuses Autoencoders Dual band Scattering Radar Radar signal processing Signal resolution

来源：评论

学校读者我要写书评

暂无评论

Dual-Band HRRP Recognition via Wavelet Packet Decomposition and Redundancy Reduction Model

Dual-Band HRRP Recognition via Wavelet Packet Decomposition ...

引用

Signal, information and Data processing (ICSIDP), IEEE International Conference on

作者： Wei Yang Zhuchang Qi Heke Wu Yang Li Liang Zhang Yanhua Wang Radar Technology Research Institute Beijing Institute of Technology Beijing China Chongqing Innovation Center Beijing Institute of Technology China Xi'an Institute of Modern Control Technology Xi’an China Zhengzhou Academy of Intelligent Technology Beijing Institute of Technology Zhengzhou China Beijing Key Laboratory of Embedded Real-Time Information: Processing Technology Beijing China

ISBN: (数字)9798331515669

ISBN: (纸本)9798331515676

High resolution range profiles (HRRP) is widely used in radar automatic target recognition. Due to aspect sensitivity, HRRP of different targets can be similar under certain aspects, making it difficult for recognition via traditional methods. One way to mitigate it is to increase the frequency dimension, utilizing the differences of target frequency response to extract inter-class discriminative information. Therefore, we propose a HRRP recognition model based on redundancy reduction criterion and wavelet packet decomposition. Specifically, we use deep wavelet packet decomposition to perform multi-level decomposition of dual-band HRRP and adaptively extract discriminative features of sub-wavelets; we use redundancy reduction layer to cluster intra-class features and expand inter-class features, thereby reducing feature heterogeneity. Furthermore, we propose a deep discriminative correlation analysis for joint analysis and transformation of dual-band features to fuse complementary information. Experimental results show that proposed method has excellent recognition performance. Additionally, analysis study also verify the effectiveness of each submodule.

关键词： Sensitivity Limiting Target recognition Fuses Redundancy Dual band Radar Feature extraction Wavelet packets Frequency response

来源：评论

学校读者我要写书评

暂无评论

Image encryption based on 2D-SAHM chaotic system and a novel DNA operation rule

引用

The European Physical Journal Special Topics 2023年第6期233卷 1311-1330页

作者： Huang, Lilian Ye, Youxin Liu, Yang College of Information and Communication Engineering Harbin Engineering University Harbin China Key Laboratory of Advanced Marine Communication and Information Technology Harbin Engineering University Ministry of Industry and Information Technology Harbin China National Key Laboratory of Underwater Acoustic Technology Harbin Engineering University Harbin China Sichuan Key Laboratory of Agile Intelligent Computing Southwest China Institute of Electronic Technology Chengdu China

With the continuous development of information technology, ensuring information security has become an important issue. As a widely used multimedia tool, images often face the risk of leakage. Therefore, this paper proposes an image encryption algorithm based on 2D-SAHM chaotic system and a new DNA operation rule. The algorithm first constructs a new chaotic system 2D-SAHM, which has better chaotic characteristics and can generate more random chaotic sequences than the traditional low-dimensional chaotic system. And then, on the basis of this system, the algorithm scrambles and diffuses the image. In the scrambling stage, the whole image is converted into a one-dimensional pixel matrix and divided into several sub-images by double Joseph scrambling. In the diffusion stage, to solve the problem that traditional DNA encryption relies too much on chaotic sequences, this paper proposes a new DNA operation rule. This rule determines the operation symbol of DNA by the type of amino acid, which improves the randomness of the algorithm. The final simulation results and performance analysis show that the algorithm has high security and strong anti-interference ability.

关键词：

来源：评论

学校读者我要写书评

暂无评论

TFGDA: exploring topology and feature alignment in semi-supervised graph domain adaptation through robust clustering 24

TFGDA: exploring topology and feature alignment in semi-supe...

引用

Proceedings of the 38th International Conference on Neural information processing Systems

作者： Jun Dan Weiming Liu Chunfeng Xie Hua Yu Shunjie Dong Yanchao Tan Zhejiang University Queen Mary University of London Dalian University of Technology Shanghai Jiao Tong University Fuzhou University and Engineering Research Center of Big Data Intelligence Ministry of Education and Fujian Key Laboratory of Network Computing and Intelligent Information Processing

ISBN: (纸本)9798331314385

Semi-supervised graph domain adaptation, as a branch of graph transfer learning, aims to annotate unlabeled target graph nodes by utilizing transferable knowledge learned from a label-scarce source graph. However, most existing studies primarily concentrate on aligning feature distributions directly to extract domain-invariant features, while ignoring the utilization of the intrinsic structure information in graphs. Inspired by the significance of data structure information in enhancing models' generalization performance, this paper aims to investigate how to leverage the structure information to assist graph transfer learning. To this end, we propose an innovative framework called TFGDA. Specially, TFGDA employs a structure alignment strategy named STSA to encode graphs' topological structure information into the latent space, greatly facilitating the learning of transferable features. To achieve a stable alignment of feature distributions, we also introduce a SDA strategy to mitigate domain discrepancy on the sphere. Moreover, to address the overfitting issue caused by label scarcity, a simple but effective RNC strategy is devised to guide the discriminative clustering of unlabeled nodes. Experiments on various benchmarks demonstrate the superiority of TFGDA over SOTA methods.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Understanding News Creation Intents: Frame, Dataset, and Method

arXiv

引用

arXiv 2023年

作者： Wang, Zhengjia Wang, Danding Sheng, Qiang Cao, Juan Su, Silong Sun, Yifan Hu, Beizhe Ma, Siyuan Key Lab of Intelligent Information Processing Chinese Academy of Sciences Institute of Computing Technology Chinese Academy of Sciences China University of Chinese Academy of Sciences China University of Macau China

As the disruptive changes in the media economy and the proliferation of alternative news media outlets, news intent has progressively deviated from ethical standards that serve the public interest. News intent refers to the purpose or intention behind the creation of a news article. While the significance of research on news intent has been widely acknowledged, the absence of a systematic news intent understanding framework hinders further exploration of news intent and its downstream applications. To bridge this gap, we propose News INTent (NINT) frame, the first component-aware formalism for understanding the news creation intent based on research in philosophy, psychology, and cognitive science. Within this frame, we define the news intent identification task and provide a benchmark dataset with fine-grained labels along with an efficient benchmark method. Experiments demonstrate that NINT is beneficial in both the intent identification task and downstream tasks that demand a profound understanding of news. This work marks a foundational step towards a more systematic exploration of news creation intents. Copyright © 2023, The Authors. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Automatic Survey Generation Based Onposition Closeness of Key Words

SSRN

引用

SSRN 2022年

作者： Sun, Xiaoping Zhuge, Hai Key Lab of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences China Chinese Academy of Sciences China

Survey enables researchers to know a research area quickly. Automatic survey generation is a challenge to text summarization research because a survey consists of many sections, each of which is composed by the sentences selected from the papers most relevant to its titles. The key is to rank papers, determine top-k papers and select sentences from the top-k papers according to section title. This paper proposes a measure called key word position closeness to rank papers by measuring how closely two neighboring key words of a section title are distributed within a paper. The basic rationale is that the positions of the neighboring key words of a section title should be closer in more relevant papers to be surveyed. To select the top-k papers for each section, an unsupervised method is proposed to predict the top-k value based on the shape of the curve of the sorted ranking scores. Based on the duality property of the closeness, sentence ranking scores of a selected paper with respect to the key words of section title can be directly obtained when the paper ranking score is computed using the closeness, both the importance and coherence of selected sentences can be reflected without extra sentence ranking calculation. Experiments and manual evaluation show that the proposed methods achieve significant improvements compared with term frequency-based approaches to generating scientific survey. © 2022, The Authors. All rights reserved.

关键词： Text processing

来源：评论

学校读者我要写书评

暂无评论

Two-Stage Multi-modal Multi-objective Algorithm Based on Dynamic Niche Updating 11th

Two-Stage Multi-modal Multi-objective Algorithm Based on Dy...

引用

11th International Joint Conference on Rough Sets, IJCRS 2025

作者： Ji, Haonian Chen, Hongmei Mi, Yong Institute of Artificial Intelligence School of Computing and Artificial Intelligence Southwest Jiaotong University Chengdu611756 China National Engering Laboratory of Integrated Transportation Big Data Application Technology Southwest Jiaotong University Chengdu611756 China Engering Research Center of Sustainable Urban Intelligent Transportation Ministry of Education Southwest Jiaotong University Chengdu611756 China Manufacturing Industry Chains Collaboration and Information Support Technology Key Laboratory of Sichuan Province Southwest Jiaotong University Chengdu611756 China

ISBN: (纸本)9783031927409

In solving multi-modal multi-objective optimization problems (MMOPs), objective and decision space changes need to be considered. However, many multi-modal multi-objective evolutionary algorithms (MMOEAs) tend to prioritize diversity in the objective space during the optimization process, often leading to suboptimal diversity and distribution in the decision space. This study proposes the Dynamic-Niche-Based Two-Stage Evolution (DNTE) approach to address this issue. DNTE employs differential evolutionary strategies in two stages, utilizing dynamic niche to enhance solution viability and optimize decision space distribution at different phases. In the first stage, the dynamic niche is used to restrict the dominance range of Pareto domination. In contrast, in the second stage, it is integrated with differential evolution to refine the distribution of the decision space. Combining DNTE with DN-NSGA-II enhances the capability of solving MMOPs and demonstrates superior performance compared to other evolutionary algorithms on MMF and MMMOP benchmark functions. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Multiobjective optimization

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：