检索结果-内蒙古大学图书馆

OSA-PD: Open-Set Active Learning Exploiting Predictive Discrepancy

IEEE signal processing LETTERS 2025年 32卷 851-855页

作者： Chen, Zhiming Han, Peng Jiang, Fei Si, Jiaxin Xiong, Lili Chongqing Univ Posts & Telecommun Sch Software Engn Chongqing 400065 Peoples R China Chongqing Acad Sci & Technol Chongqing 400065 Peoples R China Chongqing Qulian Digital Technol Co Ltd Chongqing 400065 Peoples R China

Active learning with closed-set annotation has achieved significant success. However, real-world data often comprises numerous unknown classes irrelevant to the task which often confuses the query strategies to select unknown class data for annotation. To address such challenge in the open-set annotation (OSA), we propose a novel open-set active learning framework based on predictive discrepancy, named OSA-PD, with consideration that valuable data for model improvement is often with high predictive discrepancy. Specifically, two algorithms based on different discrepancy measurements are presented under OSA-PD framework, i.e., OSA-PRD with predictive results discrepancy, and OSA-PDD with decoupled predictive distribution discrepancy. Experimental results on CIFAR100 and TinyImageNet demonstrate the proposed OSA-PD can effectively select known class data and achieve higher classification accuracy with the same amount of annotated sample in comparison with existing active learning algorithms.

关键词： Detectors Annotations Active learning Data models Accuracy Probability distribution Prediction algorithms Uncertainty Training signal processing algorithms open-set annotation predictive discrepancy image classification

来源：评论

学校读者我要写书评

暂无评论

An Attention-Based Feature processing Method for Cross-Domain Hyperspectral Image Classification

引用

IEEE signal processing LETTERS 2025年 32卷 196-200页

作者： Wang, Yazhen Liu, Guojun Yang, Lixia Liu, Junmin Wei, Lili Ningxia Univ Sch Math & Stat Yinchuan 750021 Ningxia Peoples R China Xi An Jiao Tong Univ Sch Math & Stat Xian 710049 Peoples R China

Cross-domain classification of hyperspectral remote sensing images is one of the hotspots of research in recent years, and its main problem is insufficient training samples. To address this issue, few-shot learning (FSL) has emerged as a promising paradigm in cross-domain classification tasks. However, a notable limitation of most existing FSL methods is that they focus only on local information and less on the critical role of global information. Based on this, this paper proposes a new feature processing method with adaptive band selection, which takes into account the global nature of image features. Firstly, adaptive band analysis is performed in the target domain, and threshold analysis is used to determine the number of selected bands. Secondly, a band selection method is employed to select representative bands from the spectral bands of the high-dimensional data according to the determined band count. Finally, the weights of the selected bands are analyzed, fully considering the importance of pixel weight, and then the results are used as inputs for the classification model. The experimental results on various datasets show that this method can effectively improve the classification accuracy and generalization ability. Meanwhile, the results of the objective accuracy index of the proposed method in different databases improved by 3.9%, 4.7% and 5.4%.

关键词： Support vector machines Hyperspectral imaging Attention mechanisms Accuracy signal processing algorithms Image classification Classification algorithms Visualization Training Sensors Adaptive analysis attention mechanism band selection hyperspectral image classification

来源：评论

学校读者我要写书评

暂无评论

A Proximal Newton Adaptive Importance Sampler

引用

IEEE signal processing LETTERS 2025年 32卷 1545-1549页

作者： Elvira, Victor Chouzenoux, Emilie Akyildiz, O. Deniz Univ Edinburgh Sch Math Edinburgh EH8 9YL Scotland Univ Paris Saclay Inria Saclay OPIS F-91190 Saclay France Imperial Coll London Dept Math London SW7 2AZ England

Adaptive importance sampling (AIS) algorithms are a rising methodology in signal processing, statistics, and machine learning. An effective adaptation of the proposals is key for the success of AIS. Recent works have shown that gradient information about the involved target density can greatly boost performance, but its applicability is restricted to differentiable targets. In this letter, we propose a proximal Newton adaptive importance sampler for the estimation of expectations with respect to non-smooth target distributions. We implement a scaled Newton proximal gradient method to adapt the proposal distributions, enabling efficient and optimized moves even when the target distribution lacks differentiability. We show the good performance of the algorithm in two scenarios: one with convex constraints and another with non-smooth sparse priors.

关键词： Proposals Monte Carlo methods signal processing algorithms Artificial intelligence Bayes methods Convergence signal processing Inference algorithms Gradient methods Approximation algorithms Adaptive importance sampling proximal methods Newton algorithm preconditioning

来源：评论

学校读者我要写书评

暂无评论

General Steganalysis of Generative Linguistic Steganography Based on Dynamic Segment-Level Lexical Association Extraction

引用

IEEE signal processing LETTERS 2025年 32卷 191-195页

作者： Li, Songbin Du, Hui Wang, Jingang Chinese Acad Sci Inst Acoust Hainan Branch Haikou 570100 Peoples R China Univ Chinese Acad Sci Beijing 100049 Peoples R China

In scenarios where steganographic texts from various steganographic domains generated by different generative steganography algorithms are mixed, most existing linguistic steganalysis methods lack corresponding network structures designed to account for the differences in steganographic texts from different domains, leading to the potential for further improvement in their general detection performance. To address the above issue, we propose a general generative linguistic steganalysis method based on the basic idea of dynamically extracting lexical association features of different steganographic domains at the segment level. We utilize dynamic-static text feature matrix to construct a word importance semantic encoding module to mine steganography-sensitive word features of different steganographic domains. Based on the obtained features, we propose a word correlation multi-scale perception module to focus on the segment-level lexical association changes caused by secret information embedding in different domains. Experimental results show that this method can improve the detection accuracy of existing mainstream linguistic steganalysis methods in various mixed steganography scenarios.

关键词： Feature extraction Steganography Linguistics Convolution signal processing algorithms Correlation Semantics Payloads Training Data mining General detection generative linguistic steganalysis segment-level lexical association extraction

来源：评论

学校读者我要写书评

暂无评论

Effective Coherent Integration of Agile Echo signal via Improved Sparse Adaptive Matching Pursuit

引用

IEEE signal processing LETTERS 2025年 32卷 1420-1424页

作者： Lang, Ping Fu, Xiongjun Dong, Jian Yin, Junjun Yang, Jian Tsinghua Univ Dept Elect Engn Beijing 100084 Peoples R China Beijing Inst Technol Sch Integrated Circuits & Elect Beijing 100081 Peoples R China Univ Sci & Technol Beijing Sch Comp & Commun Engn Beijing 100083 Peoples R China

Radar transmits active agile waveformplays a significant role in anti-jamming. However, efficient coherent integration of target's agile echo in a coherent processing interval (CPI) usually poses a severe challenge. This letter proposes an improved sparsity adaptive matching pursue (ISAMP) to address this issue. Firstly, the agile echo signal model of random interpulse frequency and PRT joint agile (RI-FPrtJA) waveform is derived;The sparse reconstruction model of RI-FPrtJA echo signal is then mathematically deduced based on compress sensing theory;Lastly, the ISAMP is proposed to accurately accomplish sparse reconstruction based on the regularized grids mismatch correction and adaptive searching step extension. The simulation results demonstrate that the ISAMP method can achieve better coherent integration in terms of mismatch sidelode levels suppression, sparse reconstruction capacity, and computational cost, compared to some current existing methods.

关键词： Doppler effect Dictionaries Radar Frequency modulation Vectors Sparse matrices Sensors signal processing algorithms Mathematical models Adaptation models Radar jamming suppression agile waveform coherent integration sparsity adaptive matching pursue

来源：评论

学校读者我要写书评

暂无评论

Parallel State Estimation for Systems With Integrated Measurements

引用

IEEE signal processing LETTERS 2025年 32卷 371-375页

作者： Yaghoobi, Fatemeh Sarkka, Simo Aalto Univ Dept Elect Engn & Automat Espoo 02150 Finland

This paper presents parallel-in-time state estimation methods for systems with Slow-Rate inTegrated Measurements (SRTM). Integrated measurements are common in various applications, and they appear in analysis of data resulting from processes that require material collection or integration over the sampling period. Current state estimation methods for SRTM are inherently sequential, preventing temporal parallelization in their standard form. This paper proposes parallel Bayesian filters and smoothers for linear Gaussian SRTM models. For that purpose, we develop a novel smoother for SRTM models and develop parallel-in-time filters and smoother for them using an associative scan-based parallel formulation. Empirical experiments ran on a GPU demonstrate the superior time complexity of the proposed methods over traditional sequential approaches.

关键词： State estimation Smoothing methods Bayes methods Mathematical models Time complexity Kalman filters Time measurement signal processing algorithms Particle measurements Atmospheric measurements Integrated measurements state estimation parallel-in-time filtering and smoothing

来源：评论

学校读者我要写书评

暂无评论

A Simple and Efficient Method for Hybrid AOA and DTD Localization With Unknown Transmitter Location

引用

IEEE signal processing LETTERS 2025年 32卷 401-405页

作者： Zou, Yanbin Xiao, Yangpeng Zhang, Weien Shantou Univ Dept Elect & Informat Engn Shantou 515063 Peoples R China

Recently, joint target and transmitter localization using differential time-delay (DTD) and angle-of-arrival (AOA) measurements has attracted researchers' interest. Due to the fact that three Euclidean norms exist in the DTD equation, the DTD equation is difficult to tackle directly. In this paper, we divide the joint localization problem into three subproblems, respectively, the AOA-only localization problem, the hybrid AOA and time-difference-of-arrival (TDOA) localization problem, and the hybrid AOA and time-delay (TD) localization problem with known transmitter location. Then, a two-stage algorithm is developed. In the first stage, solving the AOA-only localization problem provides initial estimates. In the second stage, alternatively and iteratively solving the problem of hybrid AOA and TDOA localization and the problem of hybrid AOA and TD localization provide the improved solutions. Simulation results validate that the proposed algorithm is superior to the existing constrained weighted least-squares (CWLS) algorithm when AOA noise variance is not sufficiently small. Index Term-Angle-of-arrival (AOA), differential time-delay (DTD), time-delay (TD), time-difference-of-arrival (TDOA), elliptic localization.

关键词： Location awareness Transmitters Mathematical models Noise Estimation signal processing algorithms Sensors Covariance matrices Three-dimensional displays Position measurement Angle-of-arrival (AOA) differential time-delay (DTD) time-delay (TD) time-difference-of-arrival (TDOA) elliptic localization

来源：评论

学校读者我要写书评

暂无评论

Exploring Local Sparse Structure Prior for Image Deraining and Desnowing

引用

IEEE signal processing LETTERS 2025年 32卷 406-410页

作者： Guo, Xin Fu, Xueyang Zha, Zheng-Jun Univ Sci & Technol China Hefei 230026 Peoples R China

Existing image deraining and desnowing methods are typically trained under specific weather conditions, which limits their effectiveness in locating rain streaks and snowflakes in diverse, open scenes. This restriction often leads to suboptimal restoration performance. To address these limitations, we propose a novel local sparse structure prior for rain and snow, characterized by high pixel intensity and the locally sparse spatial distribution of rain streaks and snowflakes. Leveraging this prior, we developed an algorithm that extracts rain and snow structure masks, enabling precise localization of rain streaks and snowflake regions across open scenes. In addition, we introduce a refinement and compensation process to remove irrelevant information from the masks and correct mask estimation errors. We further construct a Mask-Guided Restoration Network (MGNet) that utilizes the rain and snow structure masks effectively and includes a mask-conditioned attention module to focus restoration efforts on degraded areas affected by rain streaks and snowflakes. Extensive experimental results demonstrate that our method significantly outperforms current state-of-the-art techniques in open scenes, effectively restoring various types of rain streaks and snowflakes with a single model parameter configuration.

关键词： Rain Snow Image restoration Training signal processing algorithms Location awareness Image color analysis Graphical models Estimation error Distribution functions image deraining image desnowing structure prior mask guidance

来源：评论

学校读者我要写书评

暂无评论

Improved Least Lncosh Based Fetal Electrocardiography Extraction in Alpha-Stable Noise

引用

IEEE signal processing LETTERS 2025年 32卷 676-680页

作者： Wang, Mengjia Ni, Bo Zhang, Jiacheng Luan, Shengyang Liu, Tao Nanjing Univ Informat Sci & Technol Sch Elect & Informat Engn Nanjing 210044 Peoples R China Nanjing Univ Informat Sci & Technol Sch Artificial Intelligence Nanjing 210044 Peoples R China Jiangsu Normal Univ Sch Elect Engn & Automat Xuzhou 221116 Peoples R China Chengdu Univ Inst Higher Educ Sichuan Prov Key Lab Pattern Recognit & Intelligent Informat Pr Chengdu 610106 Peoples R China

Fetal electrocardiography (FECG) presents an important avenue for continuous fetal monitoring. Nonetheless, effectively extracting FECG from maternal electrocardiogram (MECG) is one considerable challenge due to its weaker amplitude compared to MECG and the non-Gaussian nature of background noise. In this letter, we introduce alpha-stable noise to model the realistic interference due to its high scalability. To improve the accuracy of FECG extraction under impulsive noise (alpha-stable noise with strong impulses), we introduce the least Lncosh algorithm (Llncosh) and the improved Llncosh algorithm (ILL) is proposed based on the Amplitude Hyperbolic Tangent Transformation (AHTT) to optimize the preset parameter. Moreover, Monte Carlo experiments are carried out to investigate the capabilities of LMS-like algorithms and the ILL algorithm for FECG extraction. The results demonstrate that the ILL algorithm outperforms the LMS-like ones with carefully selected parameters, particularly showcasing superior robustness against impulsive noise. This work holds significance both in the theoretical research of adaptive filtering and in its practical application for FECG extraction.

关键词： Noise signal processing algorithms Electrocardiography Cost function Adaptive filters Robustness Accuracy Vectors Nickel Monte Carlo methods LMS algorithm Llncosh algorithm fetal electrocardiogram alpha-stable noise impulsive noise

来源：评论

学校读者我要写书评

暂无评论

Onset-and-Offset-Aware Sound Event Detection via Differentiable Frame-to-Event Mapping

引用

IEEE signal processing LETTERS 2025年 32卷 186-190页

作者： Yoshinaga, Tomoya Tanaka, Keitaro Bando, Yoshiaki Imoto, Keisuke Morishima, Shigeo Natl Inst Adv Ind Sci & Technol Tokyo 1350064 Japan Waseda Univ Tokyo 1698555 Japan Doshisha Univ Kyoto 6028580 Japan

This paper presents a sound event detection (SED) method that handles sound event boundaries in a statistically principled manner. A typical approach to SED is to train a deep neural network (DNN) in a supervised manner such that the model predicts frame-wise event activities. Since the predicted activities often contain fine insertion and deletion errors due to their temporal fluctuations, post-processing has been applied to obtain more accurate onset and offset boundaries. Existing post-processing methods are, however, non-differentiable and prohibit end-to-end (E2E) training. In this paper, we propose an E2E detection method based on a probabilistic formulation of sound event sequences called a hidden semi-Markov model (HSMM). The HSMM is utilized to transform frame-wise features predicted by a DNN into posterior probabilities of sound events represented by their class labels and temporal boundaries. We jointly train the DNN and HSMM in a supervised E2E manner by maximizing the event-wise posterior probabilities of the HSMM. This objective is a differentiable function thanks to the forward-backward algorithm of the HSMM. Experimental results with real recordings show that our method outperforms baseline systems with standard post-processing methods.

关键词： Training Posterior probability Artificial neural networks Probabilistic logic Predictive models Filtering Event detection Fluctuations signal processing algorithms Bayes methods End-to-end training hidden semi-Markov model (HSMM) neural probabilistic modeling sound event detection (SED)

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：