检索结果-内蒙古大学图书馆

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

作者： Yuanhao Meng Lue Wang Qiang Zhou Xin Zhang Liang Zhang Yanhua Wang Radar Technology Research Institute Beijing Institute of Technology Beijing China Xi'an Modern Control Technology Research Institute 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

In recent years, high-resolution range profiles (HRRPs) have played a significant role in radar target recognition. The pose sensitivity of HRRPs results in unsatisfactory target recognition capabilities under sparse viewing angles. However, for non-cooperative targets, obtaining full-view HRRPs is often challenging, leading to suboptimal performance in HRRP-based target recognition. To address the issue of target recognition under sparse viewing angles, we propose an end-to-end model DGR for sparse view recognition that integrates combined generation and recognition tasks. The DGR model extracts deep features of HRRPs through an attention mechanism and utilizes these features for both target recognition and the generation of adjacent-view HRRPs, with both tasks mutually reinforcing each other for improved performance in recognition and data generation. Furthermore, by employing domain adaptation methods, the model learns the variability of target HRRPs in the source domain and applies this knowledge to the target domain, enhancing its generalization ability. Experimental results demonstrate that the DGR model achieves optimal recognition and generation capabilities simultaneously.

关键词： Adaptation models Sensitivity Target recognition Radar Data collection Feature extraction Generative adversarial networks Data augmentation Data models Data mining

来源：评论

学校读者我要写书评

暂无评论

Fault Diagnosis for Small Samples Based on VMR

Fault Diagnosis for Small Samples Based on VMR

引用

Chinese Automation Congress (CAC)

作者： Xuejin Wu Yanghu Hu Yali Wu Department of Information and Control Engineering Shaanxi Key Laboratory of Complex System Control and Intelligent Information Processing Xi'an University of Technology Xi'an China State Key Laboratory of Metal Extrusion and Forging Equipment Technology China National Heavy Machinery Research Institute Co. Ltd Xi'an China

ISBN: (数字)9798350368604

ISBN: (纸本)9798350368611

The scarcity of fault samples presents a significant challenge for fault diagnosis in industrial processes. Conventional methods often fail to deliver satisfactory results when dealing with small sample sizes. In addressing the issue of small sample fault diagnosis in industrial processes, this paper utilizes the Variational Mode Reconstruction(VMR) algorithm to screen the best components decomposed by the Variational Mode Decomposition(VMD) through the envelope entropy then random weighting them and signal reconstruction to achieve data enhancement, to enrich the sample size and to prevent the model overfitting phenomenon due to the scarcity of samples. Meanwhile, this paper integrates Convolutional Neural Network (CNN) and Long Short-term Memory Neural Network (LSTM) to propose a network model of spatio-temporal feature fusion for feature extraction and classification. The experiments demonstrate that this model not only enhances data diversity but also ensures consistency before and after enhancement, effectively mitigating overfitting. Furthermore, it guarantees high recognition and generalization rates in fault diagnosis.

关键词： Fault diagnosis Training Neural networks Rolling bearings Feature extraction Data models Signal reconstruction Convolutional neural networks Long short term memory Overfitting

来源：评论

学校读者我要写书评

暂无评论

IR-GAN: Image Manipulation with Linguistic Instruction by Increment Reasoning

arXiv

引用

arXiv 2022年

作者： Liu, Zhenhuan Deng, Jincan Li, Liang Cai, Shaofei Xu, Qianqian Wang, Shuhui Huang, Qingming Key Laboratory of Intelligent Information Processing Institute of Computing Technology CAS Beijing China School of Computer Science and Technology University of Chinese Academy of Sciences Beijing China Peng Cheng Laboratory Shenzhen China

Conditional image generation is an active research topic including text2image and image translation. Recently image manipulation with linguistic instruction brings new challenges of multimodal conditional generation. However, traditional conditional image generation models mainly focus on generating high-quality and visually realistic images, and lack resolving the partial consistency between image and instruction. To address this issue, we propose an Increment Reasoning Generative Adversarial Network (IR-GAN), which aims to reason the consistency between visual increment in images and semantic increment in instructions. First, we introduce the word-level and instruction-level instruction encoders to learn user's intention from history-correlated instructions as semantic increment. Second, we embed the representation of semantic increment into that of source image for generating target image, where source image plays the role of referring auxiliary. Finally, we propose a reasoning discriminator to measure the consistency between visual increment and semantic increment, which purifies user's intention and guarantees the good logic of generated target image. Extensive experiments and visualization conducted on two datasets show the effectiveness of IR-GAN. © 2022, CC BY.

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

Real-time Image Recognition System based on Ultra-Low-Latency Spiking Neural Networks

Real-time Image Recognition System based on Ultra-Low-Latenc...

引用

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

作者： Bin Lan Xi Zhang Heng Dong Ming Xu Beijing Institute of Technology Chongqing Innovation Center Chongqing China Beijing Institute of Technology Beijing China Sichuan TianFu New Area Beijing Institute of Technology Innovation Equipment Research Institute Chengdu China National Key Laboratory of Science and Technology on Space-Born Intelligent Information Processing(SBIIP) Beijing China

ISBN: (数字)9798331515669

ISBN: (纸本)9798331515676

Remote sensing technology plays an important role in many tasks such as natural disaster detection, weather and climate monitoring and military defense. Currently, remote sensing image processing predominantly relies on Convolutional Neural Networks (CNNs) and Transformers, which require a huge amount of multiplication and addition operations, bringing pressure to the deployment of satellite platforms with strict power consumption and computing power constraints. Spiking neural network (SNN), where the signal is encoded as a spike train instead of analog values, significantly reduces energy consumption compared to traditional artificial neural network. This paper proposes an all-input parallel deployment approach that minimizes or eliminates interactions with off-chip memory, thereby accelerating inference speed and reducing power consumption. We deployed LeNet ultra-low latency SNN on the Xilinx VC709 Board. Experimental results demonstrate that the proposed accelerator achieves a processing speed of 1240 frames per second, an accuracy rate of 98.14%, and a power consumption of only 0.745 Watts, making it well-suited for the low power and real-time requirements of remote sensing tasks.

关键词： Power demand Accuracy Satellites Spiking neural networks Transformers Real-time systems Resource management Remote sensing Monitoring Meteorology

来源：评论

学校读者我要写书评

暂无评论

Towards Accurate Unified Anomaly Segmentation

Towards Accurate Unified Anomaly Segmentation

引用

IEEE Workshop on Applications of Computer Vision (WACV)

作者： Wenxin Ma Qingsong Yao Xiang Zhang Zhelong Huang Zihang Jiang S. Kevin Zhou Division of Life Sciences and Medicine School of Biomedical Engineering University of Science and Technology of China (USTC) Hefei Anhui China Center for Medical Imaging Robotics Analytic Computing & Learning (MIRACLE) USTC Suzhou Institute for Advance Research Suzhou Jiangsu China Stanford University Palo Alto California United State School of Medicine Shanghai University Shanghai China Key Laboratory of Precision and Intelligent Chemistry USTC Hefei Anhui China Key Laboratory of Intelligent Information Processing of Chinese Academy of Sciences (CAS) Institute of Computing Technology CAS

ISBN: (数字)9798331510831

ISBN: (纸本)9798331510848

Unsupervised anomaly detection (UAD) from images strives to model normal data distributions, creating discriminative representations to distinguish and precisely localize anomalies. Despite recent advancements in the efficient and unified one-for-all scheme, challenges persist in accurately segmenting anomalies for further monitoring. Moreover, this problem is obscured by the widely-used AUROC metric under imbalanced UAD settings. This motivates us to emphasize the significance of precise segmentation of anomaly pixels using pAP and DSC as metrics. To address the unsolved segmentation task, we introduce the Unified Anomaly Segmentation (UniAS). UniAS presents a multi-level hybrid pipeline that progressively enhances normal information from coarse to fine, incorporating a novel multi-granularity gated CNN (MGG-CNN) into Transformer layers to explicitly aggregate local details from different granularities. UniAS achieves state-of-the-art anomaly segmentation performance, attaining 65.12/59.33 and 40.06/32.50 in pAP/DSC on the MVTec-AD and VisA datasets, respectively, surpassing previous methods significantly. The codes are shared at https://***/Mwxinnn/UniAS.

关键词： Measurement Image segmentation Computer vision Codes Pipelines Logic gates Transformers Data models Monitoring Anomaly detection

来源：评论

学校读者我要写书评

暂无评论

Open Set HRRP Recognition Using Adaptive Learning with Enclosed Decision Boundaries

Open Set HRRP Recognition Using Adaptive Learning with Enclo...

引用

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

作者： Binhua Yu Ping-An Liu Yichen Liu Hongyu Wang Liang Zhang Yanhua Wang Kun Liu Radar Technology Research Institute Beijing Institute of Technology Beijing China Xi’an Modern Control Technology Research Institute 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 Chongqing China

ISBN: (数字)9798331515669

ISBN: (纸本)9798331515676

High resolution range profiles (HRRP), which contain fine geometric structure information of targets, plays animportant role in the field of Radar automatic target recognition (RATR). In the actual application of RATR, radar may often capture targets that are non-cooperative, making it difficult to establish a comprehensive database, and traditional recognition algorithms are prone to misjudgment when facing unknown targets. Therefore, Open set recognition (OSR) is proposed to simultaneously recognize in-database and out-of-database targets. Considering the pose sensitivity of HRRP, minor changes in the target’s pose can cause significant changes in the HRRP images, leading to a potentially dispersed distribution of samples from the same category in the feature space, which makes it difficult for traditional fixed decision boundaries in OSR to adapt. To address this, this paper proposes an HRRP open set recognition method capable of adaptively learning closed decision boundaries. Based on Hierarchical dirichlet processes (HDP), the method achieves adaptive clustering of subclasses under different categories according to the data distribution characteristics of each category, determining multiple small decision boundaries within each category, and allowing the decision boundaries to dynamically adjust according to the sample features. Finally, experiments with real HRRP data have verified the effectiveness of the proposed method.

关键词： Training Sensitivity Image resolution Image recognition Target recognition Databases Imaging Radar applications Signal resolution Dispersion

来源：评论

学校读者我要写书评

暂无评论

Lightweight CNN for Radar HRRP Recognition Using NAS-Based Pruning and Multi-Knowledge Distillation

Lightweight CNN for Radar HRRP Recognition Using NAS-Based P...

引用

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

作者： Zhilong Zhang Heke Wu Yinhui Xu Liang Zhang Yanhua Wang Radar Technology Research Institute Beijing Institute of Technology Beijing China Zhengzhou Academy of Intelligent Technology Beijing Institute of Technology Zhengzhou China Xi'an Modern Control Technology Research Institute Xi'an China Beijing Key Laboratory of Embedded Real-time Information Processing Technology Beijing China Chongqing Innovation Center Beijing Institute of Technology Chongqing China

ISBN: (数字)9798331515669

ISBN: (纸本)9798331515676

Deep convolutional neural network (CNN) has been widely studied in radar target high resolution range profile (HRRP) recognition. However, the CNN with deep structure requires high storage and computational capabilities, thus restricting its applications with limited resources. In this paper, we propose a differentiable neural architecture search (NAS)-based channel pruning and multi-knowledge distillation (MKD) to prune and fine-tune the CNN for lightweight. In the pruning stage, NAS method is used to automatically find the good-performance pruning structure by optimizing channel preserve scores. After the search process, these scores are used for global pruning to derive the pruned model. In the fine-tuning stage, MKD method combine the physical scattering knowledge with the category knowledge from pretrained model to restore the pruned model performance. Experimental results on VGG-16 with HRRP dataset inversed from the MSTAR show that the recognition accuracy of the proposed method decreases 1.52% by using 5% model parameters.

关键词： Accuracy Target recognition Neural networks Scattering Radar Data processing Data models Neural architecture search Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

SSF-Net: Spatial-Spectral Fusion Network with Spectral Angle Awareness for Hyperspectral Object Tracking

引用

IEEE Transactions on Image processing 2025年 34卷 3518-3532页

作者： Wang, Hanzheng Li, Wei Xia, Xiang-Gen Du, Qian Tian, Jing Beijing Institute of Technology School of Information and Electronics Beijing100081 China National Key Laboratory of Science and Technology on Space-Born Intelligent Information Processing Beijing100081 China Beijing Institute of Technology Guangdong Zhuhai519088 China University of Delaware Department of Electrical and Computer Engineering NewarkDE19716 United States Mississippi State University Department of Electrical and Computer Engineering StarkvilleMS39762 United States

Hyperspectral video (HSV) offers valuable spatial, spectral, and temporal information simultaneously, making it highly suitable for handling challenges such as background clutter and visual similarity in object tracking. However, existing methods primarily focus on band regrouping and rely on RGB trackers for feature extraction, resulting in limited exploration of spectral information and difficulties in achieving complementary representations of object features. In this paper, a spatial-spectral fusion network with spectral angle awareness (SSF-Net) is proposed for hyperspectral (HS) object tracking. Firstly, to address the issue of insufficient spectral feature extraction in existing networks, a spatial-spectral feature backbone (S2FB) is designed. With the spatial and spectral extraction branch, a joint representation of texture and spectrum is obtained. Secondly, a spectral attention fusion module (SAFM) is presented to capture the intra- and inter-modality correlation to obtain the fused features from the HS and RGB modalities. It can incorporate the visual information into the HS context to form a robust representation. Thirdly, to ensure a more accurate response to the object position, a spectral angle awareness module (SAAM) is designed to investigate the region-level spectral similarity between the template and search images during the prediction stage. Furthermore, a novel spectral angle awareness loss (SAAL) is developed to offer guidance for the SAAM based on similar regions. Finally, to obtain the robust tracking results, a weighted prediction method is considered to combine the HS and RGB predicted motions of objects to leverage the strengths of each modality. Extensive experiments on the HOTC-2020, HOTC-2024, and BihoT datasets demonstrate the effectiveness of the proposed SSF-Net compared with state-of-the-art trackers. © 1992-2012 IEEE.

关键词： Image segmentation

来源：评论

学校读者我要写书评

暂无评论

ReconBoost: Boosting Can Achieve Modality Reconcilement

arXiv

引用

arXiv 2024年

作者： Hua, Cong Xu, Qianqian Bao, Shilong Yang, Zhiyong Huang, Qingming Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences Beijing China School of Computer Science and Technology University of Chinese Academy of Sciences Beijing China Institute of Information Engineering Chinese Academy of Sciences Beijing China School of Cyber Security University of Chinese Academy of Sciences Beijing China Key Laboratory of Big Data Mining and Knowledge Management Chinese Academy of Sciences Beijing China

This paper explores a novel multi-modal alternating learning paradigm pursuing a reconciliation between the exploitation of uni-modal features and the exploration of cross-modal interactions. This is motivated by the fact that current paradigms of multi-modal learning tend to explore multi-modal features simultaneously. The resulting gradient prohibits further exploitation of the features in the weak modality, leading to modality competition, where the dominant modality overpowers the learning process. To address this issue, we study the modality-alternating learning paradigm to achieve reconcilement. Specifically, we propose a new method called ReconBoost to update a fixed modality each time. Herein, the learning objective is dynamically adjusted with a reconcilement regularization against competition with the historical models. By choosing a KL-based reconcilement, we show that the proposed method resembles Friedman's Gradient-Boosting (GB) algorithm, where the updated learner can correct errors made by others and help enhance the overall performance. The major difference with the classic GB is that we only preserve the newest model for each modality to avoid overfitting caused by ensembling strong learners. Furthermore, we propose a memory consolidation scheme and a global rectification scheme to make this strategy more effective. Experiments over six multi-modal benchmarks speak to the efficacy of the method. We release the code at https://***/huacong/ReconBoost. 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

Causal-IQA: Towards the Generalization of Image Quality Assessment Based on Causal Inference 41

Causal-IQA: Towards the Generalization of Image Quality Asse...

引用

41st International Conference on Machine Learning, ICML 2024

作者： Zhong, Yan Wu, Xingyu Zhang, Li Yang, Chenxi Jiang, Tingting School of Mathematical Sciences Peking University Beijing China National Engineering Research Center of Visual Technology National Key Laboratory for Multimedia Information Processing School of Computer Science Peking University Beijing China Department of Computing The Hong Kong Polytechnic University Hong Kong Hefei Institute of Physical Science Chinese Academy of Sciences University of Science and Technology of China Hefei China National Biomedical Imaging Center Peking University Beijing China

Due to the high cost of Image Quality Assessment (IQA) datasets, achieving robust generalization remains challenging for prevalent deep learning-based IQA *** address this, this paper proposes a novel end-to-end blind IQA method: ***, we first analyze the causal mechanisms in IQA tasks and construct a causal graph to understand the interplay and confounding effects between distortion types, image contents, and subjective human ***, through shifting the focus from correlations to causality, Causal-IQA aims to improve the estimation accuracy of image quality scores by mitigating the confounding effects using a causality-based optimization *** optimization strategy is implemented on the sample subsets constructed by a Counterfactual Division process based on the Backdoor *** experiments illustrate the superiority of Causal-IQA. Copyright 2024 by the author(s)

关键词： Image correlation

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：