检索结果-内蒙古大学图书馆

作者： Zuo, Weiliang Xin, Jingmin Liu, Changnong Zheng, Nanning Sano, Akira National Engineering Research Center for Visual Information and Applications Institute of Artificial Intelligence and Robotics Xi'An Jiaotong University National Key Laboratory of Human-Machine Hybrid Augmented Intelligence Xi'an710049 China Data Center China Construction Bank Beijing100033 China Keio University Department of System Design Engineering Yokohama223-8522 Japan

Despite some efforts and attempts have been made to improve the direction-of-arrival (DOA) estimation performance of the standard Capon beamformer (SCB) in array processing, rigorous statistical performance analyses of these modified Capon estimators are still lacking. This paper studies an improved Capon estimator (ICE) for estimating the DOAs of multiple uncorrelated narrowband signals, where the higher-order inverse (sample) array covariance matrix is used in the Capon-like cost function. By establishing the relationship between this nonparametric estimator and the parametric and classic subspace-based MUSIC (multiple signal classification), it is clarified that as long as the power order of the inverse covariance matrix is increased to reduce the influence of signal subspace components in the ICE, the estimation performance of the ICE becomes equivalent to that of the MUSIC regardless of the signal-to-noise ratio (SNR). Furthermore the statistical performance of the ICE is analyzed, and the large-sample mean-squared-error (MSE) expression of the estimated DOA is derived. Finally the effectiveness and the theoretical analysis of the ICE are substantiated through numerical examples, where the Cramer-Rao lower bound (CRB) is used to evaluate the validity of the derived asymptotic MSE expression. © 2014 Chinese Association of Automation.

关键词： Multiple signal classification

来源：评论

学校读者我要写书评

暂无评论

Text Grouping Adapter: Adapting Pre-Trained Text Detector for Layout Analysis

Text Grouping Adapter: Adapting Pre-Trained Text Detector fo...

引用

Conference on Computer Vision and Pattern Recognition (CVPR)

作者： Tianci Bi Xiaoyi Zhang Zhizheng Zhang Wenxuan Xie Cuiling Lan Yan Lu Nanning Zheng National Key Laboratory of Human-Machine Hybrid Augmented Intelligence National Engineering Research Center for Visual Information and Applications Institute of Artificial Intelligence and Robotics Xi'an Jiaotong University Microsoft Research Asia

ISBN: (数字)9798350353006

ISBN: (纸本)9798350353013

Significant progress has been made in scene text detection models since the rise of deep learning, but scene text layout analysis, which aims to group detected text instances as paragraphs, has not kept pace. Previous works either treated text detection and grouping using separate models, or train a model from scratch while using a unified one. All of them have not yet made full use of the already well-trained text detectors and easily obtainable detection datasets. In this paper, we present Text Grouping Adapter (TGA), a module that can enable the utilization of various pretrained text detectors to learn layout analysis, allowing us to adopt a well-trained text detector right off the shelf or just fine-tune it efficiently. Designed to be compatible with various text detector architectures, TGA takes detected text regions and image features as universal inputs to as-semble text instance features. To capture broader contextual information for layout analysis, we propose to predict text group masks from text instance features by one-to-many assignment. Our comprehensive experiments demonstrate that, even with frozen pretrained models, incorporating our TGA into various pretrained text detectors and text spotters can achieve superior layout analysis performance, simultaneously inheriting generalized text detection ability from pretraining. In the case of full parameter fine-tuning, we can further improve layout analysis performance.

关键词： Deep learning Analytical models Adaptation models Computer vision Layout Text detection Detectors

来源：评论

学校读者我要写书评

暂无评论

Variance reduced EXTRA and DIGing and their optimal acceleration for strongly convex decentralized optimization

The Journal of Machine Learning Research

引用

The Journal of Machine Learning Research 2022年第1期23卷 10057-10097页

作者： Huan Li Zhouchen Lin Yongchun Fang Institute of Robotics and Automatic Information Systems College of Artificial Intelligence Nankai University Tianjin China Key Laboratory of Machine Perception School of Artificial Intelligence Peking University Beijing China

We study stochastic decentralized optimization for the problem of training machine learning models with large-scale distributed data. We extend the widely used EXTRA and DIGing methods with variance reduction (VR), and propose two methods: VR-EXTRA and VR-DIGing. The proposed VR-EXTRA requires the time of O((κs+n) log 1/ε) stochastic gradient evaluations and O((κb + κc) log 1/ε) communication rounds to reach precision ε, which are the best complexities among the non-accelerated gradient-type methods, where κs and κb are the stochastic condition number and batch condition number for strongly convex and smooth problems, respectively, κc is the condition number of the communication network, and n is the sample size on each distributed node. The proposed VR-DIGing has a little higher communication cost of O((κb + κ2b) log 1/ε). Our stochastic gradient computation complexities are the same as the ones of single-machine VR methods, such as SAG, SAGA, and SVRG, and our communication complexities keep the same as those of EXTRA and DIGing, respectively. To further speed up the convergence, we also propose the accelerated VR-EXTRA and VR-DIGing with both the optimal O((√nκs+n) log 1/ε) stochastic gradient computation complexity and O(√κbκc log 1/ε) communication complexity. Our stochastic gradient computation complexity is also the same as the ones of single-machine accelerated VR methods, such as Katyusha, and our communication complexity keeps the same as those of accelerated full batch decentralized methods, such as MSDA. To the best of our knowledge, our accelerated methods are the first to achieve both the optimal stochastic gradient computation complexity and communication complexity in the class of gradient-type methods.

关键词： stochastic decentralized optimization EXTRA DIGing variance reduction acceleration

来源：评论

学校读者我要写书评

暂无评论

PASS++: A Dual Bias Reduction Framework for Non-Exemplar Class-Incremental Learning

arXiv

引用

arXiv 2024年

作者： Zhu, Fei Zhang, Xu-Yao Cheng, Zhen Liu, Cheng-Lin The Centre for Artificial Intelligence and Robotics Hong Kong Institute of Science and Innovation Chinese Academy of Sciences Hong Kong999077 Hong Kong The State Key Laboratory of Multimodal Artificial Intelligence Systems Institute of Automation of Chinese Academy of Sciences 95 Zhongguancun East Road Beijing100190 China The School of Artificial Intelligence University of Chinese Academy of Sciences Beijing100049 China

Class-incremental learning (CIL) aims to recognize new classes incrementally while maintaining the discriminability of old classes. Most existing CIL methods are exemplar-based, i.e., storing a part of old data for retraining. Without relearning old data, those methods suffer from catastrophic forgetting. In this paper, we figure out two inherent problems in CIL, i.e., representation bias and classifier bias, that cause catastrophic forgetting of old knowledge. To address these two biases, we present a simple and novel dual bias reduction framework that employs self-supervised transformation (SST) in input space and prototype augmentation (protoAug) in deep feature space. On the one hand, SST alleviates the representation bias by learning generic and diverse representations that can transfer across different tasks. On the other hand, protoAug overcomes the classifier bias by explicitly or implicitly augmenting prototypes of old classes in the deep feature space, which poses tighter constraints to maintain previously learned decision boundaries. We further propose hardness-aware prototype augmentation and multi-view ensemble strategies, leading to significant improvements. The proposed framework can be easily integrated with pre-trained models. Without storing any samples of old classes, our method can perform comparably with state-of-the-art exemplar-based approaches which store plenty of old data. We hope to draw the attention of researchers back to non-exemplar CIL by rethinking the necessity of storing old samples in CIL. 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

A Novel Dense Object Detector with Scale Balanced Sample Assignment and Refinement

引用

IEEE Transactions on Circuits and Systems for Video Technology 2025年

作者： Dong, Jinpeng Yao, Dingyi Hu, Yufeng Zhou, Sanping Zheng, Nanning Xi’an Jiaotong University National Key Laboratory of Human-Machine Hybrid Augmented Intelligence National Engineering Research Center for Visual Information and Applications Institute of Artificial Intelligence and Robotics Xi’an710049 China Xi’an Jiaotong University Shaanxi Xi’an710049 China

Scale variation of objects remains one of the crucial challenges in object detection. Currently, conventional dense detectors with fixed receptive fields and label weights are not conducive to the detection of multi-scale objects. However, the design limitations of unbalanced label weights and fixed refinement for multi-scale objects and multi-tasks in these studies make it difficult to achieve better detection performance. In this paper, we propose a novel dense detector named Balanced FCOS which consists of two components: Balanced Label Assignment (BLA) and Flexible Shape-based Refinement (FSR). The BLA implements scale-balanced sample assignment by introducing reweighting factors consisting of localization and classification scores into the label assignment. Low-quality but high-weight samples can be weakened by the BLA. Furthermore, we design a cross-reweighting mechanism in the BLA to ensure score consistency between classification and localization. The FSR implements scale-balanced sample refinement by learning flexible sample points’ offsets for multi-scale objects and multi-tasks based on objects’ coarse features to get more discriminative features with appropriate receptive field. In addition, better features obtained by FSR are beneficial to get better classification and localization scores, which can be used by BLA to produce accurate label weights. Only equipped with the BLA, we can achieve 41.7/46.6 AP under R50/R101-FCOS without any additional parameters. When combining the BLA with the FSR, our Balanced FCOS achieves SOTA results among dense detectors on the COCO test-dev set. Experiments conducted on other heads (T-Head, DyHead), detectors (DINO), and datasets (AI-TOD) further demonstrate the effectiveness of our method. (Figure presented) © 1991-2012 IEEE.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

A Crocodile-Like Pneumatic Soft Crawling Robot With Three-Dimensional Deformation Actuators

A Crocodile-Like Pneumatic Soft Crawling Robot With Three-Di...

引用

Chinese Control Conference (CCC)

作者： Zehao Qiu Qingxiang Wu Zhuoqing Liu Tong Yang Ning Sun Institute of Robotics and Automatic Information Systems Nankai University College of Artificial Intelligence Tianjin China Institute of Intelligence Technology and Robotic Systems Shenzhen Research Institute of Nankai University Shenzhen China

Pneumatic soft crawling robots (PSCRs) have excellent application prospects in disaster relief and resource exploration due to their adaptability to complex environments. However, the crawling ability of PSCRs, including speed, load capacity, etc., is difficult to meet the requirements of these applications. To this end, a crocodile-like PSCR with three-dimensional deformation actuators is designed. First, based on the analysis of the crocodile structure, four leg actuators and a body actuator are designed, respectively, and their fabrication processes are described in detail. Meanwhile, a complete structure of the crocodile-like PSCR including connectors and air circuits is assembled. Then, the geometric and finite element models of leg actuators are established to analyze bending characteristics. On this basis, according to the relationship among the actuators, different gaits are designed to achieve moving forward, turning, and other movements. Finally, experimental results verify that leg actuators are fabricated accurately and the crocodile-like PSCR has satisfactory crawling ability.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Transosv: Offline Signature Verification with Transformers

SSRN

引用

SSRN 2022年

作者： Li, Huan Wei, Ping Ma, Zeyu Li, Changkai Zheng, Nanning Institute of Artificial Intelligence and Robotics Xi’an Jiaotong University Xi’an710049 China

Signature verification is a frequently-used forensics technology in many safety related situations. Although the previous convolution neural network (CNN) based methods have made a great progress, the limitation of local neighborhood operation of CNN impedes reasoning relation of global context of signature strokes. To overcome this weakness, in this paper, we propose a novel holistic-part unified model named TransOSV based on the popular vision transformer framework to solve offline signature verification problem. The signature images are first encoded into patch sequences by the proposed transformer-based holistic encoder to learn the global signature representation. Second, considering the subtle local difference between the genuine signature and the forged signature, we design a novel contrast based part decoder along with a sparsity loss, which are utilized to learn the discriminative part features. With the learned holistic features and the part features, the proposed model is optimized by the contrast loss function. To reduce the influence of sample imbalance, we also formulate a new focal contrast loss function. Furthermore, we conduct the proposed model to learn signature representations for writer-dependent signature verification task. To the best of our knowledge, this is the first work to adopt a transformer structure for offline signature verification task. Our experimental results prove the potential of the proposed TransOSV model for both writer-independent and writer-dependent signature verification, which achieves state-of-the-art performance on four frequently-used offline signature datasets. © 2022, 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

Skeleton-Based Human Action Recognition with Noisy Labels

Skeleton-Based Human Action Recognition with Noisy Labels

引用

IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)

作者： Yi Xu Kunyu Peng Di Wen Ruiping Liu Junwei Zheng Yufan Chen Jiaming Zhang Alina Roitberg Kailun Yang Rainer Stiefelhagen Anthropomatics and Robotics Karlsruhe Institute of Technology Germany Institute for Artificial Intelligence University of Stuttgart Germany School of Robotics Hunan University China National Engineering Research Center of Robot Visual Perception and Control Technology Hunan University China

ISBN: (数字)9798350377705

ISBN: (纸本)9798350377712

Understanding human actions from body poses is critical for assistive robots sharing space with humans in order to make informed and safe decisions about the next interaction. However, precise temporal localization and annotation of activity sequences is time-consuming and the resulting labels are often noisy. If not effectively addressed, label noise negatively affects the model’s training, resulting in lower recognition quality. Despite its importance, addressing label noise for skeleton-based action recognition has been overlooked so far. In this study, we bridge this gap by implementing a framework that augments well-established skeleton-based human action recognition methods with label-denoising strategies from various research areas to serve as the initial benchmark. Observations reveal that these baselines yield only marginal performance when dealing with sparse skeleton data. Consequently, we introduce a novel methodology, NoiseEraSAR, which integrates global sample selection, co-teaching, and Cross-Modal Mixture-of-Experts (CM-MOE) strategies, aimed at mitigating the adverse impacts of label noise. Our proposed approach demonstrates better performance on the established benchmark, setting new state-of-the-art standards. The source code for this study will be made accessible at https://***/xuyizdby/NoiseEraSAR.

关键词： Training Source coding Noise Training data Benchmark testing Skeleton Noise measurement Human activity recognition Streams Standards

来源：评论

学校读者我要写书评

暂无评论

Node Classification in CAD Data: A Graph Learning Approach for Machining Feature Localization 4

Node Classification in CAD Data: A Graph Learning Approach f...

引用

4th International Conference on Electrical, Computer, Communications and Mechatronics Engineering, ICECCME 2024

作者： Bohm, Stefan Andreas Neumayer, Martin Song, Rui Rib, Fabian Knoll, Alois Technical University of Munich Chair of Robotics Artificial Intelligence and Real-Time Systems Munich Germany Rosenheim Technical University of Applied Sciences Research and Development Department Rosenheim Germany Fraunhofer Institute for Transportation and Infrastructure Systems Ingolstadt Germany Rosenheim Technical University of Applied Sciences Faculty of Engineering Sciences Rosenheim Germany

ISBN: (纸本)9798350391183

Pattern recognition is becoming increasingly important in many sectors, such as the manufacturing industry. With rising customer demands and advancing technology, product data, often represented as 3D meshes, is becoming highly complex. Therefore, intelligent approaches are needed to recognize and localize features in 3D meshes to determine complex manufacturing processes. However, previous approaches solely work on voxel-, pixel-or. STEP-based formats and not directly on mesh-based formats such as STL data. To overcome these issues, we present a configurable data generator and customize graph neural network architectures for the problem of localizing machining features directly in 3D meshes. After comparing the graph neural networks against each other, the best resulting network is compared to an existing state-of-The-Art approach, i.e., SsdNet. Our results indicate that the best-performing graph neural network exhibits superior classification accuracies on meshes with few machining features compared to SsdNet with an average F1 score of 80%. While the accuracy slightly falls behind SsdNet with more features, the graph neural network shows substantially better runtime performance results, which are, on average, 70 times faster. © 2024 IEEE.

关键词： Graph neural networks

来源：评论

学校读者我要写书评

暂无评论

Machine learning-supported CFD optimization of heat transfer in a pipe with a corrugated wall shape 26

Machine learning-supported CFD optimization of heat transfer...

引用

26th Fluid Mechanics Conference, FMC 2024

作者： Kamiński, P. Li, Y. Wawrzak, K. Tyliszczak, A. Noack, B.R. Department of Thermal Machinery Czȩstochowa University of Technology al. Armii Krajowej 21 Czȩstochowa42-201 Poland Artificial Intelligence and Aerodynamics School of Mechanical Engineering and Automation Harbin Institute of Technology Shenzhen518055 China Guangdong Provincial Key Laboratory of Intelligent Morphing Mechanisms and Adaptive Robotics Harbin Institute of Technology Shenzhen518055 China

The paper focuses on using machine learning to optimize the corrugation of a heated pipe wall to improve the uniformity of temperature distribution while minimizing pressure losses. The corrugation is characterized by a five-parameter function, allowing for extensive variations in wall shape. The machine learning process employs the Bayesian optimization method, iteratively working alongside the ANSYS Fluent code to perform RANS computations. A two-parameter cost function, which includes temperature variation and pressure drop, is used to define the optimization goal. The study demonstrates that substantial variations in flow patterns occur depending on the type of corrugation. An optimal set of corrugation parameters, ensuring the most uniform temperature distribution with minimal pressure losses, is determined within an optimization loop consisting of 1200 RANS simulations. The optimal configuration is characterized by a smooth waviness oriented outside the original wall location in a straight pipe. It ensures more than three times smaller temperature variation at only minor increase in the pressure drop. © Published under licence by IOP Publishing Ltd.

关键词： Drops

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：