检索结果-内蒙古大学图书馆

International Conference on Information Science and Technology (ICIST)

作者： Haojin Li Sitian Qin Hongyu Jia Jiqiang Feng Department of Mathematics Harbin Institute of Technology Weihai China Department of Mathematics and Statistics Shenzhen Key Laboratory of Advanced Machine Learning and Applications Shenzhen University Shenzhen China

Most of the research on uncertainty and imprecision that is widespread in the real world can be abstracted into interval-valued optimization problems whose cost function or constraint function is a closed interval. In this paper, a zeroing neurodynamic (ZND) approach is designed for solving a class of constrained time-varying optimization problems with closed interval-valued cost functions. By virtue of the projection operator and the optimality conditions of the interval-valued optimization problem, the time-varying interval-valued optimization problem is transformed into a nonlinear equation system to be solved. For the reformulated nonlinear equation system, the proposed ZND solver has the ability to track its theoretical solution within pre-defined time. This significantly improves the convergence rate of the ZND solver, making the ZND solver more promising for complex engineering tasks. To the best of our knowledge, it is the first time applying the ZND solver to solve the time-varying interval value optimization problem. Furthermore, the introduction of the projection operator greatly reduces the computational complexity of this ZND solver, saving costs for its hardware implementation. Finally, a numerical example is given to demonstrate the effectiveness of the proposed approach.

关键词：

来源：评论

学校读者我要写书评

暂无评论

0-minimization methods for image restoration problems based on wavelet frames

引用

Inverse Problems 2019年第6期35卷

作者： Lu, Jian Qiao, Ke Li, Xiaorui Lu, Zhaosong Zou, Yuru Shenzhen Key Laboratory of Advanced Machine Learning and Applications College of Mathematics and Statistics Shenzhen University Shenzhen China College of Mathematics and Statistics Shenzhen University Shenzhen China Department of Mathematics Simon Fraser University Burnaby Canada

In this paper we consider a class of 0-minimization and wavelet frame-based models for image deblurring and denoising. Mathematically, they can be formulated as minimizing the sum of a data fidelity term and the 0-'norm' of the framelet coefficients of the underlying image, and we are particularly interested in three different types of data fidelity forms for image restoration problems. We first study the first-order optimality conditions for these models. We then propose a penalty decomposition (PD) method for solving these problems in which a sequence of penalty subproblems are solved by a block coordinate descent (BCD) method. Under some suitable assumptions, we establish that any accumulation point of the sequence generated by the PD method satisfies the first-order optimality conditions of these problems. Moreover, for the problems in which the data fidelity term is convex, we show that such an accumulation point is a local minimizer of the problems. In addition, we show that any accumulation point of the sequence generated by the BCD method is a block coordinate minimizer of the penalty subproblem. Furthermore, under some convexity assumptions on the data fidelity term, we prove that such an accumulation point is a local minimizer of the penalty subproblem. Numerical simulations show that the proposed 0-minimization methods enjoy great potential for image deblurring and denoising in terms of solution quality and/or speed. © 2019 IOP Publishing Ltd.

关键词： Image reconstruction

来源：评论

学校读者我要写书评

暂无评论

MMA regularization: decorrelating weights of neural networks by maximizing the minimal angles 20

MMA regularization: decorrelating weights of neural networks...

引用

Proceedings of the 34th International Conference on Neural Information Processing Systems

作者： Zhennan Wang Canqun Xiang Wenbin Zou Chen Xu Shenzhen Key Laboratory of Advanced Machine Learning and Applications Guangdong Key Laboratory of Intelligent Information Processing Institute of Artificial Intelligence and Advanced Communication College of Electronics and Information Engineering Shenzhen University Institute of Artificial Intelligence and Advanced Communication College of Mathematics and Statistics Shenzhen University

ISBN: (纸本)9781713829546

The strong correlation between neurons or filters can significantly weaken the generalization ability of neural networks. Inspired by the well-known Tammes problem, we propose a novel diversity regularization method to address this issue, which makes the normalized weight vectors of neurons or filters distributed on a hypersphere as uniformly as possible, through maximizing the minimal pairwise angles (MMA). This method can easily exert its effect by plugging the MMA regularization term into the loss function with negligible computational overhead. The MMA regularization is simple, efficient, and effective. Therefore, it can be used as a basic regularization method in neural network training. Extensive experiments demonstrate that MMA regularization is able to enhance the generalization ability of various modern models and achieves considerable performance improvements on CIFAR100 and TinyImageNet datasets. In addition, experiments on face verification show that MMA regularization is also effective for feature learning.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Transferable Adversarial Attacks for Deep Scene Text Detection

Transferable Adversarial Attacks for Deep Scene Text Detecti...

引用

International Conference on Pattern Recognition

作者： Shudeng Wu Tao Dai Guanghao Meng Bin Chen Jian Lu Shu-Tao Xia Tsinghua Shenzhen International Graduate School Tsinghua University Shenzhen China PCL Research Center of Networks and Communications Peng Cheng Laboratory Shenzhen China Shenzhen Key Laboratory of Advanced Machine Learning and Applications Shenzhen University China

ISBN: (纸本)9781728188089;9781728188096

Scene text detection (STD) aims to locate text in images and plays an important role in many computer vision tasks including automatic driving and text recognition systems. Recently, deep neural networks (DNNs) have been widely and successfully used in scene text detection, leading to plenty of DNN-based STD methods including regression-based and segmentation-based STD methods. However, recent studies have also shown that DNN is vulnerable to adversarial attacks, which can significantly degrade the performance of DNN models. In this paper, we investigate the robustness of DNN-based STD methods against adversarial attacks. To this end, we propose a generic and efficient attack method to generate adversarial examples, which are produced by adding small but imperceptible adversarial perturbation to the input images. Experiments on attacking four various models and a real-world STD engine of Google optical character recognition (OCR) show that the state-of-the-art DNN-based STD methods including regression-based and segmentation-based methods are vulnerable to adversarial attacks.

关键词： Image segmentation Text recognition Perturbation methods Neural networks Optical imaging Robustness Internet

来源：评论

学校读者我要写书评

暂无评论

Sample-aware Data Augmentor for Scene Text Recognition

Sample-aware Data Augmentor for Scene Text Recognition

引用

International Conference on Pattern Recognition

作者： Guanghao Meng Tao Dai Shudeng Wu Bin Chen Jian Lu Yong Jiang Shu-Tao Xia Tsinghua Shenzhen International Graduate School Tsinghua University Shenzhen China PCL Research Center of Networks and Communications Peng Cheng Laboratory Shenzhen China Shenzhen Key Laboratory of Advanced Machine Learning and Applications Shenzhen University China

Deep neural networks (DNNs) have been widely used in scene text recognition, and achieved remarkable performance. Such DNN-based scene text recognizers usually require plenty of training data for training, but data collection and annotation is usually cost-expensive in practice. To alleviate this issue, data augmentation is often applied to train the scene text recognizers. However, existing data augmentation methods including affine transformation and elastic transformation methods suffer from the problems of under- and over-diversity, due to the complexity of text contents and shapes. In this paper, we propose a sample-aware data augmentor to transform samples adaptively based on the contents of samples. Specifically, our data augmentor consists of three parts: gated module, affine transformation module, and elastic transformation module. In our data augmentor, affine transformation module focuses on keeping the affinity of samples, while elastic transformation module aims to improve the diversity of samples. With the gated module, our data augmentor determines transformation type adaptively based on the properties of training samples and the recognizer capability during the training process. Besides, our framework introduces an adversarial learning strategy to optimize the augmentor and the recognizer jointly. Extensive experiments on scene text recognition benchmarks show that our sample-aware data augmentor significantly improves the performance of state-of-the-art scene text recognizer.

关键词： Training Handwriting recognition Text recognition Shape Pose estimation Neural networks Training data

来源：评论

学校读者我要写书评

暂无评论

An improved group theory-based optimization algorithm for discounted 0-1 knapsack problem

引用

Advances in Computational Intelligence 2021年第5期1卷 1-11页

作者： Wang, Ran Zhang, Zichao Ng, Wing W. Y. Wu, Wenhui College of Mathematics and Statistics Shenzhen University Shenzhen China Shenzhen Key Laboratory of Advanced Machine Learning and Applications Shenzhen University Shenzhen China Guangdong Key Laboratory of Intelligent Information Processing Shenzhen University Shenzhen China School of Computer Science and Engineering South China University of Technology Guangzhou China College of Electronics and Information Engineering Shenzhen University Shenzhen China

Discounted 0-1 knapsack problem (D0-1KP) has been proved to be NP-hard, thus a lot of researches focus on designing non-deterministic algorithms to solve it. Group theory-based optimization algorithm (GTOA), as a recently proposed evolutionary algorithm (EA), can provide satisfactory results to D0-1KP. GTOA introduces important theories of algebra, i.e., group theory, to describe combinatorial optimization problems, and applies the classic operations in group theory to design operators for EA. In order to generate a better solution according to a set of existing solutions during each evolutionary iteration, an important operator called random linear combination operator (RLCO) is designed. However, the practical meaning of applying the operations in group theory is hard to explain, and the proposed RLCO is lack of interpretability, causing difficulties in analyzing and improving the algorithm. In this paper, to improve the interpretability and further enhance the performance, we propose a new operator named random xor operator (RXO), and interpret it from the view point of bitwise operation. By replacing RLCO with RXO, a new GTOA algorithm is realized for D0-1KP. Experimental results demonstrate that it can provide very competitive performance.

关键词：

来源：评论

学校读者我要写书评

暂无评论

MMA Regularization: Decorrelating weights of neural networks by maximizing the minimal angles

arXiv

引用

arXiv 2020年

作者： Wang, Zhennan Xiang, Canqun Zou, Wenbin Xu, Chen Shenzhen Key Laboratory of Advanced Machine Learning and Applications Guangdong Key Laboratory of Intelligent Information Processing Institute of Artificial Intelligence and Advanced Communication College of Electronics and Information Engineering Shenzhen University China The Institute of Artificial Intelligence and Advanced Communication College of Mathematics and Statistics Shenzhen University China

关键词： Neural networks

来源：评论

学校读者我要写书评

暂无评论

Crlnet: Cascaded Resolution learning Network for Unstructured Semantic Segmentation in Natural Scenes

SSRN

引用

SSRN 2024年

作者： Li, Wei Tian, Shishun Hua, Guoguang Liao, Muxin Zhang, Yuhang Zou, Wenbin Guangdong Key Laboratory of Intelligent Information Processing Shenzhen University Guangdong Shenzhen518060 China Shenzhen Key Laboratory of Advanced Machine Learning and Applications Shenzhen University Guangdong Shenzhen518060 China College of Electronics and Information Engineering Shenzhen University Guangdong Shenzhen518060 China

With the increasing demand for environmental perception in practical applications such as rescue robots, autonomous driving, and drone navigation, unstructured semantic segmentation has received widespread attention. Different from the structured street scene analysis with clear road topography, natural scenes contain irregular objects and different terrains with highly similar appearances, which pose significant challenges for unstructured semantic segmentation. Existing semantic segmentation methods typically employ feature fusion to improve segmentation performance. However, they cannot fully leverage feature information of different resolutions and their network receptive fields are limited, which leads to some degradation in segmentation accuracy. To tackle this issue, we propose a cascaded resolution learning network (CRLNet) to improve the segmentation performance through global textual embedding and multi-resolution feature learning. The proposed network constructs a multi-path segmentation system, which integrates multi-resolution feature information from different paths and progressively achieves fine learning of local features. CRLNet includes two vital modules:Partition-Fusion Channel Attention Module (PFCAM) and Features learning Module (FLM). The PFCAM is a computationally efficient channel attention module to improve the segmentation confusion caused by similar objects, which assigns partition-fusion and channel attention on multi-path textual information. FLM is designed to learn resolution feature maps of different paths, which is help to refining object representation and improving the segmentation performance by integrating multi-path resolution feature maps. Extensive experiments on real natural scene datasets (RUGD and RELLIS) and street scene dataset (Cityscapes) demonstrate that the proposed CRLNet outperforms existing efficient semantic segmentation methods in terms of accuracy. The code will be available at https://***/lv881314/CRLNet

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

OSRE: Object-to-Spot Rotation Estimation for Bike Parking Assessment

arXiv

引用

arXiv 2023年

作者： Alfasly, Saghir Al-Huda, Zaid Bello, Saifullah Elazab, Ahmed Lu, Jian Xu, Chen Shenzhen Key Laboratory of Advanced Machine Learning and Applications Shenzhen University China Guangdong Key Laboratory of Intelligent Information Processing China School of Computing and Artificial Intelligent Southwest Jiaotong University China School of Biomedical Engineering Shenzhen University China

Current deep models provide remarkable object detection in terms of object classification and localization. However, estimating object rotation with respect to other visual objects in the visual context of an input image still lacks deep studies due to the unavailability of object datasets with rotation annotations. This paper tackles these two challenges to solve the rotation estimation of a parked bike with respect to its parking area. First, we leverage the power of 3D graphics to build a camera-agnostic well-annotated Synthetic Bike Rotation Dataset (SynthBRSet). Then, we propose an object-to-spot rotation estimator (OSRE) by extending the object detection task to further regress the bike rotations in two axes. Since our model is purely trained on synthetic data, we adopt image smoothing techniques when deploying it on real-world images. The proposed OSRE is evaluated on synthetic and real-world data providing promising results. Our data and code are available at https://***/OSRE/. © 2023, CC BY.

关键词： Rotation

来源：评论

学校读者我要写书评

暂无评论

Robust Sparse Coding for Mobile Image Labeling on the Cloud

引用

IEEE Transactions on Circuits and Systems for Video Technology 2017年第1期27卷 62-72页

作者： Tao, Dapeng Cheng, Jun Gao, Xinbo Li, Xuelong Deng, Cheng School of Information Science and Engineering Yunnan University Kunming650091 China Laboratory for Human Machine Control Shenzhen Institutes of Advanced Technology Chinese Academy of Sciences Shenzhen518055 China Chinese University of Hong Kong Hong Kong School of Electronic Engineering Xidian University Xi'an710071 China State Key Laboratory of Transient Optics and Photonics Center for OPTical IMagery Analysis and Learning Xi'an Institute of Optics and Precision Mechanics Xi'an710119 China

With the rapid development of the mobile service and online social networking service, a large number of mobile images are generated and shared on the social networks every day. The visual content of these images contains rich knowledge for many uses, such as social categorization and recommendation. Mobile image labeling has, therefore, been proposed to understand the visual content and received intensive attention in recent years. In this paper, we present a novel mobile image labeling scheme on the cloud, in which mobile images are first and efficiently transmitted to the cloud by Hamming compressed sensing, such that the heavy computation for image understanding is transferred to the cloud for quick response to the queries of the users. On the cloud, we design a sparse correntropy framework for robustly learning the semantic content of mobile images, based on which the relevant tags are assigned to the query images. The proposed framework (called maximum correntropy-based mobile image labeling) is very insensitive to the noise and the outliers, and is optimized by a half-quadratic optimization technique. We theoretically show that our image labeling approach is more robust than the squared loss, absolute loss, Cauchy loss, and many other robust loss function-based sparse coding methods. To further understand the proposed algorithm, we also derive its robustness and generalization error bounds. Finally, we conduct experiments on the PASCAL VOC'07 data set and empirically demonstrate the effectiveness of the proposed robust sparse coding method for mobile image labeling. © 1991-2012 IEEE.

关键词： Social networking (online)

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：