检索结果-内蒙古大学图书馆

arXiv 2023年

作者： Wang, Chao Qi, Shuren Huang, Zhiqiu Zhang, Yushu Lan, Rushi Cao, Xiaochun Fan, Feng-Lei The College of Computer Science and Technology Nanjing University of Aeronautics and Astronautics Nanjing211106 China The Department of Mathematics The Chinese University of Hong Kong Hong Kong The Guangxi Key Laboratory of Image and Graphic Intelligent Processing Guilin University of Electronic Technology Guilin541004 China The School of Cyber Science and Technology Shenzhen Campus of Sun Yat-sen University Shenzhen518107 China

The vulnerability of deep neural networks to adversarial perturbations has been widely perceived in the computer vision community. From a security perspective, it poses a critical risk for modern vision systems, e.g., the popular Deep Learning as a Service (DLaaS) frameworks. For protecting deep models while not modifying them, current algorithms typically detect adversarial patterns through discriminative decomposition for natural and adversarial data. However, these decompositions are either biased towards frequency resolution or spatial resolution, thus failing to capture adversarial patterns comprehensively. Also, when the detector relies on few fixed features, it is practical for an adversary to fool the model while evading the detector (i.e., defense-aware attack). Motivated by such facts, we propose a discriminative detector relying on a spatial-frequency Krawtchouk decomposition. It expands the above works from two aspects: 1) the introduced Krawtchouk basis provides better spatial-frequency discriminability, capturing the differences between natural and adversarial data comprehensively in both spatial and frequency distributions, w.r.t. the common trigonometric or wavelet basis;2) the extensive features formed by the Krawtchouk decomposition allows for adaptive feature selection and secrecy mechanism, significantly increasing the difficulty of the defense-aware attack, w.r.t. the detector with few fixed features. Theoretical and numerical analyses demonstrate the uniqueness and usefulness of our detector, exhibiting competitive scores on several deep models and image sets against a variety of adversarial attacks. Copyright © 2023, The Authors. All rights reserved.

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

Denoising of 3D magnetic resonance images using a residual encoder-decoder wasserstein generative adversarial network

arXiv

引用

arXiv 2018年

作者： Ran, Maosong Hu, Jinrong Chen, Yang Chen, Hu Sun, Huaiqiang Zhou, Jiliu Zhang, Yi College of Computer Science Sichuan University Chengdu610065 China Department of Computer Science Chengdu University of Information Technology Chengdu610225 China Lab of Image Science and Technology School of Computer Science and Engineering Southeast University Nanjing210096 China School of Cyber Science and Engineering Southeast University Nanjing210096 China Ministry of Education Nanjing210096 China Department of Radiology West China Hospital of Sichuan University Chengdu610041 China Guangdong Provincial Key Laboratory of Medical Image Processing Southern Medical University Guangzhou510515 China

Structure-preserved denoising of 3D magnetic resonance imaging (MRI) images is a critical step in medical image analysis. Over the past few years, many algorithms with impressive performances have been proposed. In this paper, inspired by the idea of deep learning, we introduce an MRI denoising method based on the residual encoder-decoder Wasserstein generative adversarial network (RED-WGAN). Specifically, to explore the structure similarity between neighboring slices, a 3D configuration is utilized as the basic processing unit. Residual autoencoders combined with deconvolution operations are introduced into the generator network. Furthermore, to alleviate the oversmoothing shortcoming of the traditional mean squared error (MSE) loss function, the perceptual similarity, which is implemented by calculating the distances in the feature space extracted by a pretrained VGG-19 network, is incorporated with the MSE and adversarial losses to form the new loss function. Extensive experiments are implemented to assess the performance of the proposed method. The experimental results show that the proposed RED-WGAN achieves performance superior to several state-of-the-art methods in both simulated and real clinical data. In particular, our method demonstrates powerful abilities in both noise suppression and structure preservation. Copyright © 2018, The Authors. All rights reserved.

关键词： Magnetic resonance imaging

来源：评论

学校读者我要写书评

暂无评论

Thqa: A Perceptual Quality Assessment Database for Talking Heads

Thqa: A Perceptual Quality Assessment Database for Talking H...

引用

IEEE International Conference on image processing

作者： Yingjie Zhou Zicheng Zhang Wei Sun Xiaohong Liu Xiongkuo Min Zhihua Wang Xiao-Ping Zhang Guangtao Zhai Institute of Image Communication and Network Engineering Shanghai Jiao Tong University China PengCheng Laboratory China Guangdong Lab of Machine Perception and Intelligent Computing Shenzhen MSU-BIT University China Tsinghua Shenzhen International Graduate School Tsinghua University China MoE Key Lab of Artificial Intelligence AI Institute Shanghai Jiao Tong University China

ISBN: (数字)9798350349399

ISBN: (纸本)9798350349405

In the realm of media technology, digital humans have gained prominence due to rapid advancements in computer technology. However, the manual modeling and control required for the majority of digital humans pose significant obstacles to efficient development. The speech-driven methods offer a novel avenue for manipulating the mouth shape and expressions of digital humans. Despite the proliferation of driving methods, the quality of many generated talking head (TH) videos remains a concern, impacting user visual experiences. To tackle this issue, this paper introduces the Talking Head Quality Assessment (THQA) database, featuring 800 TH videos generated through 8 diverse speechdriven methods. Extensive experiments affirm the THQA database’s richness in character and speech features. Subsequent subjective quality assessment experiments analyze correlations between scoring results and speech-driven methods, ages, and genders. In addition, experimental results show that mainstream image and video quality assessment methods have limitations for the THQA database, underscoring the imperative for further research to enhance TH video quality assessment. The THQA database is publicly accessible at https://***/zyj-2000/THQA.

关键词： Visualization Databases Shape image processing Mouth Manuals Media

来源：评论

学校读者我要写书评

暂无评论

Predefined-time terminal sliding mode control of robot manipulators

arXiv

引用

arXiv 2020年

作者： Liang, Chang-Duo Ge, Ming-Feng Liu, Zhi-Wei Wang, Yan-Wu Karimi, Hamid Reza School of Mechanical Engineering and Electronic Information China University of Geosciences Wuhan430074 China School of Artificial Intelligence and Automation Huazhong University of Science and Technology Wuhan430074 China Key Laboratory of Image Processing and Intelligent Control Ministry of Education Huazhong University of Science and Technology Wuhan430074 China Department of Mechanical Engineering Politecnico di Milano Milan20156 Italy

In this paper, we present a new terminal sliding mode control to achieve predefined-time stability of robot manipulators. The proposed control is developed based on a novel predefined-time terminal sliding mode (PTSM) surface, on which the states are forced to reach the origin in a predefined time, i.e., the settling time is independent to the initial condition and can be explicitly user-defined via adjusting some specific parameters called the predefined-time parameters. It is also demonstrated that the proposed control can provide satisfactory steady-state performance in the case of both external disturbances and parametric uncertainties. Besides, we present a formal systemic analysis method to derive the sufficient conditions for guaranteeing the predefined-time convergence of the closed-loop system. Finally, the effectiveness and performance of the presented control scheme are illustrated through both theoretical comparisons and numerical simulations. Copyright © 2020, The Authors. All rights reserved.

关键词： Sliding mode control

来源：评论

学校读者我要写书评

暂无评论

Bridging the Domain Gap in Satellite Pose Estimation: a Self-Training Approach based on Geometrical Constraints

arXiv

引用

arXiv 2022年

作者： Wang, Zi Chen, Minglin Guo, Yulan Li, Zhang Yu, Qifeng The College of Aerospace Science and Engineering National University of Defense Technology Changsha410073 China Hunan Provincial Key Laboratory of Image Measurement and Vision Navigation Changsha410073 China The School of Electronics and Communication Engineering Sun Yat-Sen University Shenzhen518000 China The College of Electronic Science and Technology National University of Defense Technology Changsha410073 China

Recently, unsupervised domain adaptation in satellite pose estimation has gained increasing attention, aiming at alleviating the annotation cost for training deep models. To this end, we propose a self-training framework based on the domain-agnostic geometrical constraints. Specifically, we train a neural network to predict the 2D keypoints of a satellite and then use PnP to estimate the pose. The poses of target samples are regarded as latent variables to formulate the task as a minimization problem. Furthermore, we leverage fine-grained segmentation to tackle the information loss issue caused by abstracting the satellite as sparse keypoints. Finally, we iteratively solve the minimization problem in two steps: pseudo-label generation and network training. Experimental results show that our method adapts well to the target domain. Moreover, our method won the 1st place on the sunlamp task of the second international Satellite Pose Estimation Competition. Copyright © 2022, The Authors. All rights reserved.

关键词： Satellites

来源：评论

学校读者我要写书评

暂无评论

Fractional wavelet scattering network and applications

arXiv

引用

arXiv 2018年

作者： Liu, Li Wu, Jiasong Li, Dengwang Senhadji, Lotfi Shu, Huazhong Ministry of Education Nanjing210096 China International Joint Laboratory of Information Display and Visualization Nanjing210096 China Nanjing210096 China INSERM U1099 Rennes35000 France Université de Rennes 1 Rennes35000 France Rennes35000 France Shandong Province Key Laboratory of Medical Physics and Image Processing Technology School of Physics and Electronics Shandong Normal University Jinan250014 China

Objective: The present study introduces a fractional wavelet scattering network (FrScatNet), which is a generalized translation invariant version of the classical wavelet scattering network (ScatNet). Methods: In our approach, the FrScatNet is constructed based on the fractional wavelet transform (FRWT). The fractional scattering coefficients are iteratively computed using FRWTs and modulus operators. The feature vectors constructed by fractional scattering coefficients are usually used for signal classification. In this work, an application example of FrScatNet is provided in order to assess its performance on pathological images. Firstly, the FrScatNet extracts feature vectors from patches of the original histological images under different orders. Then we classify those patches into target (benign or malignant) and background groups. And the FrScatNet property is analyzed by comparing error rates computed from different fractional orders respectively. Based on the above pathological image classification, a gland segmentation algorithm is proposed by combining the boundary information and the gland location. Results: The error rates for different fractional orders of FrScatNet are examined and show that the classification accuracy is significantly improved in fractional scattering domain. We also compare the FrScatNet based gland segmentation method with those proposed in the 2015 MICCAI Gland Segmentation Challenge and our method achieves comparable results. Conclusion: The FrScatNet is shown to achieve accurate and robust results. More stable and discriminative fractional scattering coefficients are obtained by the FrScatNet in this work. Significance: The added fractional order parameter is able to analyze the image in the fractional scattering domain. Copyright © 2018, The Authors. All rights reserved.

关键词： Classification (of information)

来源：评论

学校读者我要写书评

暂无评论

Finite-size scaling of geometric renormalization flows in complex networks

arXiv

引用

arXiv 2020年

作者： Chen, Dan Su, Housheng Wang, Xiaofan Pan, Gui-Jun Chen, Guanrong School of Artificial Intelligence and Automation Image Processing and Intelligent Control Key Laboratory of Education Ministry of China Huazhong University of Science and Technology Wuhan430074 China Department of Automation Shanghai University Shanghai200072 China Faculty of Physics and Electronic Science Hubei University Wuhan430062 China Department of Electrical Engineering City University of Hong Kong Hong Kong Hong Kong

Recently, the concept of geometric renormalization group provides a good approach for studying the structural symmetry and functional invariance of complex networks. Along this line, we systematically investigate the finite-size scaling of structural and dynamical observables in geometric renormalization flows of synthetic and real evolutionary networks. Our results show that these observables can be well characterized by a certain scaling function. Specifically, we show that the critical exponent implied by the scaling function is independent of these observables but only depends on the small-world properties of the network, namely, all networks located in the small-world phase have a uniform scaling exponent, while those located in the non-small-world phase and in their critical regions have another uniform scaling. More importantly, we perform extensive experiments on real evolutionary networks with small-world characteristics, and our results show that these observables also have uniform scaling in their geometric renormalization flows. Therefore, in a sense this exponent can be used as an effective measure for classifying universal small-world and non-small-world network models. © 2020, CC BY-SA.

关键词： Geometry

来源：评论

学校读者我要写书评

暂无评论

In-Context Translation: Towards Unifying image Recognition, processing, and Generation

arXiv

引用

arXiv 2024年

作者： Xue, Han Sun, Qianru Song, Li Zhang, Wenjun Huang, Zhiwu Institute of Image Communication and Network Engineering Shanghai Jiao Tong University Shanghai200240 China School of Information Systems Singapore Management University Singapore178902 Singapore MoE Key Laboratory of Artificial Intelligence AI Institute Shanghai Jiao Tong University Shanghai200240 China School of Electronics and Computer Science University of Southampton Southampton United Kingdom

We propose In-Context Translation (ICT), a general learning framework to unify visual recognition (e.g., semantic segmentation), low-level image processing (e.g., denoising), and conditional image generation (e.g., edge-to-image synthesis). Thanks to unification, ICT significantly reduces the inherent inductive bias that comes with designing models for specific tasks, and it maximizes mutual enhancement across similar tasks. However, the unification across a large number of tasks is non-trivial due to various data formats and training pipelines. To this end, ICT introduces two designs. Firstly, it standardizes input-output data of different tasks into RGB image pairs, e.g., semantic segmentation data pairs an RGB image with its segmentation mask in the same RGB format. This turns different tasks into a general translation task between two RGB images. Secondly, it standardizes the training of different tasks into a general incontext learning, where "in-context" means the input comprises an example input-output pair of the target task and a query image. The learning objective is to generate the "missing" data paired with the query. The implicit translation process is thus between the query and the generated image. In experiments, ICT unifies ten vision tasks and showcases impressive performance on their respective benchmarks. Notably, ICT performs well across three major categories of computer vision tasks, while its two competitors (Painter and PromptDiffusion) are only effective in at most two of these task categories. In addition, compared to its competitors, ICT trained on only 4 RTX 3090 GPUs is shown to be more efficient and less costly in training. Copyright © 2024, The Authors. All rights reserved.

关键词： Semantic Segmentation

来源：评论

学校读者我要写书评

暂无评论

Learning tubule-sensitive CNNs for pulmonary airway and artery-vein segmentation in CT

arXiv

引用

arXiv 2020年

作者： Qin, Yulei Zheng, Hao Gu, Yun Huang, Xiaolin Yang, Jie Wang, Lihui Yao, Feng Zhu, Yue-Min Yang, Guang-Zhong Institute of Image Processing and Pattern Recognition Institute of Medical Robotics Shanghai Jiao Tong University Shanghai China Key Laboratory of Intelligent Medical Image Analysis and Precise Diagnosis of Guizhou Province School of Computer Science and Technology Guizhou University Guiyang China Department of Thoracic Surgery Shanghai Chest Hospital Shanghai Jiao Tong University Shanghai China Université de Lyon INSA Lyon CREATIS CNRS INSERM UMR 5220 VilleurbanneU1206 France Institute of Medical Robotics School of Biomedical Engineering Shanghai Jiao Tong University Shanghai China

Training convolutional neural networks (CNNs) for segmentation of pulmonary airway, artery, and vein is challenging due to sparse supervisory signals caused by the severe class imbalance between tubular targets and background. We present a CNNs-based method for accurate airway and artery-vein segmentation in non-contrast computed tomography. It enjoys superior sensitivity to tenuous peripheral bronchioles, arterioles, and venules. The method first uses a feature recalibration module to make the best use of features learned from the neural networks. Spatial information of features is properly integrated to retain relative priority of activated regions, which benefits the subsequent channel-wise recalibration. Then, attention distillation module is introduced to reinforce representation learning of tubular objects. Fine-grained details in high-resolution attention maps are passing down from one layer to its previous layer recursively to enrich context. Anatomy prior of lung context map and distance transform map is designed and incorporated for better artery-vein differentiation capacity. Extensive experiments demonstrated considerable performance gains brought by these components. Compared with state-of-the-art methods, our method extracted much more branches while maintaining competitive overall segmentation performance. Codes and models are available at http://***/News/56. © 2020, CC BY.

关键词： Computerized tomography

来源：评论

学校读者我要写书评

暂无评论

Learning data-adaptive non-parametric kernels

The Journal of Machine Learning Research

引用

The Journal of Machine Learning Research 2020年第1期21卷 8590-8628页

作者： Fanghui Liu Xiaolin Huang Chen Gong Jie Yang Li Li Department of Electrical Engineering ESAT-STADIUS KU Leuven Belgium Institute of Image Processing and Pattern Recognition Institute of Medical Robotics Shanghai Jiao Tong University Shanghai China PCA Lab Key Laboratory of Intelligent Perception and Systems for High-Dimensional Information of Ministry of Education School of Computer Science and Engineering Nanjing University of Science and Technology China and Department of Computing Hong Kong Polytechnic University Hong Kong SAR China Department of Automation BNRist Tsinghua University China

In this paper, we propose a data-adaptive non-parametric kernel learning framework in margin based kernel methods. In model formulation, given an initial kernel matrix, a data-adaptive matrix with two constraints is imposed in an entry-wise scheme. Learning this data-adaptive matrix in a formulation-free strategy enlarges the margin between classes and thus improves the model flexibility. The introduced two constraints are imposed either exactly (on small data sets) or approximately (on large data sets) in our model, which provides a controllable trade-off between model flexibility and complexity with theoretical demonstration. In algorithm optimization, the objective function of our learning framework is proven to be gradient-Lipschitz continuous. Thereby, kernel and classifier/regressor learning can be efficiently optimized in a unified framework via Nesterov's acceleration. For the scalability issue, we study a decomposition-based approach to our model in the large sample case. The effectiveness of this approximation is illustrated by both empirical studies and theoretical guarantees. Experimental results on various classification and regression benchmark data sets demonstrate that our non-parametric kernel learning framework achieves good performance when compared with other representative kernel learning based algorithms.

关键词： support vector machines non-parametric kernel learning gradient-Lipschitz continuous

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：