检索结果-内蒙古大学图书馆

Multi-stage image denoising with the wavelet transform

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Tian, Chunwei Zheng, Menghua Zuo, Wangmeng Zhang, Bob Zhang, Yanning Zhang, David School of Software Northwestern Polytechnical University Shaanxi Xi’an710129 China National Engineering Laboratory for Integrated Aero-Space-Ground-Ocean Big Data Application Technology Shaanxi Xi’an710129 China School of Computer Science and Technology Harbin Institute of Technology Heilongjiang Harbin150001 China Peng Cheng Laboratory Guangdong Shenzhen518055 China Department of Computer and Information Science University of Macau 999078 China School of Computer Science Northwestern Polytechnical University Shaanxi Xi’an710129 China Guangdong Shenzhen518172 China Shenzhen Institute of Artificial Intelligence and Robotics for Society Shenzhen China

Deep convolutional neural networks (CNNs) are used for image denoising via automatically mining accurate structure information. However, most of existing CNNs depend on enlarging depth of designed networks to obtain better denoising performance, which may cause training difficulty. In this paper, we propose a multi-stage image denoising CNN with the wavelet transform (MWDCNN) via three stages, i.e., a dynamic convolutional block (DCB), two cascaded wavelet transform and enhancement blocks (WEBs) and a residual block (RB). DCB uses a dynamic convolution to dynamically adjust parameters of several convolutions for making a tradeoff between denoising performance and computational costs. WEB uses a combination of signal processing technique (i.e., wavelet transformation) and discriminative learning to suppress noise for recovering more detailed information in image denoising. To further remove redundant features, RB is used to refine obtained features for improving denoising effects and reconstruct clean images via improved residual dense architectures. Experimental results show that the proposed MWDCNN outperforms some popular denoising methods in terms of quantitative and qualitative analysis. Codes are available at https://***/hellloxiaotian/MWDCNN. © 2022, CC BY-NC-ND.

关键词： Wavelet transforms

Robust facial landmark detection by cross-order cross-semantic deep network

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Wan, Jun Lai, Zhihui Shen, Linlin Zhou, Jie Gao, Can Xiao, Gang Hou, Xianxu College of Computer Science and Software Engineering Shenzhen University Shenzhen518060 China School of Mathematics and Statistics Hanshan Normal University Chaozhou521041 China Shenzhen Institute of Artificial Intelligence and Robotics for Society Shenzhen518060 China

Recently, convolutional neural networks (CNNs)-based facial landmark detection methods have achieved great success. However, most of existing CNN-based facial landmark detection methods have not attempted to activate multiple correlated facial parts and learn different semantic features from them that they can not accurately model the relationships among the local details and can not fully explore more discriminative and fine semantic features, thus they suffer from partial occlusions and large pose variations. To address these problems, we propose a cross-order cross-semantic deep network (CCDN) to boost the semantic features learning for robust facial landmark detection. Specifically, a cross-order two-squeeze multi-excitation (CTM) module is proposed to introduce the cross-order channel correlations for more discriminative representations learning and multiple attention-specific part activation. Moreover, a novel cross-order cross-semantic (COCS) regularizer is designed to drive the network to learn cross-order cross-semantic features from different activation for facial landmark detection. It is interesting to show that by integrating the CTM module and COCS regularizer, the proposed CCDN can effectively activate and learn more © 2020, CC-BY.

关键词： Semantics

Geometry Constrained Weakly Supervised Object Localization

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Lu, Weizeng Jia, Xi Xie, Weicheng Shen, Linlin Zhou, Yicong Duan, Jinming Computer Vision Institute School of Computer Science and Software Engineering Shenzhen University China Shenzhen Institute of Artificial Intelligence and Robotics for Society China School of Computer Science University of Birmingham United Kingdom Department of Computer and Information Science University of Macau China

We propose a geometry constrained network, termed GC-Net, for weakly supervised object localization (WSOL). GC-Net consists of three modules: a detector, a generator and a classifier. The detector predicts the object location defined by a set of coefficients describing a geometric shape (i.e. ellipse or rectangle), which is geometrically constrained by the mask produced by the generator. The classifier takes the resulting masked images as input and performs two complementary classification tasks for the object and background. To make the mask more compact and more complete, we propose a novel multi-task loss function that takes into account area of the geometric shape, the categorical cross-entropy and the negative entropy. In contrast to previous approaches, GC-Net is trained end-to-end and predict object location without any post-processing (e.g. thresholding) that may require additional tuning. Extensive experiments on the CUB-200-2011 and ILSVRC2012 datasets show that GC-Net outperforms state-of-the-art methods by a large margin. Our source code is available at https://***/lwzeng/GC-Net. Copyright © 2020, The Authors. All rights reserved.

关键词： Geometry

iLGaCo: Incremental Learning of Gait Covariate Factors

学校读者我要写书评

暂无评论

iLGaCo: Incremental Learning of Gait Covariate Factors

IEEE International Joint Conference on Biometrics (IJCB)

作者： Zihao Mu Francisco M. Castro Manuel J. Marín-Jiménez Nicolás Guil Yan-Ran Li Shiqi Yu College of Computer Science and Software Engineering Shenzhen University China University of Málaga Spain University of Córdoba Spain Shenzhen Institute of Artificial Intelligence and Robotics for Society (AIRS) China Southern University of Science and Technology China

ISBN: (数字)9781728191867

ISBN: (纸本)9781728191874

Gait is a popular biometric pattern used for identifying people based on their way of walking. Traditionally, gait recognition approaches based on deep learning are trained using the whole training dataset. In fact, if new data (classes, view-points, walking conditions, etc.) need to be included, it is necessary to re-train again the model with old and new data samples. In this paper, we propose iLGaCo, the first incremental learning approach of covariate factors for gait recognition, where the deep model can be updated with new information without re-training it from scratch by using the whole dataset. Instead, our approach performs a shorter training process with the new data and a small subset of previous samples. This way, our model learns new information while retaining previous knowledge. We evaluate iLGaCo on CASIA-B dataset in two incremental ways: adding new view-points and adding new walking conditions. In both cases, our results are close to the classical `training-from-scratch' approach, obtaining a marginal drop in accuracy ranging from 0.2% to 1.2%, what shows the efficacy of our approach. In addition, the comparison of iLGaCo with other incremental learning methods, such as LwF and iCarl, shows a significant improvement in accuracy, between 6% and 15% depending on the experiment.

关键词： Training Gait recognition Adaptation models Feature extraction Legged locomotion Task analysis Biological system modeling

Corrections to "Toward Adaptive Knowledge Transfer in Multifactorial Evolutionary Computation"

学校读者我要写书评

暂无评论

IEEE transactions on cybernetics 2024年第11期54卷 7116页

作者： Lei Zhou Liang Feng Kay Chen Tan Jinghui Zhong Zexuan Zhu Kai Liu Chao Chen Key Laboratory of Dependable Service Computing in Cyber Physical Society Ministry of Education Chongqing University Chongqing China College of Computer Science Chongqing University Chongqing China Department of Computer Science City University of Hong Kong kowloon Hong Kong City University of Hong Kong Shenzhen Research Institute Shenzhen China School of Computer Science and Engineering South China University of Technology Guangzhou China College of Computer Science and Software Engineering Shenzhen University Shenzhen China Shenzhen Institute of Artificial Intelligence and Robotics for Society Shenzhen China

Presents corrections to the paper, (Corrections to "Toward Adaptive Knowledge Transfer in Multifactorial Evolutionary Computation").

关键词： Evolutionary computation Knowledge transfer Cybernetics

An efficient 2-opt operator for the robotic task sequencing problem

学校读者我要写书评

暂无评论

An efficient 2-opt operator for the robotic task sequencing ...

2019 IEEE International Conference on Real-Time Computing and robotics, RCAR 2019

作者： Li, Hong Liu, Si-Yang Huang, Yan-Wei Chen, Yong-Quan Fu, Zhang-Hua College of Automation & College of Artificial Intelligence Nanjing University of Posts and Telecommunications Nanjing210023 China Institute of Robotics and Intelligent Manufacturing Chinese University of HongKong Shenzhen China School of Software Engineering Xi’an Jiao Tong University Xi’an China

ISBN: (纸本)9781728137261

Nowadays, automated guided vehicles (AGVs) are widely used in many real life applications, such as in modern factories and logistics systems. Generally, an AGV is assigned a number of random tasks, and different execution orders of the tasks correspond to different moving distances. Therefore, it is important to determine the task execution order. This problem is known as the robotic task sequencing problem, which could be transformed to an equivalent asymmetric travelling salesman problem (ATSP). In the field of TSP, the 2-opt movements is a basic operator which has been widely used by local-search based heuristics. However, for the ATSP, given an incumbent solution with N tasks, the current best method requires a complexity of O(N3) to evaluate all the O(N2) possible 2-opt based movements, and thus, the computational cost is too expensive, especially for large-scale instances. This paper develops a series of data structures, to reduce the above time complexity from O(N3) to O(N2). Experimental results based on 60 task sets indicate that, the proposed method can significantly improve the efficiency of 2-opt based local search. © 2018 IEEE.

关键词： Local search (optimization)

Chattering-free fixed-time sliding mode control for bilateral teleoperation under unknown time-varying delay via disturbance and state observers

学校读者我要写书评

暂无评论

Advanced Control for Applications: Engineering and Industria...

Advanced Control for Applications: engineering and Industrial Systems 2020年第4期2卷

作者： Abadi, Ali Soltani Sharif Hosseinabadi, Pooyan Alinaghi Mekhilef, Saad Ordys, Andrzej Department of Electrical Engineering Faculty of Engineering Yazd University Yazd Iran Faculty of Engineering University of Malaya Kuala Lumpur Malaysia School of Software and Electrical Engineering Faculty of Science Engineering and Technology Swinburne University of Technology Melbourne Australia Center of Research Excellence in Renewable Energy and Power Systems King Abdulaziz University Jeddah Saudi Arabia The Institute of Automatic Control and Robotics Faculty of Mechatronics Warsaw University of Technology Warsaw Poland

This paper proposes a new chattering-free Fixed-time Observer-Based Sliding Mode Control (FOBSMC) scheme for synchronization of two bilateral teleoperations under unknown time-varying delay. The system is subjected to unknown disturbances which are estimated in a fixed time by utilizing the Disturbance Observer-based SMC scheme. The fixed-time State Observer-based SMC is designed to estimate the unmeasured velocity state, while the position state is assumed to be available. Fixed-time stability method is used to provide the system convergence time independently of initial states. A FOBSMC scheme is first designed for master system of bilateral teleoperation under unknown time-varying delay to track the environmental torque by the human operating torque in the presence of time delay in the communication channel, as well as estimating the unknown disturbances and unmeasured states. A FOBSMC scheme is designed to synchronize slave system to master system in the presence of time delay in the communication channel, as well as estimating disturbances and states. The stability analysis is performed for closed-loop system of combined controller-observer by using Lyapunov theory. The efficacy of the proposed method to fulfill a good transparency and stability under time-varying communication delays is tested by performing numerical simulation in Simulink/MATLAB. © 2020 John Wiley & Sons Ltd.

关键词： Time delay

Taming Self-Supervised Learning for Presentation Attack Detection: De-Folding and De-Mixing

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Kong, Zhe Zhang, Wentian Liu, Feng Luo, Wenhan Liu, Haozhe Shen, Linlin Ramachandra, Raghavendra College of Computer Science and Software Engineering Shenzhen University Shenzhen518060 China SZU Branch Shenzhen Institute of Artificial Intelligence and Robotics for Society China Guangdong Key Laboratory of Intelligent Information Processing Shenzhen University Shenzhen518060 China School of Cyber Science and Technology Sun Yat-sen University Shenzhen Campus Guangdong Shenzhen518107 China Norwegian University of Science and Technology Gjøvik2818 Norway

Biometric systems are vulnerable to Presentation Attacks (PA) performed using various Presentation Attack Instruments (PAIs). Even though there are numerous Presentation Attack Detection (PAD) techniques based on both deep learning and hand-crafted features, the generalization of PAD for unknown PAI is still a challenging problem. In this work, we empirically prove that the initialization of the PAD model is a crucial factor for the generalization, which is rarely discussed in the community. Based on such observation, we proposed a self-supervised learning-based method, denoted as DF-DM. Specifically, DF-DM is based on a global-local view coupled with De-Folding and De-Mixing to derive the task-specific representation for PAD. During De-Folding, the proposed technique will learn region-specific features to represent samples in a local pattern by explicitly minimizing generative loss. While De-Mixing drives detectors to obtain the instance-specific features with global information for more comprehensive representation by minimizing interpolation-based consistency. Extensive experimental results show that the proposed method can achieve significant improvements in terms of both face and fingerprint PAD in more complicated and hybrid datasets when compared with state-of-the-art methods. When training in CASIA-FASD and Idiap Replay-Attack, the proposed method can achieve an 18.60% Equal Error Rate (EER) in OULU-NPU and MSU-MFSD, exceeding baseline performance by 9.54%. The source code of the proposed technique is available at https://***/kongzhecn/dfdm. Copyright © 2021, The Authors. All rights reserved.

关键词： Supervised learning

Precise iterative closest point algorithm with corner point constraint for isotropic scaling registration

学校读者我要写书评

暂无评论

Precise iterative closest point algorithm with corner point ...

作者： Du, Shaoyi Cui, Wenting Wu, Liyang Zhang, Sirui Zhang, Xuetao Xu, Guanglin Xu, Meifeng Institute of Artificial Intelligence and Robotics Xi’an Jiaotong University Xi’anShaanxi710049 China School of Software Engineering Xi’an Jiaotong University Xi’anShaanxi710049 China Air Force Engineering University Xi’anShaanxi710038 China The Second Affiliated Hospital of Xi’an Jiaotong University Xi’anShaanxi710004 China

The traditional iterative closest point (ICP) algorithm could register two point sets well, but it is easily affected by local dissimilarity. To deal with this problem, this paper proposes an isotropic scaling ICP algorithm with corner point constraint. First of all, because the corner points can preserve the similarity of the whole shapes, an objective function based on least square error is proposed under the guidance of the corner points. Second, a new ICP algorithm is proposed to complete the isotropic scaling registration. At each iterative step of this new algorithm, the correspondence is built based on the closest point searching, and then a closed-form solution of the transformation is computed. This new algorithm converges monotonically to a local minimum from any given initial scaling transformation. To obtain the expected minimum, the traditional scaling ICP algorithm is applied to compute the initial transformation. The experimental results demonstrate that our algorithm can prevent the influence of the local dissimilarity and improve the registration precision compared with the traditional ICP algorithm. © 2017, Springer-Verlag GmbH Germany.

关键词： Iterative methods