检索结果-内蒙古大学图书馆

CTCNet: A CNN-Transformer Cooperation Network for Face Image Super-Resolution

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Gao, Guangwei Xu, Zixiang Li, Juncheng Yang, Jian Zeng, Tieyong Qi, Guo-Jun The Institute of Advanced Technology Nanjing University of Posts and Telecommunications Nanjing China The Provincial Key Laboratory for Computer Information Processing Technology Soochow University Suzhou China The School of Communication & Information Engineering Shanghai University Shanghai China Jiangsu Key Laboratory of Image and Video Understanding for Social Safety Nanjing University of Science and Technology Nanjing China The School of Computer Science and Technology Nanjing University of Science and Technology Nanjing China The Center for Mathematical Artificial Intelligence Department of Mathematics The Chinese University of Hong Kong Hong Kong Research Center for Industries of the Future School of Engineering Westlake University OPPO Research Seattle United States

Recently, deep convolution neural networks (CNNs) steered face super-resolution methods have achieved great progress in restoring degraded facial details by joint training with facial priors. However, these methods have some obvious limitations. On the one hand, multi-task joint learning requires additional marking on the dataset, and the introduced prior network will significantly increase the computational cost of the model. On the other hand, the limited receptive field of CNN will reduce the fidelity and naturalness of the reconstructed facial images, resulting in suboptimal reconstructed images. In this work, we propose an efficient CNN-Transformer Cooperation Network (CTCNet) for face super-resolution tasks, which uses the multi-scale connected encoder-decoder architecture as the backbone. Specifically, we first devise a novel Local-Global Feature Cooperation Module (LGCM), which is composed of a Facial Structure Attention Unit (FSAU) and a Transformer block, to promote the consistency of local facial detail and global facial structure restoration simultaneously. Then, we design an efficient Feature Refinement Module (FRM) to enhance the encoded features. Finally, to further improve the restoration of fine facial details, we present a Multi-scale Feature Fusion Unit (MFFU) to adaptively fuse the features from different stages in the encoder procedure. Extensive evaluations on various datasets have assessed that the proposed CTCNet can outperform other state-of-the-art methods significantly. Source code will be available at https://***/IVIPLab/CTCNet. Copyright © 2022, The Authors. All rights reserved.

关键词： Restoration

Interpretable Saliency Map for Deep Reinforcement Learning

学校读者我要写书评

暂无评论

Interpretable Saliency Map for Deep Reinforcement Learning

2020 International Conference on computer Big Data and Artificial Intelligence, ICCBDAI 2020

作者： Zheng, Hong Dai, Yinglong Yu, Fumin Hu, Yuezhen School of Physics and Electronics Hunan Normal University Changsha410081 China College of Liberal Arts and Sciences National University of Defense Technology Changsha410073 China Hunan Provincial Key Laboratory of Intelligent Computing and Language Information Processing Hunan Normal University Changsha410081 China

Deep reinforcement learning (deep RL) achieved big successes with the advantage of deep learning techniques, while it also introduces the disadvantage of the model interpretability. Bad interpretability is a great obstacle for deep RL to be applied in real situations or human-machine interaction situations. Borrowed from the deep learning field, the techniques of saliency maps recently become popular to improve the interpretability of deep RL. However, the saliency maps still cannot provide specific and clear enough model interpretations for the behavior of deep RL agents. In this paper, we propose to use hierarchical conceptual embedding techniques to introduce prior-knowledge in the deep neural network (DNN) based models of deep RL agents and then generate the saliency maps for all the embedded factors. As a result, we can track and discover the important factors that influence the decisions of deep RL agents. © Published under licence by IOP Publishing Ltd.

关键词： Deep neural networks

Non-IID Free Federated Learning with Fuzzy Optimization for Consumer Electronics Systems

学校读者我要写书评

暂无评论

IEEE Transactions on Consumer Electronics 2025年

作者： Bai, Jun Wu, Di Zeng, Shan Zhao, Yao Qu, Youyang Yu, Shui School of Information Technology Deakin University MelbourneVIC3125 Australia School of Mathematics Physics and Computing University of Southern Queensland ToowoombaQLD4350 Australia School of Mathematics and Computer Science Wuhan Polytechnic University Wuhan430023 China School of Computing Technologies RMIT University MelbourneVIC3000 Australia Qilu University of Technology Shandong Academy of Sciences Jinan250101 China Shandong Provincial Key Laboratory of Computing Power Internet and Service Computing Shandong Fundamental Research Center for Computer Science Jinan250102 China School of Computer Science University of Technology Sydney SydneyNSW2007 Australia

—Consumer electronics suffer from data surges which lead to data privacy and integrity issues. Federated Learning (FL) keeps data with local devices which enhances privacy, and efficient device collaboration by processing data locally without transmitting sensitive information to centralized servers. However, data heterogeneity within practical FL settings poses a formidable challenge, such as client model drift, significantly impacting the convergence speed of the global model and leading to a substantial communication overhead. To address these issues arising from data heterogeneity, we propose a novel FL framework based on latent dependency optimization with fuzzy-based client selection (FCS), named FedLaDO. Specifically, in the consumer electronic client-side training, we introduce two new loss regularizers: a positive latent dependency loss and a perceptive knowledge co-distillation loss. These regularizers are integrated into the client training objective function to enhance the client models’ reinforcement learning over its distinctive training data while preserving the global knowledge inherited from the prior global model. For consumer electronic server-side model aggregation, we propose an FCS mechanism to filter out underperforming and overperforming clients and introduce a novel inverse dependency aggregation algorithm to effectively integrate drifted client models. The efficacy of our approach is validated through extensive experiments on diverse real-world datasets, showcasing its superior performance in achieving higher model convergence accuracy compared to state-of-the-art FL baseline methods. © 2025 IEEE. All rights reserved,

关键词： Federated learning

Financial Trading Decisions based on Deep Fuzzy Self-Organizing Map

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Dehao, Pei Chao, Luo School of Information Science and Engineering Shandong Normal University Jinan250014 China Shandong Provincial Key Laboratory for Novel Distributed Computer Software Technology Jinan250014 China

The volatility features of financial data would considerably change in different periods, that is one of the main factors affecting the applications of machine learning in quantitative trading. Therefore, to effectively distinguish fluctuation patterns of financial markets can provide meaningful information for the trading decision. In this article, a novel intelligent trading system based on deep fuzzy self-organizing map (DFSOM) companied with GRU networks is proposed, where DFSOM is utilized for the clustering of financial data to acquire multiple fluctuation patterns in an unsupervised way. Firstly, in order to capture the trend features and evade the effect of high noises in financial data, the images of extended candlestick charts instead of raw data are processed and the obtained features are applied for the following unsupervised learning, where candlestick charts are produced with both price and volume information. Secondly, by using the candlestick features, a two-layer deep fuzzy self-organizing map is constructed to carry out the clustering, where two-layer models carry out the clustering in multiple time scales to improve the processing of time-dependent information. Thirdly, GRU networks are used to implement the prediction task, based on which an intelligent trading model is constructed. The feasibility and effectiveness of the proposed method are verified by using various real financial data sets. Copyright © 2022, The Authors. All rights reserved.

关键词： Self organizing maps

Generalized Cross-Entropy Benchmarking for Random Circuits with Ergodicity

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Cheng, Bin Meng, Fei Zhang, Zhi-Jiong Yung, Man-Hong Shenzhen Institute for Quantum Science and Engineering Department of Physics Southern University of Science and Technology Shenzhen518055 China Centre for Quantum Technologies National University of Singapore Singapore Centre for Quantum Software and Information Faculty of Engineering and Information Technology University of Technology SydneyNSW2007 Australia Department of Physics City University of Hong Kong Tat Chee Avenue Kowloon Hong Kong QICI Quantum Information and Computation Initiative Department of Computer Science The University of Hong Kong Pokfulam Road Hong Kong International Quantum Academy Shenzhen518048 China Guangdong Provincial Key Laboratory of Quantum Science and Engineering Southern University of Science and Technology Shenzhen518055 China Shenzhen Key Laboratory of Quantum Science and Engineering Southern University of Science and Technology Shenzhen518055 China

Cross-entropy benchmarking is a central technique used to certify a quantum chip in recent experiments. To better understand its mathematical foundation and develop new benchmarking schemes, we introduce the concept of ergodicity to random circuit sampling and find that the Haar random quantum circuit satisfies an ergodicity condition—the average of certain types of post-processing function over the output bit strings is close to the average over the unitary ensemble. For noiseless random circuits, we prove that the ergodicity holds for polynomials of degree t with positive coefficients and when the random circuits form a unitary 2t-design. For strong enough noise, the ergodicity condition is violated. This suggests that ergodicity is a property that can be exploited to certify a quantum chip. We formulate the deviation of ergodicity as a measure for quantum chip benchmarking and show that it can be used to estimate the circuit fidelity for global depolarizing noise and weakly correlated noise. For a quadratic post-processing function, our framework recovers Google’s result on estimating the circuit fidelity via linear cross-entropy benchmarking (XEB), and we give a sufficient condition on the noise model characterizing when such estimation is valid. Our results establish an interesting connection between ergodicity and noise in random circuits and provide new insights into designing quantum benchmarking schemes. Copyright © 2025, The Authors. All rights reserved.

关键词： Quantum electronics

An Optimizing Parameters and Feature Selection in SVM Based on Improved Cockroach Swarm Optimization 16th

学校读者我要写书评

暂无评论

An Optimizing Parameters and Feature Selection in SVM Based ...

16th International Conference on Intelligent information Hiding and Multimedia Signal processing, IIH-MSP 2020 in conjunction with the 13th International Conference on Frontiers of information technology, Applications and Tools, FITAT 2020

作者： Nguyen, Trong-The Yu, Jie Nguyen, Thi-Thanh-Tan Lai, Quoc-Anh Ngo, Truong-Giang Dao, Thi-Kien Fujian Provincial Key Laboratory of Big Data Mining and Applications Fujian University of Technology Fuzhou China College of Mechanical and Automotive Engineering Fujian University of Technology Fuzhou China Information Technology Faculty Electric Power University Hanoi Viet Nam Department of Pattern Recognition & Image Processing Institute of Information Technology Vietnam Academy of Science and Technology Hanoi Viet Nam Faculty of Computer Science and Engineering Thuyloi University 175 Tay Son Dong Da Hanoi Viet Nam

ISBN: (纸本)9789813367562

This study improves a classifier of the support vector machine (SVM) by optimizing its parameters by adjusting cockroach swarm optimization (CSO). Classification system design includes data inputs, pre-process, and classification. The relief technique selects the feature subset, and the kernel parameters used as input for the system. The feature selection and classification of data sets were figured out by the combination of ICSO and SVM with its optimized parameters synchronous. Simulation results of the proposed scheme are compared with other systems, e.g., GA-SVM, PSO-SVM, and CSO-SVM, which show that the proposed project can achieve better classification accuracy than the different algorithms. It is promising that the proposed scheme can be applied to high-dimensional data classification, such as image classification, signal classification. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2021.

关键词： Support vector machines

Disentangled Generation Network for Enlarged License Plate Recognition and A Unified Dataset

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Li, Chenglong Yang, Xiaobin Wang, Guohao Zheng, Aihua Tan, Chang Jia, Ruoran Tang, Jin Information Materials and Intelligent Sensing Laboratory of Anhui Province Anhui Provincial Key Laboratory of Multimodal Cognitive Computation School of Artificial Intelligence Anhui University Hefei230601 China Information Materials and Intelligent Sensing Laboratory of Anhui Province Key Lab of Intelligent Computing and Signal Processing Ministry of Education Anhui Provincial Key Laboratory of Multimodal Cognitive Computation School of Computer Science and Technology Anhui University Hefei230601 China iFLYTEK Co. Ltd. Hefei230088 China

License plate recognition plays a critical role in many practical applications, but license plates of large vehicles are difficult to be recognized due to the factors of low resolution, contamination, low illumination, and occlusion, to name a few. To overcome the above factors, the transportation management department generally introduces the enlarged license plate behind the rear of a vehicle. However, enlarged license plates have high diversity as they are non-standard in position, size, and style. Furthermore, the background regions contain a variety of noisy information which greatly disturbs the recognition of license plate characters. Existing works have not studied this challenging problem. In this work, we first address the enlarged license plate recognition problem and contribute a dataset containing 9342 images, which cover most of the challenges of real scenes. However, the created data are still insufficient to train deep methods of enlarged license plate recognition, and building large-scale training data is very time-consuming and high labor cost. To handle this problem, we propose a novel task-level disentanglement generation framework based on the Disentangled Generation Network (DGNet), which disentangles the generation into the text generation and background generation in an end-to-end manner to effectively ensure diversity and integrity, for robust enlarged license plate recognition. Extensive experiments on the created dataset are conducted, and we demonstrate the effectiveness of the proposed approach in three representative text recognition frameworks. © 2022, CC BY.

关键词： Optical character recognition

Adaptive Variational Mode Time-frequency Analysis of Ship Radiated Noise 7

学校读者我要写书评

暂无评论

Adaptive Variational Mode Time-frequency Analysis of Ship Ra...

7th International Conference on information Science and Control Engineering, ICISCE 2020

作者： Zhang, Haoyi Junejo, Naveed Ur Rehman Sun, Weitao Chen, Hailan Yan, Jiaquan Minjiang University Fujian Provincial Key Laboratory of Information Processing and Intelligent Control College of Computer and Control Engineering Fuzhou China Ilma University Department of Computer Science Karachi Pakistan Northwestern Polytechnical University School of Marine Science and Technology Xi'an China Jimei University School of Science Xiamen China Minjiang University Fujian Provincial Key Laboratory of Information Processing and Intelligent Control Fuzhou China

ISBN: (纸本)9781728164069

In this paper, we have proposed a novel time-frequency analysis method implementing adaptive variational mode decomposition (AVMD) and Wigner-Ville Distribution (WVD) to visualize the local features of ship radiated noise. Unlike the traditional methods are invalid under low signal to noise ratio (SNR), the proposed method is suitable for constructing time-frequency (TF) image with the capability of mining the local feature information accurately. Firstly, we employ complete ensemble empirical mode decomposition with adaptive noise (CEEMDAN) on the raw signal to determine the numbers of variational modes which is equal to intrinsic mode functions (IMFs) numbers. Secondly, we perform VMD algorithm to extract the local features absolutely by decomposing the raw signal into IMFs, where we set the IMFs gained by CEEMDAN as the input parameter of VMD. Finally, we adopt Wigner-Ville distribution (WVD) to draw TF signatures of all the IMFs, then superpose them to reconstruct the objected signal that can solve the cross-item problem. We have conducted the comparative experiments by the real oceanic data. Under the different SNRs, we have verified the effectiveness and robustness of the proposed method, also obtained better performance in terms of resolution than compared algorithm. © 2020 IEEE.

关键词： Intrinsic mode functions

An optimized aes masking method for resisting side channel analysis 8th

学校读者我要写书评

暂无评论

An optimized aes masking method for resisting side channel a...

8th International Conference on computer Engineering and Networks, CENet 2018

作者： Jiao, Ge Li, Lang Zou, Yi College of Computer Science and Technology Hengyang Normal University HengyangHunan421002 China Hunan Provincial Key Laboratory of Intelligent Information Processing and Application HengyangHunan421002 China

ISBN: (纸本)9783030146795

In order to against the side channel analysis attack such as power, electromagnetic waves, and time attack, an optimized masking method is proposed for Advanced Encryption Standard (AES) algorithm in this paper. This scheme adopts random hamming distance mask and offset randomization strategy in the first two rounds, the last round and two rounds randomly selected in the middle of the AES algorithm to ensure the security of each intermediate value. The scheme then adopts fixed-value mask strategy in the five rounds in the middle, which can reduce the time and space consumption to recalculate S box, improve the efficiency of the algorithm and reduce the production cost. To compare with other defence methods, we build a power analysis platform and conduct extensive experiments. The experimental results show that our optimized AES masking method is more secure than the compared methods, and it is able to resist second-order correlation power analysis (CPA) attacks. © Springer Nature Switzerland AG 2020.

关键词： Hamming distance