检索结果-内蒙古大学图书馆

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

CCA-Net: Zero-shot SSVEP classification via an integration of canonical correlation analysis and deep neural network

学校读者我要写书评

暂无评论

IEEE Transactions on Instrumentation and Measurement 2025年 74卷

作者： Deng, Yang Ji, Zhiwei Wang, Yijun Zhou, S. Kevin Harbin Institute of Technology School of Life Science and Technology Heilongjiang Harbin 150001 China University of Science and Technology of China Division of Life Sciences and Medicine School of Biomedical Engineering Anhui Hefei 230026 China University of Science and Technology of China Center for Medical Imaging Robotics Analytic Computing & Learning (MIRACLE) Suzhou Institute for Advanced Research Jiangsu Suzhou 215123 China Nanjing Agricultural University College of Artificial Intelligence Jiangsu Nanjing 210095 China Chinese Academy of Sciences State Key Laboratory on Integrated Optoelectronics Institute of Semiconductors Beijing 100083 China University of Science and Technology of China Key Laboratory of Precision and Intelligent Chemistry Anhui Hefei 230026 China Chinese Academy of Sciences Key Laboratory of Intelligent Information Processing of Chinese Academy of Sciences Institute of Computing Technology Beijing 100190 China

Accurate decoding of electroencephalographic (EEG) signals is a crucial foundation for brain-computer interface (BCI) applications. Among various decoding approaches, those that do not require calibration are particularly significant for advancing BCI technologies into everyday life, as they alleviate user fatigue by eliminating the need for user-specific training. In this study, we integrate a deep neural network with canonical correlation analysis (CCA) to form the CCA-Net approach for decoding steady-state visually evoked potential (SSVEP) based BCI without user-specific calibration, i.e., at the zero-shot scenario. The CCA-Net aims to reduce the cross-subject domain gap for better transfer learning and make full use of the testing signal itself. Specifically, it adapts the cross-subject dual-domain fusion network (CSDuDoFN) by transferring the global multi-reference least-squares transformation coefficient from source subjects to both source and target data to reduce the cross-subject domain gap. In addition, CCA-Net enhances the transfer template-based canonical correlation analysis (tt-CCA) by introducing a subject-specific template to replace the sine-cosine reference template and adding an extra CCA coefficient to make full use of the testing signal itself, resulting in the Modified tt-CCA. Finally, the features extracted by CSDuDoFN and Modified tt-CCA are integrated to produce the final decoding result. Our approach leverages the strengths of both data-driven and model-driven methods and achieves state-of-the-art performance on three publicly available datasets, thus holding the potential to facilitate everyday BCI applications based on SSVEP. The reproducibility code is available at: https://***/Sungden/Zero-shot-SSVEP-classification. © 1963-2012 IEEE.

关键词： Brain-computer interface (BCI) canonical correlation analysis (CCA) deep neural network (DNN) steady-state visual evoked potential (SSVEP) zero-shot learning

Decentralized Nonconvex Robust Optimization over Unsafe Multiagent Systems: System Modeling, Utility, Resilience, and Privacy Analysis

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Hu, Jinhui Chen, Guo Li, Huaqing Cheng, Huqiang Guo, Xiaoyu Huang, Tingwen School of Automation Central South University Changsha410083 China Department of Biomedical Engineering City University of Hong Kong Kowloon Hong Kong School of Electrical Engineering and Telecommunications University of New South Wales SydneyNSW2052 Australia Chongqing Key Laboratory of Nonlinear Circuits and Intelligent Information Processing College of Electronic and Information Engineering Southwest University Chongqing400715 China Key Laboratory of Dependable Services Computing in Cyber Physical Society Ministry of Education College of Computer Science Chongqing University Chongqing400044 China Faculty of Computer Science and Control Engineering Shenzhen University of Advanced Technology Shenzhen518055 China

Privacy leakage and Byzantine failures are two adverse factors to the intelligent decision-making process of multiagent systems (MASs). Considering an unsafe MAS with these two issues, this paper targets the resolution of a class of nonconvex optimization problems under the Polyak-Lojasiewicz (P-L) condition. To address this problem, we first identify and construct the unsafe MAS model. Under this kind of unfavorable MASs, we mask the local gradients with Gaussian noises and adopt a resilient aggregation method self-centered clipping (SCC) to design a differentially private (DP) decentralized Byzantine-resilient algorithm, namely DP-SCC-PL, which simultaneously achieves differential privacy and Byzantine resilience. The convergence analysis of DP-SCC-PL is challenging since the convergence error can be contributed jointly by privacy-preserving and Byzantine-resilient mechanisms, as well as the nonconvex relaxation, which is addressed via seeking the contraction relationships among the disagreement measure of reliable agents before and after SCC aggregation, together with the optimal gap. Theoretical results reveal that DP-SCC-PL achieves consensus among all reliable agents and sublinear (inexact) convergence with well-designed step-sizes. It has also been proved that if there are no privacy issues and Byzantine agents, then the asymptotic exact convergence can be recovered. Numerical experiments verify the utility, resilience, and differential privacy of DP-SCC-PL by tackling a nonconvex optimization problem satisfying the P-L condition under various Byzantine attacks. Copyright © 2024, The Authors. All rights reserved.

关键词： Differential privacy

Improved Diversity-Promoting Collaborative Metric Learning for Recommendation

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Bao, Shilong Xu, Qianqian Yang, Zhiyong He, Yuan Cao, Xiaochun Huang, Qingming Institute of Information Engineering Chinese Academy of Sciences Beijing100093 China School of Cyber Security University of Chinese Academy of Sciences Beijing100049 China The Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences Beijing100190 China The School of Computer Science and Technology University of Chinese Academy of Sciences Beijing101408 China The Security Department of Alibaba Group Hangzhou311121 China School of Cyber Science and Technology Shenzhen Campus of Sun Yat-sen University Shenzhen518107 China University of Chinese Academy of Sciences Beijing101408 China Peng Cheng Laboratory Shenzhen518055 China

Collaborative Metric Learning (CML) has recently emerged as a popular method in recommendation systems (RS), closing the gap between metric learning and collaborative filtering. Following the convention of RS, existing practices exploit unique user representation in their model design. This paper focuses on a challenging scenario where a user has multiple categories of interests. Under this setting, the unique user representation might induce preference bias, especially when the item category distribution is imbalanced. To address this issue, we propose a novel method called Diversity-Promoting Collaborative Metric Learning (DPCML), with the hope of considering the commonly ignored minority interest of the user. The key idea behind DPCML is to introduce a set of multiple representations for each user in the system where users' preference toward an item is aggregated by taking the minimum item-user distance among their embedding set. Specifically, we instantiate two effective assignment strategies to explore a proper quantity of vectors for each user. Meanwhile, a Diversity Control Regularization Scheme (DCRS) is developed to accommodate the multi-vector representation strategy better. Theoretically, we show that DPCML could induce a smaller generalization error than traditional CML. Furthermore, we notice that CML-based approaches usually require negative sampling to reduce the heavy computational burden caused by the pairwise objective therein. In this paper, we reveal the fundamental limitation of the widely adopted hard-aware sampling from the One-Way Partial AUC (OPAUC) perspective and then develop an effective sampling alternative for the CML-based paradigm. Finally, comprehensive experiments over a range of benchmark datasets speak to the efficacy of DPCML. Code are available at https://***/statusrank/LibCML. © 2024, CC BY-NC-SA.

关键词： Adversarial machine learning

HieNet: Bidirectional Hierarchy Framework for Automated ICD Coding

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Wang, Shi Tang, Daniel Zhang, Luchen Li, Huilin Han, Ding Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences China TruX Luxembourg National Computer Network Emergency Response Technical Team Coordination Center of China China Department of Civil Engineering Technical University of Denmark Lyngby2800 Denmark Huazhong University of Science and Technology China

International Classification of Diseases (ICD) is a set of classification codes for medical records. Automated ICD coding, which assigns unique International Classification of Diseases codes with each medical record, is widely used recently for its efficiency and error-prone avoidance. However, there are challenges that remain such as heterogeneity, label unbalance, and complex relationships between ICD codes. In this work, we proposed a novel Bidirectional Hierarchy Framework(HieNet) to address the challenges. Specifically, a personalized PageRank routine is developed to capture the co-relation of codes, a bidirectional hierarchy passage encoder to capture the codes’ hierarchical representations, and a progressive predicting method is then proposed to narrow down the semantic searching space of prediction. We validate our method on two widely used datasets. Experimental results on two authoritative public datasets demonstrate that our proposed method boosts the state-of-the-art performance by a large margin. Copyright © 2022, The Authors. All rights reserved.

关键词： Semantics

Noise optimization for artificial neural networks

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Xiao, Li Zhang, Zeliang Peng, Yijie Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences Beijing100090 China Department of Management Science and Information Systems Guanghua School of Management Peking University Beijing100871 China School of computer science and technology Huazhong University of Science and Technology China

Adding noises to artificial neural network(ANN) has been shown to be able to improve robustness in previous work. In this work, we propose a new technique to compute the pathwise stochastic gradient estimate with respect to the standard deviation of the Gaussian noise added to each neuron of the ANN. By our proposed technique, the gradient estimate with respect to noise levels is a byproduct of the backpropagation algorithm for estimating gradient with respect to synaptic weights in ANN. Thus, the noise level for each neuron can be optimized simultaneously in the processing of training the synaptic weights at nearly no extra computational cost. In numerical experiments, our proposed method can achieve significant performance improvement on robustness of several popular ANN structures under both black box and white box attacks tested in various computer vision datasets. code is available at https://***/LX-doctorAI/ noiseoptimize © 2021, CC BY.

关键词： Neural networks

Computationally efficient sandbox algorithm for multifractal analysis of large-scale complex networks with tens of millions of nodes

学校读者我要写书评

暂无评论

Physical Review E 2021年第4期103卷 043303-043303页

作者： Yuemin Ding Jin-Long Liu Xiaohui Li Yu-Chu Tian Zu-Guo Yu Department of Energy and Process Engineering Norwegian University of Science and Technology 7049 Trondheim Norway School of Computer Science Queensland University of Technology Brisbane QLD 4000 Australia Key Laboratory of Intelligent Computing and Information Processing of Ministry of Education and Hunan Key Laboratory for Computation and Simulation in Science and Engineering Xiangtan University Xiangtan Hunan 411105 China School of Information Science and Engineering Wuhan University of Science and Technology Wuhan Hubei 430081 China

Among various algorithms of multifractal analysis (MFA) for complex networks, the sandbox MFA algorithm behaves with the best computational efficiency. However, the existing sandbox algorithm is still computationally expensive for MFA of large-scale networks with tens of millions of nodes. It is also not clear whether MFA results can be improved by a largely increased size of a theoretical network. To tackle these challenges, a computationally efficient sandbox algorithm (CESA) is presented in this paper for MFA of large-scale networks. Distinct from the existing sandbox algorithm that uses the shortest-path distance matrix to obtain the required information for MFA of networks, our CESA employs the compressed sparse row format of the adjacency matrix and the breadth-first search technique to directly search the neighbor nodes of each layer of center nodes, and then to retrieve the required information. A theoretical analysis reveals that the CESA reduces the time complexity of the existing sandbox algorithm from cubic to quadratic, and also improves the space complexity from quadratic to linear. Then the CESA is demonstrated to be effective, efficient, and feasible through the MFA results of (u,v)-flower model networks from the fifth to the 12th generations. It enables us to study the multifractality of networks of the size of about 11 million nodes with a normal desktop computer. Furthermore, we have also found that increasing the size of (u,v)-flower model network does improve the accuracy of MFA results. Finally, our CESA is applied to a few typical real-world networks of large scale.

关键词： Network formation & growth Fractals Fractal dimension characterization

CodeEnhance: A Codebook-Driven Approach for Low-Light Image Enhancement

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Wu, Xu Hou, XianXu Lai, Zhihui Zhou, Jie Zhang, Ya-Nan Pedrycz, Witold Shen, Linlin The Computer Vision Institute College of Computer Science and Software Engineering Shenzhen University Shenzhen518060 China Shenzhen Institute of Artificial Intelligence and Robotics for Society Shenzhen518060 China Guangdong Key Laboratory of Intelligent Information Processing Shenzhen University Shenzhen518060 China School of AI and Advanced Computing Xi’an Jiaotong-Liverpool University China National Engineering Laboratory for Big Data System Computing Technology Shenzhen University SZU Branch Shenzhen Institute of Artificial Intelligence and Robotics for Society Guangdong Shenzhen518060 China The Department of Electrical & Computer Engineering University of Alberta University of Alberta Canada

Low-light image enhancement (LLIE) aims to improve low-illumination images. However, existing methods face two challenges: (1) uncertainty in restoration from diverse brightness degradations;(2) loss of texture and color information caused by noise suppression and light enhancement. In this paper, we propose a novel enhancement approach, CodeEnhance, by leveraging quantized priors and image refinement to address these challenges. In particular, we reframe LLIE as learning an image-to-code mapping from low-light images to discrete codebook, which has been learned from high-quality images. To enhance this process, a Semantic Embedding Module (SEM) is introduced to integrate semantic information with low-level features, and a Codebook Shift (CS) mechanism, designed to adapt the pre-learned codebook to better suit the distinct characteristics of our low-light dataset. Additionally, we present an Interactive Feature Transformation (IFT) module to refine texture and color information during image reconstruction, allowing for interactive enhancement based on user preferences. Extensive experiments on both real-world and synthetic benchmarks demonstrate that the incorporation of prior knowledge and controllable information transfer significantly enhances LLIE performance in terms of quality and fidelity. The proposed CodeEnhance exhibits superior robustness to various degradations, including uneven illumination, noise, and color distortion. Copyright © 2024, The Authors. All rights reserved.

关键词： Image enhancement

Multi-turn response selection with Language Style and Topic Aware enhancement

学校读者我要写书评

暂无评论

Computer Speech & Language 2026年 95卷

作者： Weiwei Li Yuzhong Chen Junjie Xu Jiayuan Zhong Chen Dong College of Computer and Data Science Fuzhou University Fuzhou 350108 Fujian Province China Fujian Provincial Key Laboratory of Network Computing and Intelligent Information Processing Fuzhou 350108 Fujian Province China

The multi-turn response selection is an important component in retrieval-based human–computer dialogue systems. Most recent models adopt the utilization of pre-trained language models to acquire fine-grained semantic information within diverse dialogue contexts, thereby enhancing the precision of response selection. However, effectively leveraging the language style information of speakers along with the topic information in the dialogue context to enhance the semantic understanding capability of pre-trained language models still poses a significant challenge that requires resolution. To address this challenge, we propose a BERT-based Language Style and Topic Aware (BERT-LSTA) model for multi-turn response selection. BERT-LSTA augments BERT with two distinctive modules: the Language Style Aware (LSA) module and the Question-oriented Topic Window Selection (QTWS) module. The LSA module introduces a contrastive learning method to learn the latent language style information from distinct speakers in the dialogue. The QTWS module proposes a topic window segmentation algorithm to segment the dialogue context into topic windows, which facilitates the capacity of BERT-LSTA to refine and incorporate relevant topic information for response selection. Experimental results on two public benchmark datasets demonstrate that BERT-LSTA outperforms all state-of-the-art baseline models across various metrics. Furthermore, ablation studies reveal that the LSA module significantly improves performance by capturing speaker-specific language styles, while the QTWS module enhances topic relevance by filtering irrelevant contextual information.

关键词： Multi-turn response selection Language style Topic window segmentation BERT Contrastive learning