检索结果-内蒙古大学图书馆

arXiv 2024年

作者： Tang, Jialiang Chen, Shuo Gong, Chen School of Computer Science and Engineering Nanjing University of Science and Technology China Key Laboratory of Intelligent Perception and Systems for High-Dimensional Information of Ministry of Education China Jiangsu Key Laboratory of Image and Video Understanding for Social Security China Center for Advanced Intelligence Project RIKEN Japan Department of Automation Institute of Image Processing and Pattern Recognition Shanghai Jiao Tong University China

Data-free knowledge distillation aims to learn a compact student network from a pre-trained large teacher network without using the original training data of the teacher network. Existing collection-based and generation-based methods train student networks by collecting massive real examples and generating synthetic examples, respectively. However, they inevitably become weak in practical scenarios due to the difficulties in gathering or emulating sufficient real-world data. To solve this problem, we propose a novel method called Hybrid Data-Free Distillation (HiDFD), which leverages only a small amount of collected data as well as generates sufficient examples for training student networks. Our HiDFD comprises two primary modules, i.e., the teacher-guided generation and student distillation. The teacher-guided generation module guides a Generative Adversarial Network (GAN) by the teacher network to produce high-quality synthetic examples from very few real-world collected examples. Specifically, we design a feature integration mechanism to prevent the GAN from overfitting and facilitate the reliable representation learning from the teacher network. Meanwhile, we drive a category frequency smoothing technique via the teacher network to balance the generative training of each category. In the student distillation module, we explore a data inflation strategy to properly utilize a blend of real and synthetic data to train the student network via a classifier-sharing-based feature alignment technique. Intensive experiments across multiple benchmarks demonstrate that our HiDFD can achieve state-of-the-art performance using 120 times less collected data than existing methods. Code is available at https://***/tangjialiang97/HiDFD. Copyright © 2024, The Authors. All rights reserved.

关键词： Students

来源：评论

学校读者我要写书评

暂无评论

Image Classification with Deep Reinforcement Active Learning

arXiv

引用

arXiv 2024年

作者： Jiu, Mingyuan Song, Xuguang Sahbi, Hichem Li, Shupan Chen, Yan Guo, Wei Guo, Lihua Xu, Mingliang School of Computer and Artificial Intelligence Zhengzhou University China Engineering Research Center of Intelligent Swarm Systems Ministry of Education China National Supercomputing Center Zhengzhou China Sorbonne University CNRS LIP6 ParisF-75005 France Luoyang float glass group Co. Ltd State Key Laboratory of Advanced Technology for Float Glass China

Deep learning is currently reaching outstanding performances on different tasks, including image classification, especially when using large neural networks. The success of these models is tributary to the availability of large collections of labeled training data. In many real-world scenarios, labeled data are scarce, and their hand-labeling is time, effort and cost demanding. Active learning is an alternative paradigm that mitigates the effort in hand-labeling data, where only a small fraction is iteratively selected from a large pool of unlabeled data, and annotated by an expert (a.k.a oracle), and eventually used to update the learning models. However, existing active learning solutions are dependent on handcrafted strategies that may fail in highly variable learning environments (datasets, scenarios, etc). In this work, we devise an adaptive active learning method based on Markov Decision Process (MDP). Our framework leverages deep reinforcement learning and active learning together with a Deep Deterministic Policy Gradient (DDPG) in order to dynamically adapt sample selection strategies to the oracle’s feedback and the learning environment. Extensive experiments conducted on three different image classification benchmarks show superior performances against several existing active learning strategies. Copyright © 2024, The Authors. All rights reserved.

关键词： Deep reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Multimodal Emotion Recognition Based on Multi-Scale Facial Features and Cross-Modal Attention 26

Multimodal Emotion Recognition Based on Multi-Scale Facial F...

引用

26th International Conference on Industrial technology, ICIT 2025

作者： Bao, Chengao Chen, Luefeng Li, Min Wu, Min Pedrycz, Witold Hirota, Kaoru School of Automation China University of Geosciences Wuhan430074 China School of Automation Engineering Research Center of Intelligent Technology for Geo-Exploration Ministry of Education China University of Geosciences Hubei Key Laboratory of Advanced Control and Intelligent Automation for Complex Systems Wuhan430074 China University of Alberta Department of Electrical and Computer Engineering EdmontonABT6R 2G7 Canada Tokyo Institute of Technology Yokohama226-8502 Japan Tokyo Institute of Technology Tokyo226-8502 Japan

ISBN: (纸本)9798331521950

A multi-modal emotion recognition method based on facial multi-scale features and cross-modal attention (MS-FCA) network is proposed. The MSFCA model improves the traditional single-branch ViT network into a two-branch ViT architecture by using classification tokens in each branch to interact with picture embeddings in the other branch, which facilitates effective interactions between different scales of information. Subsequently, audio features are extracted using ResNet18 network. The cross-modal attention mechanism is used to obtain the weight matrices between different modal features, making full use of inter-modal correlation and effectively fusing visual and audio features for more accurate emotion recognition. Two datasets are used for the experiments: eNTERFACE'05 and REDVESS dataset. The experimental results show that the accuracy of the proposed method on the eNTERFACE'05 and REDVESS datasets is 85.42% and 83.84% respectively, which proves the effectiveness of the proposed method. © 2025 IEEE.

关键词： Modal analysis

来源：评论

学校读者我要写书评

暂无评论

A Synergistic Ensemble Approach for Enhanced Time Series Forecasting in Crime Analytics

Research Square

引用

Research Square 2025年

作者： Rani, Reenu Rohith, M. Mehta, Rohan Israr, Sabeeh Tamboli, Umar Chavan, Sanvi School of Advanced Sciences Vellore Institute of Technology Vellore India School of Computer Science Engg. & Info. Systems Vellore Institute of Technology Vellore India School of Computer Science Engg. Vellore Institute of Technology Vellore India

—This study proposes a novel ensemble approach of RF Regression, ANNs, and ARIMA for time series forecasting. To address the objectives of the present research, sensitive and restricted crime data obtained from the Mumbai police has been used. It covers a number of years and entails detailed records of various categories of offenses that have been committed in the area monthly. Several techniques of data preprocessing are applied to ensure that the data in the given set is fit to train the model and they include data cleaning, scaling, and handling of missing values. The hybrid ANN-ARIMA-RF approach captures the special advantages of each component technology: ANNs are employed for nonlinear patterns while ARIMA is employed for the linear patterns in residuals and RF is applied on both models outputs. The hybrid of ARIMA and ANN outperforms the individual ARIMA and ANN models when applied to the exclusive crime dataset to forecast future crime rates. This is because the developed model improves the prediction accuracy as shown by the lowest Mean Absolute Percentage Error. This study differs from other works due to the utilization of a unique dataset and the integration of several forecasting methods that improve upon the individual ones. © 2025, CC BY.

关键词： Data reduction

来源：评论

学校读者我要写书评

暂无评论

TraSeTR: Track-to-segment transformer with contrastive query for instance-level instrument segmentation in robotic surgery

arXiv

引用

arXiv 2022年

作者： Zhao, Zixu Jin, Yueming Heng, Pheng-Ann Department Of Computer Science And Engineering The Chinese University Of Hong Kong Hong Kong Guangdong-Hong Kong-Macao Joint Laboratory Of Human-Machine Intelligence-Synergy Systems Shenzhen Institute Of Advanced Technology Chinese Academy Of Sciences China Department Of Computer Science University College London United Kingdom

Surgical instrument segmentation - in general a pixel classification task - is fundamentally crucial for promoting cognitive intelligence in robot-assisted surgery (RAS). However, previous methods are struggling with discriminating instrument types and instances. To address above issues, we explore a mask classification paradigm that produces per-segment predictions. We propose TraSeTR, a novel Track-to-Segment Transformer that wisely exploits tracking cues to assist surgical instrument segmentation. TraSeTR jointly reasons about the instrument type, location, and identity with instance-level predictions i.e., a set of class-bbox-mask pairs, by decoding query embeddings. Specifically, we introduce the prior query that encoded with previous temporal knowledge, to transfer tracking signals to current instances via identity matching. A contrastive query learning strategy is further applied to reshape the query feature space, which greatly alleviates the tracking difficulty caused by large temporal variations. The effectiveness of our method is demonstrated with state-of-the-art instrument type segmentation results on three public datasets, including two RAS benchmarks from EndoVis Challenges and one cataract surgery dataset CaDIS. © 2022, CC BY-NC-SA.

关键词： Surgical equipment

来源：评论

学校读者我要写书评

暂无评论

Class-Aware Patch Embedding Adaptation for Few-Shot Image Classification

Class-Aware Patch Embedding Adaptation for Few-Shot Image Cl...

引用

International Conference on computer Vision (ICCV)

作者： Fusheng Hao Fengxiang He Liu Liu Fuxiang Wu Dacheng Tao Jun Cheng Shenzhen Institute of Advanced Technology Guangdong-Hong Kong-Macao Joint Laboratory of Human-Machine Intelligence-Synergy Systems Chinese Academy of Sciences China The Chinese University of Hong Kong Hong Kong China AIAI School of Informatics University of Edinburgh United Kingdom School of Computer Science Faculty of Engineering The University of Sydney Australia

"A picture is worth a thousand words", significantly beyond mere a categorization. Accompanied by that, many patches of the image could have completely irrelevant meanings with the categorization if they were independently observed. This could significantly reduce the efficiency of a large family of few-shot learning algorithms, which have limited data and highly rely on the comparison of image patches. To address this issue, we propose a Class-aware Patch Embedding Adaptation (CPEA) method to learn "class-aware embeddings" of the image patches. The key idea of CPEA is to integrate patch embeddings with class-aware embeddings to make them class-relevant. Furthermore, we define a dense score matrix between class-relevant patch embeddings across images, based on which the degree of similarity between paired images is quantified. Visualization results show that CPEA concentrates patch embeddings by class, thus making them class-relevant. Extensive experiments on four benchmark datasets, miniImageNet, tieredImageNet, CIFAR-FS, and FC-100, indicate that our CPEA significantly outperforms the existing state-of-the-art methods. The source code is available at https://***/FushengHao/CPEA.

关键词：

来源：评论

学校读者我要写书评

暂无评论

EEG-Based Epileptic Seizure Detection via Machine/Deep Learning Approaches: A Systematic Review

引用

Computational Intelligence and Neuroscience 2022年第0期2022卷 6486570页

作者： Ahmad, Ijaz Wang, Xin Zhu, Mingxing Wang, Cheng Pi, Yao Khan, Javed Ali Khan, Siyab Samuel, Oluwarotimi Williams Chen, Shixiong Li, Guanglin CAS Key Laboratory of Human-Machine Intelligence-Synergy Systems Shenzhen Institute of Advanced Technology Chinese Academy of Sciences Shenzhen China Shenzhen College of Advanced Technology University of Chinese Academy of Sciences Shenzhen China Guangdong-Hong Kong-Macao Joint Laboratory of Human-Machine Intelligence-Synergy Systems Chinese Academy of Sciences Shenzhen China School of Electronics and Information Engineering Harbin Institute of Technology Shenzhen China School of Biomedical Engineering Sun Yat-Sen University Guangzhou China Department of Software Engineering University of Science and Technology Khyber Pakhtunkhwa Bannu Pakistan Institute of Computer Science and Information Technology The University of Agriculture Khyber Pakhtunkhwa Peshawar Pakistan

Epileptic seizure is one of the most chronic neurological diseases that instantaneously disrupts the lifestyle of affected individuals. Toward developing novel and efficient technology for epileptic seizure management, recent diagnostic approaches have focused on developing machine/deep learning model (ML/DL)-based electroencephalogram (EEG) methods. Importantly, EEG's noninvasiveness and ability to offer repeated patterns of epileptic-related electrophysiological information have motivated the development of varied ML/DL algorithms for epileptic seizure diagnosis in the recent years. However, EEG's low amplitude and nonstationary characteristics make it difficult for existing ML/DL models to achieve a consistent and satisfactory diagnosis outcome, especially in clinical settings, where environmental factors could hardly be avoided. Though several recent works have explored the use of EEG-based ML/DL methods and statistical feature for seizure diagnosis, it is unclear what the advantages and limitations of these works are, which might preclude the advancement of research and development in the field of epileptic seizure diagnosis and appropriate criteria for selecting ML/DL models and statistical feature extraction methods for EEG-based epileptic seizure diagnosis. Therefore, this paper attempts to bridge this research gap by conducting an extensive systematic review on the recent developments of EEG-based ML/DL technologies for epileptic seizure diagnosis. In the review, current development in seizure diagnosis, various statistical feature extraction methods, ML/DL models, their performances, limitations, and core challenges as applied in EEG-based epileptic seizure diagnosis were meticulously reviewed and compared. In addition, proper criteria for selecting appropriate and efficient feature extraction techniques and ML/DL models for epileptic seizure diagnosis were also discussed. Findings from this study will aid researchers in deciding the most efficient ML/DL m

关键词： Electroencephalography

来源：评论

学校读者我要写书评

暂无评论

Graph Confidence Intercalibration Network for Intracranial Aneurysm Lesion Instance Segmentation in Dsa

SSRN

引用

SSRN 2024年

作者： Ye, Haili Mo, Yancheng Tang, Chen Liao, Mingqian Zhang, Xiaoqing Dai, Limeng Li, Baihua Liu, Jiang Research Institute of Trustworthy Autonomous Systems Department of Computer Science and Engineering Southern University of Science and Technology Shenzhen518055 China Department of Computer Science Loughborough University LoughboroughLE11 3TU United Kingdom School of Ophthalmology and Optometry Eye Hospital Wenzhou Medical University Wenzhou325027 China Center for High Performance Computing and Shenzhen Key Laboratory of Intelligent Bioinformatics Shenzhen Institute of Advanced Technology Chinese Academy of Sciences Shenzhen518055 China Shenzhen People’s Hospital Neurosurgery Department Shenzhen518020 China China

Intracranial aneurysm (IA) lesion segmentation is significant for its treatment and prognosis. Although exiting deep network-based instance methods have good IA lesion segmentation results based on digital subtraction angiography (DSA) images, they still face great challenges with instance confidence bias and imprecise boundary segmentation, which may negatively affect IA diagnosis. To tackle these problems, this paper proposes a novel graph confidence intercalibration network (GCINet) to automatically segment IA lesions from DSA images. To be specific, we design a graph confidence intercalibration (GCI) module to mitigate instance confidence bias by dynamically adjusting their confidence distributions. At the same time, we propose an edge space perception (ESP) module to correct ambiguous segmentation boundaries. Extensive experiments on a clinical IA-DSA and a publicly available LiTS dataset demonstrate that our GCINet outperforms state-of-the-art methods. Additionally, visual analysis and ablation studies are provided to verify the effectiveness of each module in GCINet. © 2024, The Authors. All rights reserved.

关键词： Image segmentation

来源：评论

学校读者我要写书评

暂无评论

Block-Wise Index Modulation and Receiver Design for High-Mobility OTFS Communications

arXiv

引用

arXiv 2023年

作者： Qian, Mi Ji, Fei Ge, Yao Wen, Miaowen Cheng, Xiang Poor, H. Vincent The School of Electronic and Information Engineering South China University of Technology Guangzhou510641 China The Continental-NTU Corporate Lab Nanyang Technological University Singapore The State Key Laboratory of Advanced Optical Communication Systems and Networks Department of Electronics School of Electronics Engineering and Computer Science Peking University Beijing100871 China The Department of Electrical and Computer Engineering Princeton University PrincetonNJ08544 United States

As a promising technique for high-mobility wireless communications, orthogonal time frequency space (OTFS) has been proved to enjoy excellent advantages with respect to traditional orthogonal frequency division multiplexing (OFDM). Although multiple studies have considered index modulation (IM) based OTFS (IM-OTFS) schemes to further improve system performance, a challenging and open problem is the development of effective IM schemes and efficient receivers for practical OTFS systems that must operate in the presence of channel delays and Doppler shifts. In this paper, we propose two novel block-wise IM schemes for OTFS systems, named delay-IM with OTFS (DeIM-OTFS) and Doppler-IM with OTFS (DoIM-OTFS), where a block of delay/Doppler resource bins are activated simultaneously. Based on a maximum likelihood (ML) detector, we analyze upper bounds on the average bit error rates for the proposed DeIM-OTFS and DoIM-OTFS schemes, and verify their performance advantages over the existing IM-OTFS systems. We also develop a multi-layer joint symbol and activation pattern detection (MLJSAPD) algorithm and a customized message passing detection (CMPD) algorithm for our proposed DeIM-OTFS and DoIM-OTFS systems with low complexity. Simulation results demonstrate that our proposed MLJSAPD and CMPD algorithms can achieve desired performance with robustness to the imperfect channel state information (CSI). © 2023, CC BY.

关键词： Message passing

来源：评论

学校读者我要写书评

暂无评论

Safe Reinforcement Learning for Social Motor Coordination in Two Dimensional Space 26

Safe Reinforcement Learning for Social Motor Coordination in...

引用

26th International Conference on Industrial technology, ICIT 2025

作者： Yang, Fan Huang, Yuening Zhai, Chao Zhang, Hehong China University of Geosciences School of Automation Wuhan Campus China Hubei Key Laboratory of Advanced Control and Intelligent Automation for Complex Systems China Engineering Research Center of Intelligent Technology for Geo-Exploration Ministry of Education Wuhan China Rice University George R. Brown School of Engineering and Computing HoustonTX United States Fuzhou University School of Computer and Data Science Fuzhou China

ISBN: (纸本)9798331521950

This paper presents an interactive motion control method based on reinforcement learning, designed to assist children with autism who have social motor impairments through a mirror game intervention. The virtual teacher uses the Deep Deterministic Policy Gradient (DDPG) algorithm to optimize its actions, guiding the participant to follow a Lissajous trajectory. To ensure safety, a motion-correction mechanism was developed, which automatically adjusts actions when the predicted trajectory surpasses predefined safety boundaries. The reward function considers both the distance between the virtual teacher and the target trajectory, as well as the distance between the virtual teacher and the participant, with dynamic adjustments applied by the motion-correction mechanism. Experimental results demonstrate that the virtual teacher effectively guides the participant towards the target trajectory while adhering to safety constraints. © 2025 IEEE.

关键词： Reinforcement learning

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：