检索结果-内蒙古大学图书馆

SSRN 2024年

作者： Liu, Haixiong Li, Zuoyong Wu, Jiawei Zeng, Kun Hu, Rong Zeng, Wei Fujian Provincial Key Laboratory of Big Data Mining and Applications School of Computer Science and Mathematics Fujian University of Technology Fuzhou350118 China Fujian Provincial Key Laboratory of Information Processing and Intelligent Control College of Computer and Data Science Minjiang University Fuzhou350121 China School of Intelligent Systems Engineering Shenzhen Campus of Sun Yat-sen University Guangdong Shenzhen518107 China The Key Laboratory of Cognitive Computing and Intelligent Information Processing of Fujian Education Institutions Wuyi University Wuyishan354300 China School of Physics and Mechanical and Electrical Engineering Longyan University Longyan364012 China

SSL(Semi-supervised learning) is widely used in machine learning, which leverages labeled and unlabeled data to improve model performance. SSL aims to optimize class mutual information, but noisy pseudo-labels introduce false class information due to the scarcity of labels. Therefore, these algorithms often need significant training time to refine pseudo-labels for performance improvement iteratively. To tackle this challenge, we propose a novel plug-and-play method named ASCL(Accelerating Semi-Supervised Learning via Contrastive Learning). This method combines contrastive learning with uncertainty-based selection for performance improvement and accelerates the convergence of SSL algorithms. Contrastive learning initially emphasizes the mutual information between samples as a means to decrease dependence on pseudo-labels. Subsequently, it gradually turns to maximizing the mutual information between classes, aligning with the objective of semi-supervised learning. Uncertainty-based selection provides a robust mechanism for acquiring pseudo-labels. The combination of the contrastive learning module and the uncertainty-based selection module forms a virtuous cycle to improve the performance of the proposed model. Extensive experiments demonstrate that ASCL outperforms state-of-the-art methods in terms of both convergence efficiency and performance. In the experimental scenario where only one label is assigned per class in the CIFAR-10 dataset, the application of ASCL to Pseudo-label, UDA (Unsupervised Data Augmentation for Consistency Training), and Fixmatch benefits substantial improvements in classification accuracy. Specifically, the results demonstrate notable improvements in respect of 16.32%, 6.9%, and 24.43% when compared to the original outcomes. Moreover, the required training time is reduced by almost 50%. © 2024, The Authors. All rights reserved.

关键词： Image classification

来源：评论

学校读者我要写书评

暂无评论

Attention information Fusion Emotion Analysis Model Based on BiLSTM-BERT

Attention Information Fusion Emotion Analysis Model Based on...

引用

Consumer Electronics and computer Engineering (ICCECE), 2021 IEEE International Conference on

作者： Zhi-Wei Cheng Shun-Xin Li Department of Computer Science and Technology Wuhan University of Science and Technology Wuhan China Hubei Province Key Laboratory of Intelligent Information Processing and Real-time Industrial Wuhan University of Science and Technology Wuhan China

Aiming at the problem that most sentiment analysis methods do not focus on the weight fusion of local context and global context information and the important information in fusion features is not prominent, AIFM-BB (Attention information fusion emotion analysis model based on BiLSTM-BERT) is proposed. The model uses a pre-trained BERT model to process text vectors and a collaborative speech analysis algorithm to process audio vectors, and introduces BiLSTM and Attention mechanisms. The weight of the feature vector is dynamically adjusted by combining the global information and local information of text and audio and the attention information of text and audio modes. The emotion analysis results are obtained through the Softmax layer after the fusion features are self-focused. The experimental results show that the accuracy of the proposed AIFM-BB model on the CMU-MOSI dataset is 85.3%, which is 2.8 percentage points higher than the baseline. In the multi-category emotion classification task, the accuracy of the model is 44.7%, an improvement of 1.1 percentage points compared with baseline. The accuracy is 83.6% on the CMU-MOSEI dataset, an improvement of 1.4 percentage points compared to baseline.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Dynamic Disentangled Fusion Network for RGBT Tracking

arXiv

引用

arXiv 2024年

作者： Li, Chenglong Wang, Tao Ding, Zhaodong Xiao, Yun 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 Anhui Provincial Key Laboratory of Multimodal Cognitive Computation School of Computer Science and Technology Anhui University Hefei230601 China

RGBT tracking usually suffers from various challenging factors of low resolution, similar appearance, extreme illumination, thermal crossover and occlusion, to name a few. Existing works often study complex fusion models to handle challenging scenarios, but can not well adapt to various challenges, which might limit tracking performance. To handle this problem, we propose a novel Dynamic Disentangled Fusion Network called DDFNet, which disentangles the fusion process into several dynamic fusion models via the challenge attributes to adapt to various challenging scenarios, for robust RGBT tracking. In particular, we design six attribute-based fusion models to integrate RGB and thermal features under the six challenging scenarios respectively. Since each fusion model is to deal with the corresponding challenges, such disentangled fusion scheme could increase the fusion capacity without the dependence on large-scale training data. Considering that every challenging scenario also has different levels of difficulty, we propose to optimize the combination of multiple fusion units to form each attribute-based fusion model in a dynamic manner, which could well adapt to the difficulty of the corresponding challenging scenario. To address the issue that which fusion models should be activated in the tracking process, we design an adaptive aggregation fusion module to integrate all features from attribute-based fusion models in an adaptive manner with a three-stage training algorithm. In addition, we design an enhancement fusion module to further strengthen the aggregated feature and modality-specific features. Experimental results on benchmark datasets demonstrate the effectiveness of our DDFNet against other state-of-the-art methods. Copyright © 2024, The Authors. All rights reserved.

关键词： Data fusion

来源：评论

学校读者我要写书评

暂无评论

Two-pupil optical heterodyne scanning holographic system with highpass filtering pupils

Two-pupil optical heterodyne scanning holographic system wit...

引用

Frontiers in Optics, FiO 2022

作者： Yao, Yongwei Zhang, Yaping Poon, Ting-Chung Yunnan Provincial Key Laboratory of Modern Information Optics Kunming University of Science and Technology Yunnan Kunming650500 China Bradley Department of Electrical and Computer Engineering Virginia Tech BlacksburgVA24061 United States

We propose the use of highpass filtering pupils to achieve edge extraction in a two-pupil optical heterodyne scanning holographic system. Preliminary simulation results have shown an effective edge extraction. © ...

ISBN: (纸本)9781557528209

关键词：

来源：评论

学校读者我要写书评

暂无评论

Remote Sensing Images Semantic Segmentation Method Based on Improved Nested UNet

Remote Sensing Images Semantic Segmentation Method Based on ...

引用

2022 International Conference on Geographic information and Remote Sensing technology, GIRST 2022

作者： Li, Zhongyu Liu, Yang Kuang, Yin Wang, Huajun Liu, Cheng College of Geophysics Chengdu University of Technology Chengdu610059 China College of Computer Science Chengdu Normal University Chengdu611130 China Key Laboratory of interior Layout optimization and Security Institutions of Higher Education of Sichuan Province Sichuan Chengdu611130 China Key Laboratory of Pattern Recognition and Intelligent Information Processing of Sichuan Chengdu University Chengdu610106 China Artificial Intelligence Key Laboratory of Sichuan Province Zigong643000 China

ISBN: (纸本)9781510662186

With the development of remote sensing technology, remote sensing images of buildings are of great significance in urban planning, disaster response, and other directions. When we use a neural network containing batch normalization layers for semantic segmentation, the neural network is sensitive to batch size and has low segmentation accuracy for occluded and dense buildings. This paper proposes a method for building segmentation in remote sensing images based on Nested UNet (UNet++) deep neural network. First, the UNet++ network is used to extract features, and the Group Normalization (GN) method is used instead of Batch Normalization (BN) to alleviate the model's sensitivity to batch size. Then the weighted combination of Cross-Entropy Loss (CELoss) and DiceLoss is used as the loss function to improve the feature extraction ability of the neural network for unbalanced buildings. Finally, experiments are carried out on the WHUBuilding dataset. The experimental results show that the improved model (UNet++-GN) improves Mean Intersection over Union (MIoU) and Mean Pixel Accuracy (Macc) by 12.16% and 2.92%, respectively, compared with the original model (UNet++-BN). © 2023 SPIE.

关键词： Feature extraction

来源：评论

学校读者我要写书评

暂无评论

DBSSL: A Scheme to Detect Backdoor Attacks in Self-Supervised Learning Models

引用

IEEE Transactions on Dependable and Secure Computing 2025年

作者： Huang, Yuxian Yang, Geng Yuan, Dong Yu, Shui Nanjing University of Posts and Telecommunication College of Computer Science and Software China Jiangsu Key Laboratory of Big Data Security and Intelligent Processing China University of Sydney School of Electrical and Information Engineering Australia University of Technology Sydney School of Computer Science Australia

Recently, self-supervised learning has garnered significant attention for its ability to extract high-quality features from unlabeled data. However, existing research indicates that backdoor attacks can pose significant threats to self-supervised learning. Additionally, due to the substantial training overhead, traditional backdoor detection methods in supervised learning, such as meta-learning, are not well-suited for self-supervised learning. Current backdoor detection methods for self-supervised learning can only defend against backdoor attacks triggered by patch. To address this challenge, we proposes DBSSL, a scheme that can efficiently detect backdoor attacks in self-supervised learning models. In DBSSL, we connect backdoor attacks with adversarial attacks and use adversarial perturbations for detection. Specifically, we first conduct targeted adversarial attacks on the samples, classifying them into different classes. Then, we employ the Z-Score method to analyze these adversarial perturbations. If outliers are present, we can infer that the self-supervised learning model has been backdoored. Unlike previous works, our scheme is better suited for downstream users with constrained computation resources and exhibits excellent detection capabilities for backdoor attacks caused by patch -type or global triggers. Abundant theoretical analysis has demonstrated the feasibility of our scheme. Moreover, extensive experiments show that our method performs well in detecting prevalent backdoor attacks in self-supervised learning, achieving detection accuracy exceeding 95%. © 2004-2012 IEEE.

关键词： Self-supervised learning

来源：评论

学校读者我要写书评

暂无评论

TRAIL: Trust-Aware Client Scheduling for Semi-Decentralized Federated Learning 39

TRAIL: Trust-Aware Client Scheduling for Semi-Decentralized ...

引用

39th Annual AAAI Conference on Artificial Intelligence, AAAI 2025

作者： Hu, Gangqiang Lu, Jianfeng Han, Jianmin Cao, Shuqin Liu, Jing Fu, Hao School of Computer Science and Technology Zhejiang Normal University China School of Computer Science and Technology Wuhan University of Science and Technology China Key Laboratory of Social Computing and Cognitive Intelligence Dalian University of Technology Ministry of Education China Hubei Province Key Laboratory of Intelligent Information Processing and Real-time Industrial System Wuhan University of Science and Technology China

ISBN: (纸本)157735897X

Due to the sensitivity of data, Federated Learning (FL) is employed to enable distributed machine learning while safeguarding data privacy and accommodating the requirements of various devices. However, in the context of semi-decentralized FL, clients’ communication and training states are dynamic. This variability arises from local training fluctuations, heterogeneous data distributions, and intermittent client participation. Most existing studies primarily focus on stable client states, neglecting the dynamic challenges inherent in real-world scenarios. To tackle this issue, we propose a TRust-Aware clIent scheduLing mechanism called TRAIL, which assesses client states and contributions, enhancing model training efficiency through selective client participation. We focus on a semi-decentralized FL framework where edge servers and clients train a shared global model using unreliable intra-cluster model aggregation and inter-cluster model consensus. First, we propose an adaptive hidden semi-Markov model to estimate clients’ communication states and contributions. Next, we address a client-server association optimization problem to minimize global training loss. Using convergence analysis, we propose a greedy client scheduling algorithm. Finally, our experiments conducted on real-world datasets demonstrate that TRAIL outperforms state-of-the-art baselines, achieving an improvement of 8.7% in test accuracy and a reduction of 15.3% in training loss. Copyright © 2025, Association for the Advancement of Artificial Intelligence (***). All rights reserved.

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

CBAT-ASG: Adversarial Sample Generation Method Based on CBA-Transformer

CBAT-ASG: Adversarial Sample Generation Method Based on CBA-...

引用

International Conference on computer Supported Cooperative Work in Design

作者： Lijuan Xu Zhiang Yao Haoran Li Chengcai Diao Guangrun Zhou Dawei Zhao Hua Ding Key Laboratory of Computing Power Network and Information Security Ministry of Education Shandong Computer Science Center (National Supercomputer Center in Jinan) Qilu University of Technology (Shandong Academy of Sciences) Shandong Provincial Key Laboratory of Industrial Network and Information System Security Shandong Fundamental Research Center for Computer Science Jinan China

ISBN: (数字)9798331513054

ISBN: (纸本)9798331513061

In recent years, machine learning models have become prevalent for anomaly detection in industrial control systems (ICS). However, their vulnerability to adversarial samples poses a significant security threat. Current methods for adversarial sample attacks in ICS are inadequate, requiring urgent research. Present adversarial samples mainly target machine learning-based anomaly detection models, overlooking invariant rule detectors in ICS, which reduces attack success rates. This paper introduces CBAT-ASG, a novel adversarial sample generation method based on CBA-Transformer. We enhance the Transformer with channel and spatial attention modules, creating the CBA-Transformer generative model. This model improves performance and generates initial adversarial samples that better match industrial control data. To avoid detection by invariant rule detectors, we use an invariant rule checker to refine adversarial samples, increasing their resistance to detection. Experiments on public datasets show CBAT-ASG significantly reduces the detection capabilities of the advanced anomaly detection model GDN, with Precision decreasing by 0.94, and Recall and F1-Score dropping by over 0.4. Comparisons with three state-of-the-art adversarial sample generation methods across four anomaly detection models show CBAT-ASG's attack efficacy is approximately 0.7 higher in the best-case scenario.

关键词： Resistance Federated learning Industrial control Detectors Predictive models Transformers Data models Security Integrated circuit modeling Anomaly detection

来源：评论

学校读者我要写书评

暂无评论

Simplifying Control Mechanism in Text-to-Image Diffusion Models 39

Simplifying Control Mechanism in Text-to-Image Diffusion Mod...

引用

39th Annual AAAI Conference on Artificial Intelligence, AAAI 2025

作者： Feng, Zhida Chen, Li Sun, Yuenan Liu, Jiaxiang Feng, Shikun School of Computer Science and Technology Wuhan University of Science and Technology China Hubei Province Key Laboratory of Intelligent Information Processing and Real-time Industrial System Wuhan University of Science and Technology China Baidu Inc China

ISBN: (纸本)157735897X

ControlNet has significantly advanced controllable image generation by integrating dense conditions (such as depth and canny edges) with text-to-image diffusion models. However, ControlNet’s integration requires an additional amount nearly equal to half of the base diffusion model’s parameters, making it inefficient. To address this, we introduce Simple-ControlNet, an efficient and streamlined network for controllable text-to-image generation. It employs a single-scale projection layer to incorporate condition information into the denoising U-Net. It is supplemented by Low-Rank Adapter (LoRA) parameters to facilitate condition learning. Impressively, Simple-ControlNet requires fewer than 3 million parameters for the control mechanism, substantially less than the 300 million needed by ControlNet. Our extensive experiments confirm that Simple-ControlNet matches and surpasses ControlNet’s performance across a broad range of tasks and base diffusion models, showcasing its utility and efficiency. © 2025, Association for the Advancement of Artificial Intelligence (***). All rights reserved.

关键词： Controllability

来源：评论

学校读者我要写书评

暂无评论

Few-Shot Class-Incremental Semantic Segmentation via Pseudo-Labeling and Knowledge Distillation

Few-Shot Class-Incremental Semantic Segmentation via Pseudo-...

引用

information Science, Parallel and Distributed Systems (ISPDS), International Conference on

作者： Chengjia Jiang Tao Wang Sien Li Jinyang Wang Shirui Wang Antonios Antoniou Fujian Provincial Key Laboratory of Information Processing and Intelligent Control Minjiang University Fuzhou China The Key Laboratory of Cognitive Computing and Intelligent Information Processing Fujian Education Institutions Wuyi University Wuyishan China College of Computer and Data Science Fuzhou University Fuzhou China Department of Computer Science and Engineering European University Cyprus Nicosia Cyprus

We address the problem of learning new classes for semantic segmentation models from few examples, which is challenging because of the following two reasons. Firstly, it is difficult to learn from limited novel data to capture the underlying class distribution. Secondly, it is challenging to retain knowledge for existing classes and to avoid catastrophic forgetting. For learning from limited data, we propose a pseudo-labeling strategy to augment the few-shot training annotations in order to learn novel classes more effectively. Given only one or a few images labeled with the novel classes and a much larger set of unlabeled images, we transfer the knowledge from labeled images to unlabeled images with a coarse-to-fine pseudo-labeling approach in two steps. Specifically, we first match each labeled image to its nearest neighbors in the unlabeled image set at the scene level, in order to obtain images with a similar scene layout. This is followed by obtaining pseudo-labels within this neighborhood by applying classifiers learned on the few-shot annotations. In addition, we use knowledge distillation on both labeled and unlabeled data to retain knowledge on existing classes. We integrate the above steps into a single convolutional neural network with a unified learning objective. Extensive experiments on the Cityscapes and KITTI datasets validate the efficacy of the proposed approach in the self-driving domain. Code is available from https://***/ChasonJiang/FSCILSS.

关键词：

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：