检索结果-内蒙古大学图书馆

SSRN 2024年

作者： Fan, Weiwei Gao, Zhenguo Zhang, Jiahui Jiang, Yang College of Computer Science and Technology Huaqiao University Fujian Xiamen China Key Laboratory of Computer Vision Machine Learning of Fujian Province University Fujian Xiamen China

The rapid development of intelligent transportation and the exponential growth of data traffic drive the emerging of more computation-intensive latency-critical tasks in vehicles, bring challenges to the task offloading research in the Internet of Vehicles (IoV), which is for providing vehicles with ultralow latency task processing services via offloading tasks to Edge Servers (ESs) and Cloud Servers (CSs). Focusing on offloading splittable tasks, an end-edge-cloud cooperative splittable task offloading framework is presented for IoV where vehicles with idle resources are regarded as temporary ESs for complementing the computing services of ESs and CSs. Then, we propose a Multi-Agent Deep Deterministic Policy Gradient (MADDPG) algorithm to minimize task completion latency by making comprehensive decisions jointly involving task splition, communication and computation resource allocation. Furthermore, we propose a Group-based Random Updating Strategy (GRUS) for multi-agent deep reinforcement model training to promote training efficiency. To incentivize High-performance Vehicles (HVs) to offer edge computing services via sharing their spare computation resources, we construct a Multi-Leader Multi-Follower Stackelberg (MLMFS) incentive game model where CSs act as leaders and HVs act as followers. We prove the existence of Stackelberg Equilibrium (SE) point, and propose an Optimal Dynamic Response (ODR) algorithm to drive the CSs' resource renting price decisions and the HVs' resource sharing amount decisions to arrive at the SE point via multi-round negotiations. Simulation results demonstrate the superiority of the proposed algorithm over some selected benchmark algorithms. © 2024, The Authors. All rights reserved.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Multi-task Collaborative Network for Image-Text Retrieval 1

引用

30th International Conference on MultiMedia Modeling, MMM 2024

作者： Qin, Xueyang Li, Lishuang Hao, Jing Ge, Meiling Huang, Jiayi Pang, Guangyao School of Computer Science and Technology Dalian University of Technology Dalian116024 China School of Computer Engineering Weifang University Weifang261061 China Guangxi Key Laboratory of Machine Vision and Intelligent Control Wuzhou University Wuzhou543002 China

ISBN: (数字)9783031533112

ISBN: (纸本)9783031533105

Image-text retrieval aims to capture semantic relevance between images and texts. Most existing approaches rely solely on the image-text pairs to learn visual-semantic representation through fine-grained alignments while neglecting the potential beneficial impact of unimodal tasks on cross-modal retrieval. To this end, we present a Multi-Task Collaborative Network (MTCN) that leverages the synergy between multiple tasks to enhance the performance of image-text retrieval. Specifically, we introduce three unimodal tasks, including text-text matching, image multi-label classification, and text multi-label classification, and train together with target task image-text retrieval from the perspective of semantic constraints. Additionally, we employ a modality interaction module for image-text retrieval to discover interrelationships between these two modalities. Subsequently, a cascaded graph convolutional network combined with a multi-layer perceptron is used to infer the correlation scores between images and texts. We conduct comprehensive experiments on two benchmark datasets, Flickr30K and MSCOCO, and the quantitative and qualitative experimental results demonstrate the effectiveness of the proposed method. The source code is available at https://***/FlyCuteBird/MTCN. © 2024, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Defending Poisoning Attacks in Federated learning via Loss Value Normal Distribution 26

Defending Poisoning Attacks in Federated Learning via Loss V...

引用

26th International Conference on computer Supported Cooperative Work in Design, CSCWD 2023

作者： Han, Fei Zhang, Yao Zhao, Meng Tianjin University of Technology Engineering Research Center of Learning-Based Intelligent System Ministry of Education Key Laboratory of Computer Vision and System of Ministry of Education Tianjin300384 China

ISBN: (纸本)9798350331684

As an emerging distributed machine learning paradigm, federated learning (FL) only shares model updates between clients and servers, and training data are secured on each client's device. Due to local data privacy, FL is vulnerable to poisoning attacks, which causes serious degradation in the model performance. In this paper, we analyze the targeted poisoning attacks of FL and reveal that when the data held by each client of FL is independent and identically distributed (iid), the loss of all non-poisoned models on some clean dataset agrees with a normal distribution (ND), while the loss value of the poisoned model deviates from this distribution. Based on this observation, we propose a method named ND-defense to defend FL targeted poisoning attacks. We set a small clean test dataset on the server, compute the loss of each client model on it, detect the abnormal ones with the proposed loss-value-based inspection algorithm, and then only aggregate the benign clients' models to get the global model. We conducted experiments on three benchmark datasets and compared several state-of-the-art defense methods. The results show that our NDdefense is effective in defending against targeted poisoning attacks. © 2023 IEEE.

关键词： Normal distribution

来源：评论

学校读者我要写书评

暂无评论

vision-Language Guidance for LiDAR-based Unsupervised 3D Object Detection

arXiv

引用

arXiv 2024年

作者： Fruhwirth-Reisinger, Christian Lin, Wei Malić, Dušan Bischof, Horst Possegger, Horst Christian Doppler Laboratory for Embedded Machine Learning Austria Institute of Computer Graphics and Vision Graz University of Technology Austria Institute for Machine Learning Johannes Kepler University Linz Austria

Accurate 3D object detection in LiDAR point clouds is crucial for autonomous driving systems. To achieve state-of-the-art performance, the supervised training of detectors requires large amounts of human-annotated data, which is expensive to obtain and restricted to predefined object categories. To mitigate manual labeling efforts, recent unsupervised object detection approaches generate class-agnostic pseudo-labels for moving objects, subsequently serving as supervision signal to bootstrap a detector. Despite promising results, these approaches do not provide class labels or generalize well to static objects. Furthermore, they are mostly restricted to data containing multiple drives from the same scene or images from a precisely calibrated and synchronized camera setup. To overcome these limitations, we propose a vision-language-guided unsupervised 3D detection approach that operates exclusively on LiDAR point clouds. We transfer CLIP knowledge to classify point clusters of static and moving objects, which we discover by exploiting the inherent spatio-temporal information of LiDAR point clouds for clustering, tracking, as well as box and label refinement. Our approach outperforms state-of-the-art unsupervised 3D object detectors on the Waymo Open Dataset (+23 AP3D) and Argoverse 2 (+7.9 AP3D) and provides class labels not solely based on object size assumptions, marking a significant advancement in the field. Code will be available at https://***/chreisinger/ViLGOD. © 2024, CC BY-NC-SA.

关键词： Visual languages

来源：评论

学校读者我要写书评

暂无评论

Missing Customized Distillation Network for Incomplete Multimodal Sentiment Analysis 27th

Missing Customized Distillation Network for Incomplete Multi...

引用

27th International Conference on Pattern Recognition, ICPR 2024

作者： Hu, Zhangfeng Zheng, Wenming Wei, Mengting Shi, Mengxin Zong, Yuan Key Laboratory of Child Development and Learning Science of Ministry of Education Southeast University Nanjing210096 China School of Biological Science and Medical Engineering Southeast University Nanjing210096 China Pazhou Laboratory Guangzhou510320 China Center for Machine Vision and Signal Analysis Oulu University Oulu90570 Finland

ISBN: (纸本)9783031781858

The fusion of multimodal cues, i.e., visual, audio, and language, can provide complementary insights and benefit sentiment analysis. However, not all of them are always available in practical scenarios, posing a challenge for inference with incomplete modality. One idea to address this issue is tailoring distillation algorithms to transfer multimodal knowledge from a full-modality teacher to the incomplete-modality student for missing information compensation. However, existing works utilize fixed and unified knowledge from the pretrained teacher to guide students under different missing states, ignoring their varying capacities. Consequently, the knowledge may be challenging for students with lower capacities to assimilate due to the huge gap. Thus, we propose a missing-customized distillation framework, to adapt the teacher’s knowledge to different missing-state students for better knowledge transfer. Specifically, for the student side, we devise a learnable missing token for each modality to perceive the current missing status. Then for the teacher side, these missing-aware tokens, along with extra trainable adapters, are inserted into it to facilitate knowledge adaptation. With a novel gradient-guided interactive training strategy, our method ensures that the teacher provides student-adaptive knowledge for different students and then the student absorbs valuable knowledge for improved missing information recovery. Extensive experiments on CMU-MOSI and CMU-MOSEI datasets validate the efficiency of our method compared with the state-of-the-arts across various missing rates. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Students

来源：评论

学校读者我要写书评

暂无评论

Discriminative Score Suppression for Weakly Supervised Video Anomaly Detection

Discriminative Score Suppression for Weakly Supervised Video...

引用

2025 IEEE/CVF Winter Conference on Applications of computer vision, WACV 2025

作者： Xu, Chen Li, Chunguo Xing, Hongjie College of Mathematics and Information Science Hebei University Hebei Key Laboratory of Machine Learning and Computational Intelligence Baoding071002 China School of Cyber Security and Computer Hebei University Baoding071000 China

ISBN: (纸本)9798331510831

Weakly supervised video anomaly detection (WSVAD) often relies on Multiple Instance learning (MIL). However, selecting only the most discriminative segments for training limits the model's ability to comprehensively detect anomalous events, particularly hard anomalies. To overcome this limitation, we propose the Discriminative Score Suppression (DSS) module. This module suppresses the discriminative scores of the most prominent anomalies, shifting the model's attention to less obvious but important hard anomalies. This approach guides the model to learn the critical features of hard anomalies, enabling a more comprehensive detection of anomalous events. Additionally, the Anomaly Score Refinement (ASR) module constructs a dissimilarity-based classifier by storing normal patterns as prototypes, and integrates this with a neural network classifier. By combining the anomaly scores from both classifiers, more accurate detection of true hard anomalies is achieved. A score-sensitive inner-bag loss function not only adjusts penalties based on anomaly scores but also ensures that the model avoids erroneous selections. Our method accurately detects various anomalies, including challenging and multi-segment anomalies, while minimizing false positives for normal events. Extensive experiments show that the proposed framework outperforms state-of-the-art methods on the UCF-Crime and XD-Violence datasets. © 2025 IEEE.

关键词： Supervised learning

来源：评论

学校读者我要写书评

暂无评论

Diffusion Posterior Proximal Sampling for Image Restoration 24

Diffusion Posterior Proximal Sampling for Image Restoration

引用

32nd ACM International Conference on Multimedia, MM 2024

作者： Wu, Hongjie He, Linchao Zhang, Mingqin Chen, Dongdong Luo, Kunming Luo, Mengting Zhou, Ji-Zhe Chen, Hu Lv, Jiancheng College of Computer Science Sichuan University Chengdu China National Key Laboratory of Fundamental Science on Synthetic Vision Sichuan University Chengdu China Heriot-Watt University Edinburgh United Kingdom Hong Kong University of Science and Technology Hong Kong Engineering Research Center of Machine Learning and Industry Intelligence Ministry of Education China College of Computer Science Sichuan University China

ISBN: (纸本)9798400706868

Diffusion models have demonstrated remarkable efficacy in generating high-quality samples. Existing diffusion-based image restoration algorithms exploit pre-trained diffusion models to leverage data priors, yet they still preserve elements inherited from the unconditional generation paradigm. These strategies initiate the denoising process with pure white noise and incorporate random noise at each generative step, leading to over-smoothed results. In this paper, we present a refined paradigm for diffusion-based image restoration. Specifically, we opt for a sample consistent with the measurement identity at each generative step, exploiting the sampling selection as an avenue for output stability and enhancement. The number of candidate samples used for selection is adaptively determined based on the signal-to-noise ratio of the timestep. Additionally, we start the restoration process with an initialization combined with the measurement signal, providing supplementary information to better align the generative process. Extensive experimental results and analyses validate that our proposed method significantly enhances image restoration performance while consuming negligible additional computational resources. © 2024 ACM.

关键词： Image reconstruction

来源：评论

学校读者我要写书评

暂无评论

Interactive Deep Clustering via Value Mining 38

Interactive Deep Clustering via Value Mining

引用

38th Conference on Neural Information Processing Systems, NeurIPS 2024

作者： Liu, Honglin Hu, Peng Zhang, Changqing Li, Yunfan Peng, Xi College of Computer Science Sichuan University Chengdu China College of Intelligence and Computing Tianjin University Tianjin China Tianjin Key Lab of Machine Learning Tianjin China State Key Laboratory of Hydraulics and Mountain River Engineering Sichuan University Chengdu China

In the absence of class priors, recent deep clustering methods resort to data augmentation and pseudo-labeling strategies to generate supervision signals. Though achieved remarkable success, existing works struggle to discriminate hard samples at cluster boundaries, mining which is particularly challenging due to their unreliable cluster assignments. To break such a performance bottleneck, we propose incorporating user interaction to facilitate clustering instead of exhaustively mining semantics from the data itself. To be exact, we present Interactive Deep Clustering (IDC), a plug-and-play method designed to boost the performance of pre-trained clustering models with minimal interaction overhead. More specifically, IDC first quantitatively evaluates sample values based on hardness, representativeness, and diversity, where the representativeness avoids selecting outliers and the diversity prevents the selected samples from collapsing into a small number of clusters. IDC then queries the cluster affiliations of high-value samples in a user-friendly manner. Finally, it utilizes the user feedback to finetune the pre-trained clustering model. Extensive experiments demonstrate that IDC could remarkably improve the performance of various pre-trained clustering models, at the expense of low user interaction costs. The code could be accessed at ***. © 2024 Neural information processing systems foundation. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A CNN-LSTM Network for Classification of Attention Deficit Hyperactivity Disorder from EEG Data 41

A CNN-LSTM Network for Classification of Attention Deficit H...

引用

第41届中国控制会议

作者： Yaru Zhang Xiangxin Tan Yue Gu Key Laboratory of Computer Vision and System (Ministry of Education) School of Computer Science and EngineeringTianjin University of Technology Engineering Research Center of Learning-Based Intelligent system Ministry of Education

ISBN: (数字)9789887581536

ISBN: (纸本)9781665482561

Attention deficit hyperactivity disorder(ADHD) is one of the most common neuropsychiatric disorders in children,with core symptoms of inattention,impulsivity,and *** a result,early detection and treatment are *** this point,ADHD can be diagnosed using an electroencephalogram(EEG).This study proposes a model for identifying the EEG of children with *** proposed model is made up of three parts:temporal convolutional blocks,spatial convolutional blocks,and Long Short Term Memory(LSTM),and because EEG contains more temporal information than other data,we build a model that can extract more temporal *** study included 24 subjects,including 12 children with ADHD and12 normal *** experimental results show that our proposed model outperforms Support Vector machine(SVM) and EEGNet,with our model achieving correct classification rates of 92.29%,92.76%,and 90.91% on the three backs,respectively,and 94.25% on the full data,demonstrating the model's feasibility and applicability to the ADHD recognition problem.

关键词： Attention Deficit Hyperactivity Disorder Electroencephalogram Deep learning Classification

来源：评论

学校读者我要写书评

暂无评论

learning to see speckle in the weak laser field through multimode fiber

引用

Optoelectronics Letters 2025年

作者： JI Yunqi SONG Binbin LI Xueqing LI Yonghui The Engineering Research Center of Learning-Based Intelligent System (Ministry of Education)， the Key Laboratory of Computer Vision and Systems (Ministry of Education)， and the School of Computer Science and Engineering， Tianjin University of Technology

Multimode fibers (MMFs) have great potential for endoscopic imaging due to the high number of modes and a small core diameter. Deep learning based on neural networks has received increasing attention in the field of scattering image reconstruction. However， most studies focus on designing complex network architectures to improve reconstruction， but these network models struggle to reconstruct images in a weak laser field. In the paper， a lightweight generative adversarial network model combined with a histogram specification algorithm is designed to reconstruct speckles in the weak laser field through MMF. Experimental results show that the reconstruction results of our algorithm have better metrics. Moreover， the model demonstrates excellent cross-domain generalization ability with regards to the Fashion-MNIST dataset. It is worth mentioning that we found that the speckles after inactivation still retain the ability to be reconstructed， which enhances the robustness of the model

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：