检索结果-内蒙古大学图书馆

International Conference on Acoustics, Speech, and Signal Processing (ICASSP)

作者： Yingjie Ma Zitong Yu Xun Lin Weicheng Xie Linlin Shen College of Computer Science and Software Engineering Shenzhen University Great Bay University National Engineering Laboratory for Big Data System Computing Technology Shenzhen University Guangdong Provincial Key Laboratory of Intelligent Information Processing

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

In the domain of facial recognition security, multimodal Face Anti-Spoofing (FAS) is essential for countering presentation attacks. However, existing technologies encounter challenges due to modality biases and imbalances, as well as domain shifts. Our research introduces a Mixture of Experts (MoE) model to address these issues effectively. We identified three limitations in traditional MoE approaches to multimodal FAS: (1) Coarse-grained experts’ inability to capture nuanced spoofing indicators; (2) Gated networks’ susceptibility to input noise affecting decision-making; (3) MoE’s sensitivity to prompt tokens leading to overfitting with conventional learning methods. To mitigate these, we propose the Bypass Isolated Gating MoE (BIG-MoE) framework, featuring: (1) Fine-grained experts for enhanced detection of subtle spoofing cues; (2) An isolation gating mechanism to counteract input noise; (3) A novel differential convolutional prompt bypass enriching the gating network with critical local features, thereby improving perceptual capabilities. Extensive experiments on four benchmark datasets demonstrate significant generalization performance improvement in multimodal FAS task. The code is released at https://***/murInJ/BIG-MoE.

关键词： Convolutional codes Sensitivity Convolution Face recognition Noise Logic gates Feature extraction Security Speech processing Overfitting

来源：评论

学校读者我要写书评

暂无评论

Learning with Open-world Noisy Data via Class-independent Margin in Dual Representation Space

arXiv

引用

arXiv 2025年

作者： Pan, Linchao Gao, Can Zhou, Jie Wang, Jinbao College of Computer Science and Software Engineering Shenzhen University China Guangdong Provincial Key Laboratory of Intelligent Information Processing China National Engineering Laboratory for Big Data System Computing Technology Shenzhen University China

Learning with Noisy Labels (LNL) aims to improve the model generalization when facing data with noisy labels, and existing methods generally assume that noisy labels come from known classes, called closed-set noise. However, in real-world scenarios, noisy labels from similar unknown classes, i.e., open-set noise, may occur during the training and inference stage. Such open-world noisy labels may significantly impact the performance of LNL methods. In this study, we propose a novel dual-space joint learning method to robustly handle the open-world noise. To mitigate model overfitting on closed-set and open-set noises, a dual representation space is constructed by two networks. One is a projection network that learns shared representations in the prototype space, while the other is a One-Vs-All (OVA) network that makes predictions using unique semantic representations in the class-independent space. Then, bi-level contrastive learning and consistency regularization are introduced in two spaces to enhance the detection capability for data with unknown classes. To benefit from the memorization effects across different types of samples, class-independent margin criteria are designed for sample identification, which selects clean samples, weights closed-set noise, and filters open-set noise effectively. Extensive experiments demonstrate that our method outperforms the state-of-the-art methods and achieves an average accuracy improvement of 4.55% and an AUROC improvement of 6.17% on CIFAR80N. Copyright © 2025, The Authors. All rights reserved.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

Multi-View Representation Learning for Multi-Instance Learning with Applications to Medical Image Classification

Multi-View Representation Learning for Multi-Instance Learni...

引用

2022 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2022

作者： Zhao, Lu Yuan, Liming Li, Zhenliang Wen, Xianbin School of Computer Science and Engineering Tianjin University of Technology Tianjin300384 China School of Computer and Information Engineering Tianjin Chengjian University Tianjin300384 China Key Laboratory of Computer Vision and System Ministry of Education Tianjin300384 China Tianjin Key Laboratory of Intelligence Computing and Novel Software Technology Tianjin300384 China

ISBN: (纸本)9781665468190

Multi-Instance Learning (MIL) is a weakly supervised learning paradigm, in which every training example is a labeled bag of unlabeled instances. In typical MIL applications, instances are often used for describing the features of regions/parts in a whole object, e.g., regional patches/lesions in an eye-fundus image. However, for a (semantically) complex part the standard MIL formulation puts a heavy burden on the representation ability of the corresponding instance. To alleviate this pressure, we still adopt a bag-of-instances as an example in this paper, but extract from each instance a set of representations using 1 times1 convolutions. The advantages of this tactic are two-fold: i) This set of representations can be regarded as multi-view representations for an instance;ii) Compared to building multi-view representations directly from scratch, extracting them automatically using 1 times1 convolutions is more economical, and may be more effective since 1 times1 convolutions can be embedded into the whole network. Furthermore, we apply two consecutive multi-instance pooling operations on the reconstituted bag that has actually become a bag of sets of multi-view representations. We have conducted extensive experiments on several canonical MIL data sets from different application domains. The experimental results show that the proposed framework outperforms the standard MIL formulation in terms of classification performance and has good interpretability. © 2022 IEEE.

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

Deep Multi-Instance Learning with Adaptive Recurrent Pooling for Medical Image Classification

Deep Multi-Instance Learning with Adaptive Recurrent Pooling...

引用

2022 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2022

作者： Ding, Yi Zhao, Lu Yuan, Liming Wen, Xianbin School of Computer Science and Engineering Tianjin University of Technology Tianjin300384 China School of Computer and Information Engineering Tianjin Chengjian University Tianjin300384 China Key Laboratory of Computer Vision and System Ministry of Education Tianjin300384 China Tianjin Key Laboratory of Intelligence Computing and Novel Software Technology Tianjin300384 China

ISBN: (纸本)9781665468190

Recently, deep multi-instance neural networks have been successfully applied for medical image classification, where only image-level labels rather than fine-grained patch-level labels are available for use. One key issue for these multi-instance neural networks is how to aggregate all patch (instance) features into an entire image (bag) representation, referred to as multi-instance pooling, e.g., max, mean, and attention based pooling. Nevertheless, these multi-instance pooling operations do not take the structural information within an image into account. This is obviously inappropriate for medical image classification since there often exist certain dependencies among regional patches/lesions. We propose an adaptive recurrent pooling based deep multi-instance neural network in this paper. In this network, we first extract multi-view global structural features from every bag using the self-attention mechanism, and then aggregate these multi-view features into a whole bag representation based on the adaptive recurrent pooling operation in order to further capture the contextual information within the bag. Moreover, we introduce the cross-normalization operation used in the Unit Force Operated Vision Transformer into the self-attention module to reduce its computational complexity. We have experimentally evaluated the performance of the proposed network on three medical image datasets, namely UCSB breast, Messidor, and Colon cancer. The results demonstrate the advantage of our network over current state-of-the-art deep multi-instance networks in terms of classification accuracy and interpretability. © 2022 IEEE.

关键词： Aggregates

来源：评论

学校读者我要写书评

暂无评论

Object Segmentation-Assisted Inter Prediction for Versatile Video Coding

arXiv

引用

arXiv 2024年

作者： Li, Zhuoyuan Yuan, Zikun Li, Li Liu, Dong Tang, Xiaohu Wu, Feng CAS Key Laboratory of Technology in Geo-Spatial Information Processing and Application System University of Science and Technology of China Hefei230027 China Information Security and National Computing Grid Laboratory Southwest Jiaotong University Chengdu610031 China

In modern video coding standards, block-based inter prediction is widely adopted, which brings high compression efficiency. However, in natural videos, there are usually multiple moving objects of arbitrary shapes, resulting in complex motion fields that are difficult to represent compactly. This problem has been tackled by more flexible block partitioning methods in the Versatile Video Coding (VVC) standard, but the more flexible partitions require more overhead bits to signal and still cannot be made arbitrarily shaped. To address this limitation, we propose an object segmentation-assisted inter prediction method (SAIP), where objects in the reference frames are segmented by some advanced technologies. With a proper indication, the object segmentation mask is translated from the reference frame to the current frame as the arbitrary-shaped partition of different regions without any extra signal. Using the segmentation mask, motion compensation is separately performed for different regions, achieving higher prediction accuracy. The segmentation mask is further used to code the motion vectors of different regions more efficiently. Moreover, the segmentation mask is considered in the joint rate-distortion optimization for motion estimation and partition estimation to derive the motion vector of different regions and partition more accurately. The proposed method is implemented into the VVC reference software, VTM version 12.0. Experimental results show that the proposed method achieves up to 1.98%, 1.14%, 0.79%, and on average 0.82%, 0.49%, 0.37% BD-rate reduction for common test sequences, under the Low-delay P, Low-delay B, and Random Access configurations, respectively. Copyright © 2024, The Authors. All rights reserved.

关键词： Video signal processing

来源：评论

学校读者我要写书评

暂无评论

Service Migration in Mec: An Approach Based on Deep Reinforcement Learning and Fuzzy Logic

SSRN

引用

SSRN 2023年

作者： Zhang, Xinyang Bu, Chao Wang, Jinsong Key Laboratory of Computer Vision System of Ministry of Education School of Computer Science and Engineering Tianjin University of Technology China Tianjin Key Laboratory of Intelligence Computing and Novel Software Technology Tianjin University of Technology Tianjin300384 China

As a new computing paradigm, Mobile Edge computing (MEC) sinks resources to the network edge to support real-time re-sponses of services. Facing the demand for migrating services caused by the frequent movement of the mobile device, it is a great challenge to reduce the operation costs of migrating services with user requirements satisfied, especially for the continu-ous optimization of services deployed in hot spot areas. In order to address the above challenge, we propose the mechanism of dynamically migrating and optimally deploying services, which optimizes the latency and energy consumption of the service mi-gration. Firstly, we introduce Markov Decision Process (MDP) to model changes of deployment locations of the single-user ser-vice, and devise the approach to determine whether to migrate a service at the current network status based on the dueling Deep Q-Network (DQN). Secondly, we propose the service pre-migration decision approach to determine where to migrate a ser-vice by combining the Long Short-Term Memory (LSTM) network and the attention mechanism, so as to determine the future moving area of the user and perform the migration decision in advance with the impact of migration service on service quality considered. Finally, we devise the distance-weighted matching algorithm based on the fuzzy logic to further optimize the selec-tion of the most appropriate services to migrate in hotspot areas and the corresponding service migration regions, thus, the load pressure of the edge computing node caused by the imbalanced deployment density of service among multiple regions. Simula-tion results show that the proposed mechanism has significant improvements in overall operating costs compared with the cur-rent state of the art. © 2023, The Authors. All rights reserved.

关键词： Fuzzy logic

来源：评论

学校读者我要写书评

暂无评论

Learning Topic Emotion and Logical Semantic for Video Paragraph Captioning

SSRN

引用

SSRN 2024年

作者： Li, Qinyu Wang, Hanli Yi, Xiaokai Department of Computer Science & Technology Tongji University Shanghai201804 China Key Laboratory of Embedded System & Service Computing Ministry of Education Tongji University Shanghai200092 China

Video paragraph captioning aims to generate multiple descriptive sentences for videos, which strive to replicate human writing in accuracy, logicality, and richness. However, current research focuses on the accuracy and temporal order of events, ignoring emotion and other critical logical relations embedded in human language, such as causal and adversative relations. The ignorance impairs the reasonable transition across generated event descriptions and restricts the vividness of expression, resulting in a gap from the standard of human language. To resolve the problem, a framework that integrates logic and emotion representation learning is proposed to narrow the gap. Concretely, a large-scale inter-event relation corpus is constructed based on the EMVPC dataset. This corpus is named EMVPC-EvtRel (standing for "EMVPC-Event Relations") and contains six widely-used logical relations in human writing, 127 explicit inter-sentence connectives, and over 20,000 pairs of event segments with newly annotated logical relations. A logical semantic representation learning method is developed for recognizing the dependencies between visual events, thereby enhancing the characteristics of video contents and boosting the logicality of generated paragraphs. Moreover, a fine-grained emotion recognition module is designed to uncover emotion features embedded in videos. Finally, experimental results on the EMVPC dataset demonstrate the superiority of the proposed method compared to existing state-of-the-art approaches. © 2024, The Authors. All rights reserved.

关键词： Emotion Recognition

来源：评论

学校读者我要写书评

暂无评论

Generalization-Enhanced Code Vulnerability Detection via Multi-Task Instruction Fine-Tuning

arXiv

引用

arXiv 2024年

作者： Du, Xiaohu Wen, Ming Zhu, Jiahao Xie, Zifan Ji, Bin Liu, Huijun Shi, Xuanhua Jin, Hai School of Cyber Science and Engineering Huazhong University of Science and Technology China School of Computer Science and Technology Huazhong University of Science and Technology China College of Computer National University of Defense Technology China National Engineering Research Center for Big Data Technology and System Services Computing Technology and System Lab HUST Wuhan430074 China Hubei Engineering Research Center on Big Data Security Hubei Key Laboratory of Distributed System Security HUST Wuhan430074 China JinYinHu Laboratory Wuhan430077 China Cluster and Grid Computing Lab HUST Wuhan430074 China

Code Pre-trained Models (CodePTMs) based vulnerability detection have achieved promising results over recent years. However, these models struggle to generalize as they typically learn superficial mapping from source code to labels instead of understanding the root causes of code vulnerabilities, resulting in poor performance in real-world scenarios beyond the training instances. To tackle this challenge, we introduce VulLLM, a novel framework that integrates multi-task learning with Large Language Models (LLMs) to effectively mine deep-seated vulnerability features. Specifically, we construct two auxiliary tasks beyond the vulnerability detection task. First, we utilize the vulnerability patches to construct a vulnerability localization task. Second, based on the vulnerability features extracted from patches, we leverage GPT-4 to construct a vulnerability interpretation task. VulLLM innovatively augments vulnerability classification by leveraging generative LLMs to understand complex vulnerability patterns, thus compelling the model to capture the root causes of vulnerabilities rather than overfitting to spurious features of a single task. The experiments conducted on six large datasets demonstrate that VulLLM surpasses seven state-of-the-art models in terms of effectiveness, generalization, and robustness. © 2024, CC BY.

关键词： Large datasets

来源：评论

学校读者我要写书评

暂无评论

A Topic-Aware Graph-Based Neural Network for User Interest Summarization and Item Recommendation in Social Media 28th

A Topic-Aware Graph-Based Neural Network for User Interest ...

引用

28th International Conference on Database systems for Advanced Applications, DASFAA 2023

作者： Chen, Junyang Fan, Ge Gong, Zhiguo Li, Xueliang Leung, Victor C. M. Wang, Mengzhu Yang, Ming College of Computer Science and Software Engineering Shenzhen University Shenzhen China Shenzhen China Tencent Inc. Shenzhen China State Key Laboratory of Internet of Things for Smart City Department of Computer Information Science University of Macau China National Engineering Laboratory for Big Data System Computing Technology Shenzhen University Shenzhen China

ISBN: (纸本)9783031306716

User-generated content is daily produced in social media, as such user interest summarization is critical to distill salient information from massive information. While the interested messages (e.g., tags or posts) from a single user are usually sparse becoming a bottleneck for existing methods, we propose a topic-aware graph-based neural interest summarization method (UGraphNet), enhancing user semantic mining by unearthing potential user relations and jointly learning the latent topic representations of posts that facilitates user interest learning. Experiments on two datasets collected from well-known social media platforms demonstrate the superior performance of our model in the tasks of user interest summarization and item recommendation. Further discussions also show that exploiting the latent topic representations and user relations are conductive to the user automatic language understanding. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Graphic methods

来源：评论

学校读者我要写书评

暂无评论

Generative artificial intelligence and its applications in materials science:Current situation and future perspectives

引用

Journal of Materiomics 2023年第4期9卷 798-816页

作者： Yue Liu Zhengwei Yang Zhenyao Yu Zitu Liu Dahui Liu Hailong Lin Mingqing Li Shuchang Ma Maxim Avdeev Siqi Shi School of Computer Engineering and Science Shanghai UniversityShanghai200444China State Key Laboratory of Advanced Special Steel School of Materials Science and EngineeringShanghai UniversityShanghai200444China Materials Genome Institute Shanghai UniversityShanghai200444China Shanghai Engineering Research Center of Intelligent Computing System Shanghai200444China Australian Nuclear Science and Technology Organisation Sydney2232Australia School of Chemistry The University of SydneySydney2006Australia

Generative Artificial Intelligence(GAI)is attracting the increasing attention of materials community for its excellent capability of generating required *** the introduction of Prompt paradigm and reinforcement learning from human feedback(RLHF),GAI shifts from the task-specific to general pattern gradually,enabling to tackle multiple complicated tasks involved in resolving the structure-activity ***,we review the development status of GAI comprehensively and analyze pros and cons of various generative models in the view of *** applications of task-specific generative models involving materials inverse design and data augmentation are also *** ChatGPT as an example,we explore the potential applications of general GAI in generating multiple materials content,solving differential equation as well as querying materials ***,we summarize six challenges encountered for the use of GAI in materials science and provide the corresponding *** work paves the way for providing effective and explainable materials data generation and analysis approaches to accelerate the materials research and development.

关键词： Machine learning Artificial intelligence Generative artificial intelligence Materials science Novel materials discovery Deep 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：