检索结果-内蒙古大学图书馆

Visual Prompt Flexible-Modal Face Anti-Spoofing

IEEE Transactions on Dependable and Secure computing 2025年第3期22卷 2597-2606页

作者： Yu, Zitong Cai, Rizhao Cui, Yawen Liu, Ajian Chen, Changsheng Great Bay University School of Computing and Information Technology Dongguan523000 China Nanyang Technological University ROSE Lab School of EEE 639798 Singapore Hong Kong Polytechnic University Kowloon Hong Kong Chinese Academy of Sciences University of Chinese Academy of Sciences National Laboratory of Pattern Recognition Institute of Automation Beijing100190 China Shenzhen University Guangdong Key Laboratory of Intelligent Information Processing Shenzhen Key Laboratory of Media Security College of Electronics and Information Engineering Shenzhen518060 China

Recently, vision transformer based multimodal learning methods have been proposed to improve the robustness of face anti-spoofing (FAS) systems. However, multimodal face data collected from the real world is often imperfect due to missing modalities from various imaging sensors. Recently, flexible-modal FAS (Yu et al. 2023) has attracted more attention, which aims to develop a unified multimodal FAS model using complete multimodal face data but is insensitive to test-time missing modalities. In this paper, we tackle one main challenge in flexible-modal FAS, i.e., when missing modality occurs either during training or testing in real-world situations. Inspired by the recent success of the prompt learning in language models, we propose Visual Prompt flexible-modal FAS (VP-FAS), which learns the modal-relevant prompts to adapt the frozen pre-trained foundation model to downstream flexible-modal FAS task. Specifically, both vanilla visual prompts and residual contextual prompts are plugged into multimodal transformers to handle general missing-modality cases, while only requiring less than 4% learnable parameters compared to training the entire model. Furthermore, missing-modality regularization is proposed to force models to learn consistent multimodal feature embeddings when missing partial modalities. Extensive experiments conducted on two multimodal FAS benchmark datasets demonstrate the effectiveness of our VP-FAS framework that improves the performance under various missing-modality cases while alleviating the requirement of heavy model re-training. © 2004-2012 IEEE.

关键词： Alignment

来源：评论

学校读者我要写书评

暂无评论

A Flexible Knowledge Graph Error Detection Framework Combined with Semantic Information 12th

A Flexible Knowledge Graph Error Detection Framework Combine...

引用

12th CCF Conference on BigData, BigData 2024

作者： Zhao, Yangwu Liu, Yang Ao, Xiang He, Qing Henan Institute of Advanced Technology Zhengzhou University Zhengzhou China Beijing China Key Lab of Intelligent Information Processing Institute of Computing Technology CAS Beijing China

ISBN: (纸本)9789819610235

Knowledge graphs (KGs) are extensively utilized in numerous applications, including question-answering systems and recommender systems. However, knowledge graphs are often constructed through web crawling or crowdsourcing, leading to errors in the data. The task of knowledge graph error detection aims to identify inaccurate triplets in KGs and has received substantial attention in recent years. However, the majority of current error detection methods overlook the semantic information of the triplets, which can be vital for accurate error detection. In this paper, we introduce a Flexible Knowledge Graph Error Detection Framework that integrates Semantic Information (FKED), which combines both structural and semantic information to detect errors within the knowledge graph. FKED first extracts the structural information of KGs using a graph embedding model. Next, FKED employs a pre-trained language model (PLM) to extract semantic information from the triplets. Then the structural and semantic information are combined to detect errors within the knowledge graph. FKED can be flexibly added to other structure-based error detection models, enhancing their capabilities in downstream tasks of knowledge graphs. We assess FKED using two benchmark datasets: FB15k-237 and WN18RR. Experimental results indicate that our method is both superior and effective, substantially improving the performance of the base models. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Knowledge graph

来源：评论

学校读者我要写书评

暂无评论

Object-to-Manipulation Graph for Affordance Navigation

引用

CAAI Artificial Intelligence Research 2024年第1期3卷 178-186页

作者： Xinhang Song Bohan Wang Liye Dong Gongwei Chen Xinyun Hu Shuqiang Jiang Key Lab of Intelligent Information Processing of Chinese Academy of Sciences(CAS) Institute of Computing TechnologyCASBeijing 100190China University of Chinese Academy of Sciences Beijing 100049China

Object navigation,whose goal is to let the agent to reach some places(or objects),has been a popular topic in embodied Artificial Intelligence(AI)***,in our real-world applications,it is more practical to find the targets with particular goals,raising the new requirements of finding the places to achieve the particular *** this paper,we define a new task of affordance navigation,whose goal is to find possible places to accomplish the required functions,achieving some particular *** first introduce a new dataset for affordance navigation,collected by the proposed affordance *** order to avoid the high cost of labor,the groundtruth of each episode which is annotated with the interaction data provided by the AI2-THOR *** addition,we also propose an affordance navigation framework,where an Object-to-Manipulation Graph(OMG)is constructed and optimized to emphasize the corresponding nodes(including object nodes and manipulation nodes).Finally,a navigation policy is implemented(trained by reinforcement learning)to guide the navigation to the target *** results on AI2-THOR simulator illustrate the effectiveness of the proposed approach,which achieves significant gains of 14.0%and 11.7%(on success rate and Success weighted by Path Length(SPL),respectively)over the baseline model.

关键词： navigation affordance manipulation graph neural network

来源：评论

学校读者我要写书评

暂无评论

Small Scale Data-Free Knowledge Distillation

Small Scale Data-Free Knowledge Distillation

引用

Conference on Computer Vision and Pattern Recognition (CVPR)

作者： He Liu Yikai Wang Huaping Liu Fuchun Sun Anbang Yao China Telecom Cloud Technology Co. Ltd. Department of Computer Science and Technology BNRist Center State Key Lab on Intelligent Technology and Systems Tsinghua University Intel Labs China

ISBN: (数字)9798350353006

ISBN: (纸本)9798350353013

Data-free knowledge distillation is able to utilize the knowledge learned by a large teacher network to augment the training of a smaller student network without accessing the original training data, avoiding privacy, security, and proprietary risks in real applications. In this line of research, existing methods typically follow an inversion-and-distillation paradigm in which a generative adversarial network on-the-fly trained with the guidance of the pre-trained teacher network is used to synthesize a large-scale sample set for knowledge distillation. In this paper, we reexam-ine this common data-free knowledge distillation paradigm, showing that there is considerable room to improve the overall training efficiency through a lens of “small-scale inverted data for knowledge distillation”. In light of three empirical observations indicating the importance of how to balance class distributions in terms of synthetic sample di-versity and difficulty during both data inversion and distillation processes, we propose Small Scale Data-free Knowledge Distillation (SSD-KD). Informulation, SSD-KD introduces a modulating function to balance synthetic samples and a priority sampling function to select proper samples, facilitated by a dynamic replay buffer and a reinforcement learning strategy. As a result, SSD-KD can perform dis-tillation training conditioned on an extremely small scale of synthetic samples (e.g., 10x less than the original training data scale), making the overall training efficiency one or two orders of magnitude faster than many mainstream methods while retaining superior or competitive model performance, as demonstrated on popular image classification and semantic segmentation benchmarks. The code is available at https://***/OSVAI/SSD-KD.

关键词： Training Knowledge engineering Semantic segmentation Training data Reinforcement learning Benchmark testing Pattern recognition

来源：评论

学校读者我要写书评

暂无评论

New Offloading Method of computing Task Based on Gray Wolf Hunting Optimization Mechanism for the IOV

引用

IEEE Transactions on Network and Service Management 2025年

作者： Zhang, Jie Zhang, De-Gan Qiao, Meng Hong-Lin, E. Zhang, Ting Zhang, Ping University of Macau Key Lab of Internet of Things for Smart City Faculty of Science and Technology 999078 China Tianjin University of Technology Tianjin Key Lab of Intelligent Computing and Novel Software Technology Tianjin300384 China Tianjin University of Sport School of Sports Economics and Management Tianjin301617 China

Task offloading, as an effective solution, provides low latency and sufficient computing resources for mobile users in the network. However, how to reasonably offload to reduce system overhead is a challenging issue today. This article takes user terminals, edge servers, and idle vehicles with resources as the network structure, and is inspired by the highly social nature of the gray wolf pack. It proposes a new offloading method of edge computing task based on hunting optimizing mechanism of gray wolf for the Internet of Vehicle (IOV). Firstly, an adaptive weight factor is proposed to balance the weight ratio of delay and energy consumption in the system cost under the constraints of delay and energy consumption. With delay and computing resources of vehicles and servers as constraints, a multi constraint minimization system cost problem is proposed. Secondly, the hunting process of the gray Wolf optimization algorithm is used to find the optimal solution of the unloading scheme, The Levy flight strategy was added to enhance the global search ability of the algorithm, and a dynamic weight strategy was introduced to improve the convergence performance of the algorithm. Finally, the improved gray Wolf optimization algorithm was used to solve the optimal unloading plan and minimum *** simulation results show that compared with traditional gray Wolf optimization algorithm offloading schemes, the proposed scheme in this paper requires lower system costs. © 2004-2012 IEEE.

关键词： Mobile edge computing

来源：评论

学校读者我要写书评

暂无评论

Adversarial Example Generation Method Based on Probability Histogram Equalization

Adversarial Example Generation Method Based on Probability H...

引用

第42届中国控制会议

作者： Youqing Fang Jingwen Jia Yuhai Yang Wan-Li Lyu Key Lab of Intelligent Computing and Signal Processing of Ministry of Education School of Computer Science and TechnologyAnhui University

CNNs(Convolutional Neural Networks) have a good performance on most classification tasks,but they are vulnerable when meeting adversarial *** and design of highly aggressive adversarial examples can help enhance the security and robustness of *** transferability of adversarial examples is still low in black-box ***,an adversarial example method based on probability histogram equalization,namely HE-MI-FGSM(Histogram Equalization Momentum Iterative Fast Gradient Sign Method) is *** each iteration of the adversarial example generation process,the original input image is randomly histogram equalized,and then the gradient is calculated to generate adversarial perturbations to mitigate overfitting in the adversarial *** effectiveness of the method is verified on the ImageNet *** with the advanced method I-FGSM(Iterative Fast Gradient Sign Method) and MI-FGSM(Momentum I-FGSM),the attack success rate in the adversarial training network increased by 27.9% and 7.7% on average,respectively.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Improving Transferability Reversible Adversarial Examples Based on Flipping Transformation

Improving Transferability Reversible Adversarial Examples Ba...

引用

作者： Youqing Fang Jingwen Jia Yuhai Yang Wanli Lyu Key Lab of Intelligent Computing and Signal Processing of Ministry of Education School of Computer Science and Technology Anhui University

Adding subtle perturbations to an image can cause the classification model to misclassify, and such images are called adversarial examples. Adversarial examples threaten the safe use of deep neural networks, but when combined with reversible data hiding(RDH) technology, they can protect images from being correctly identified by unauthorized models and recover the image lossless under authorized models. Based on this, the reversible adversarial example(RAE) is rising. However, existing RAE technology focuses on feasibility, attack success rate and image quality, but ignores transferability and time complexity. In this paper,we optimize the data hiding structure and combine data augmentation technology,which flips the input image in probability to avoid overfitting phenomenon on the dataset. On the premise of maintaining a high success rate of white-box attacks and the image's visual quality, the proposed method improves the transferability of reversible adversarial examples by approximately 16% and reduces the computational cost by approximately 43% compared to the state-of-the-art method. In addition, the appropriate flip probability can be selected for different application scenarios.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Non-autoregressive machine translation with probabilistic context-free grammar 23

Non-autoregressive machine translation with probabilistic co...

引用

Proceedings of the 37th International Conference on Neural Information Processing Systems

作者： Shangtong Gui Chenze Shao Zhengrui Ma Xishan Zhang Yunji Chen Yang Feng State Key Lab of Processors Institute of Computing Technology Chinese Academy of Sciences and Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences and University of Chinese Academy of Sciences Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences and University of Chinese Academy of Sciences State Key Lab of Processors Institute of Computing Technology Chinese Academy of Sciences and Cambricon Technologies State Key Lab of Processors Institute of Computing Technology Chinese Academy of Sciences and University of Chinese Academy of Sciences

Non-autoregressive Transformer(NAT) significantly accelerates the inference of neural machine translation. However, conventional NAT models suffer from limited expression power and performance degradation compared to autoregressive (AT) models due to the assumption of conditional independence among target tokens. To address these limitations, we propose a novel approach called PCFG-NAT, which leverages a specially designed Probabilistic Context-Free Grammar (PCFG) to enhance the ability of NAT models to capture complex dependencies among output tokens. Experimental results on major machine translation benchmarks demonstrate that PCFG-NAT further narrows the gap in translation quality between NAT and AT models. Moreover, PCFG-NAT facilitates a deeper understanding of the generated sentences, addressing the lack of satisfactory explainability in neural machine translation. Code is publicly available at https://***/ictnlp/PCFG-NAT.

关键词：

来源：评论

学校读者我要写书评

暂无评论

G-MAP: General Memory-Augmented Pre-trained Language Model for Domain Tasks

G-MAP: General Memory-Augmented Pre-trained Language Model f...

引用

2022 Conference on Empirical Methods in Natural Language Processing, EMNLP 2022

作者： Wan, Zhongwei Yin, Yichun Zhang, Wei Shi, Jiaxin Shang, Lifeng Chen, Guangyong Jiang, Xin Liu, Qun Guangdong Provincial Key Laboratory of Computer Vision and Virtual Reality Technology Shenzhen Institute of Advanced Technology Chinese Academy of Science China University of Chinese Academy of Sciences China Huawei Noah's Ark Lab Huawei Cloud Computing Zhejiang Lab China

Recently, domain-specific PLMs have been proposed to boost the task performance of specific domains (e.g., biomedical and computer science) by continuing to pre-train general PLMs with domain-specific corpora. However, this Domain-Adaptive Pre-Training (DAPT;Gururangan et al. (2020)) tends to forget the previous general knowledge acquired by general PLMs, which leads to a catastrophic forgetting phenomenon and sub-optimal performance. To alleviate this problem, we propose a new framework of General Memory-Augmented Pre-trained Language Model (G-MAP), which augments the domain-specific PLM by a memory representation built from the frozen general PLM without losing any general knowledge. Specifically, we propose a new memory-augmented layer, and based on it, different augmented strategies are explored to build the memory representation and then adaptively fuse it into the domain-specific PLM. We demonstrate the effectiveness of G-MAP on various domains (biomedical and computer science publications, news, and reviews) and different kinds (text classification, QA, NER) of tasks, and the extensive results show that the proposed G-MAP can achieve SOTA results on all tasks. © 2022 Association for Computational Linguistics.

关键词： Computational linguistics

来源：评论

学校读者我要写书评

暂无评论

Blockchain-Based Multi-cloud Data Storage System Disaster Recovery

Blockchain-Based Multi-Cloud Data Storage System Disaster Re...

引用

2023 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2023

作者： Wang, Feiyu Zhou, Jian-Tao College of Computer Science Inner Mongolia University Inner Mongolia Hohhot China Engineering Research Center of Ecological Big Data Ministry of Education Natl. Loc. Jt. Eng. Research Center of Intelligent Information Processing Technology for Mongolian Inner Mongolia Engineering Laboratory for Cloud Computing and Service Software Inner Mongolia Key Laboratory of Social Computing and Data Processing Inner Mongolia Engineering Laboratory for Big Data Analysis Technology China

ISBN: (纸本)9798350337020

cloud storage services have been used by most businesses and individual users. However, data loss, service interruptions and cyber attacks often lead to cloud storage services not being provided properly, and these incidents have caused financial losses to users. Second, traditional and single-cloud model disaster recovery services are no longer suitable for the current complex cloud storage systems. Therefore, a scheme to provide disaster recovery for cloud storage services in a multi-cloud storage environment is needed in real production. In this paper, we propose a disaster recovery scheme based on blockchain technology. The proposed scheme outlined in this study aims to address the issue of data availability within the cloud storage landscape. The proposed scheme achieves this goal by dividing data into hot and cold categories, verifying the integrity of copy data via blockchain technology, and utilizing blockchain networks to manage multi-cloud storage systems. Experimental findings demonstrate that the proposed scheme yields superior results in terms of computation and time overheads. © 2023 IEEE.

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：