检索结果-内蒙古大学图书馆

Generalized Face Forgery Detection via Adaptive Learning for Pre-trained Vision Transformer

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Luo, Anwei Cai, Rizhao Kong, Chenqi Ju, Yakun Kang, Xiangui Huang, Jiwu Kot, Alex C. The School of Information Technology Jiangxi University of Finance and Economics Nanchang330013 China The School of Computer Science and Engineering Sun Yat-Sen University Guangzhou510006 China Lab. School of Electrical and Electronic Engineering Nanyang Technology University Singapore The Guangdong Key Laboratory of Intelligent Information Processing National Engineering Laboratory for Big Data System Computing Technology Shenzhen University Shenzhen518060 China The China-Singapore International Joint Research Institute Singapore

With the rapid progress of generative models, the current challenge in face forgery detection is how to effectively detect realistic manipulated faces from different unseen domains. Though previous studies show that pre-trained Vision Transformer (ViT) based models can achieve some promising results after fully fine-tuning on the Deepfake dataset, their generalization performances are still unsatisfactory. One possible reason is that fully fine-tuned ViT-based models may disrupt the pre-trained features [1], [2] and overfit to some data-specific patterns [3]. To alleviate this issue, we present a Forgery-aware Adaptive Vision Transformer (FA-ViT) under the adaptive learning paradigm, where the parameters in the pre-trained ViT are kept fixed while the designed adaptive modules are optimized to capture forgery features. Specifically, a global adaptive module is designed to model long-range interactions among input tokens, which takes advantage of self-attention mechanism to mine global forgery clues. To further explore essential local forgery clues, a local adaptive module is proposed to expose local inconsistencies by enhancing the local contextual association. In addition, we introduce a fine-grained adaptive learning module that emphasizes the common compact representation of genuine faces through relationship learning in fine-grained pairs, driving these proposed adaptive modules to be aware of fine-grained forgery-aware information. Extensive experiments demonstrate that our FA-ViT achieves state-of-the-arts results in the cross-dataset evaluation, and enhances the robustness against unseen perturbations. Particularly, FA-ViT achieves 93.83% and 78.32% AUC scores on Celeb-DF and DFDC datasets in the cross-dataset evaluation. The code and trained model have been released at: https://***/LoveSiameseCat/FAViT. Copyright © 2023, The Authors. All rights reserved.

关键词： Contrastive Learning

An architecture description language based on dynamic description logics for self-healing systems

学校读者我要写书评

暂无评论

International Journal of Advancements in computing technology 2012年第18期4卷 89-96页

作者： Wang, Zhuxiao Peng, Hui Guo, Jing Wu, Kehe Cui, Wenchao Wang, Xiaofeng School of Control and Computer Engineering State Key Laboratory of Alternate Electrical Power System with Renewable Energy Sources North China Electric Power University Beijing 102206 China Education Technology Center Beijing International Studies University Beijing 100024 China National Computer Network Emergency Response Technical Team/Coordination Center of China Beijing 100029 China School of Control and Computer Engineering Institute of Electric Information Security Engineering Research Center of Power Information North China Electric Power University Beijing 102206 China Institute of Computing Technology Chinese Academy of Sciences Beijing 100190 China

As biological systems exhibit adaptation, healing and robustness in the face of changing environmental behavior, this paradigm has actuated research dealing with the concept of self-healing systems, which attempt to heal themselves in the sense of recovering from malicious attacks and rectifying of system faults. The goal of self-healing systems is to provide survivable systems that require high dependability, robustness, adaptability, and availability. Such systems maintain one or more models, whether external or internal, at run time as a basis for identifying problems and resolving them. This article describes an architectural description language, called ADML, which is being developed as a new formal language and/or conceptual model for representing evolving software architectures. The ADML embraces dynamic change as a fundamental consideration, supports a broad class of adaptive changes at the architectural level, and offers a uniform way to represent and reason about both static and dynamic aspects of self-healing systems. Because the ADML is based on the Dynamic Description Logic DDL(SHON (D)), which can represent both dynamic semantics and static semantics under a unified logical framework, architectural ontology entailment for the ADML languages can be reduced to knowledge base satisfiability in DDL(SHON (D)), and dynamic description logic algorithms and implementations can be used to provide reasoning services for ADML. In this article, we present the syntax of ADML, explain its underlying semantics using the Dynamic Description Logic DDL(SHON (D)), and exemplify our approach by applying it to the domain of load balancing a wireless remote-access system;the preliminary results certify the potential of the approach.

关键词： Formal languages

Integrated verification model atsFPM based on functional, time and spatial constraints

学校读者我要写书评

暂无评论

Jisuanji Xuebao/Chinese Journal of computers 2009年第4期32卷 740-750页

作者： Niu, Jun Zeng, Guo-Sun Chen, Bo Department of Computer Science and Technology Tongji University Shanghai 201804 China Key Laboratory of Embedded System and Service Computing of Ministry of Education Shanghai 201804 China College of Information Engineering Zhejiang Business Technology Institute Ningbo 315012 China

Nowadays complex information system's integrated formal models of function verification and performance evaluation lack properties constraint about space aspect. This paper presents an integrated verification model atsFPM by defining a space requirement function over the states of the considered information system. The patterns of paths which are based on regular expressions is proposed in order to specify the functional specifications. The syntax and semantic of the model atsFPM is defined. A conversion product model is obtained by the combination of the system model and the automaton of the pattern of paths which expresses the functional specifications. The verification of the model atsFPM is tackled by the performance verification technique of Markov Reward Model. Experimental results show that the atsFPM model and its verification approach can satisfy the modeling of information system and verification of functional and performance specifications.

关键词： Information systems

A co-evolutionary particle swarm optimization with dynamic topology for solving multi-objective optimization problems

学校读者我要写书评

暂无评论

Advances in Modelling and Analysis A

Advances in Modelling and Analysis A 2016年第1期53卷 145-159页

作者： Wu, Daqing Tang, Lixiang Li, Haiyan Ouyang, LiJun Computer Science and Technology Institute University of South China HangyangHunan China Antai College of Economics and Management Shanghai Jiao Tong University Shanghai200240 China Zigong643000 China Key Laboratory of Guangxi High Schools for Complex System and Computational Intelligence Guangxi University for Nationalities Nanning530006 China Key Laboratory of Intelligent Computing and Signal Processing Ministry of Education Anhui University HefeiAnhui Province230039 China Department of Business Administration Hunan University of Finance and Economics Hunan410205 China

This paper proposes a multi-objective with dynamic topology particle swarm optimization (PSO) algorithm for solving multi-objective problems, named DTPSO. One of the main drawbacks of classical multi-objective particle swarm optimization algorithm is low diversity. To overcome this disadvantage, DTPSO uses two dynamic local best particles to lead the search particles with multiple populations to deal with multiple objectives, and maintains diversity of new found non-dominated solutions via partitioned the searching space into fixed number of cells. The proposed DTPSO is validated through comparisons with other two multi-objective algorithms using established benchmarks and metrics. Simulation results demonstrated that DTPSO shows competitive, if not better, performance as compared to the other algorithms. © 2016, AMSE Press. All rights reserved.

关键词： Multiobjective optimization

AsyncSC: An Asynchronous Sidechain for Multi-Domain Data Exchange in Internet of Things

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Yang, Lingxiao Dong, Xuewen Wan, Zhiguo Gao, Sheng Tong, Wei Lu, Di Shen, Yulong Du, Xiaojiang The School of Computer Science and Technology Xidian University The Engineering Research Center of Blockchain Technology Application and Evaluation Ministry of Education China The Shaanxi Key Laboratory of Blockchain and Secure Computing Xi'An710071 China The Zhejiang Lab Hangzhou311121 China The School of Information Central University of Finance and Economics Beijing100081 China The School of Information Science and Engineering Zhejiang Sci-Tech University Hangzhou310018 China The School of Computer Science and Technology Xidian University China The Shaanxi Key Laboratory of Network and System Security Xi'An710071 China The School of Engineering and Science Stevens Institute of Technology Hoboken07030 United States

Sidechain techniques improve blockchain scalability and interoperability, providing decentralized exchange and cross-chain collaboration solutions for Internet of Things (IoT) data across various domains. However, current state-of-the-art (SOTA) schemes for IoT multi-domain data exchange are constrained by the need for synchronous networks, hindering efficient cross-chain interactions in discontinuous networks and leading to suboptimal data exchange. In this paper, we propose AsyncSC, a novel asynchronous sidechain construction. It employs a committee to provide Cross-Blockchain as a Service (C-BaaS) for data exchange in multi-domain IoT. To fulfill the need for asynchronous and efficient data exchange, we combine the ideas of aggregate signatures and verifiable delay functions to devise a novel cryptographic primitive called delayed aggregate signature (DAS), which constructs asynchronous cross-chain proofs (ACPs) that ensure the security of cross-chain interactions. To ensure the consistency of asynchronous transactions, we propose a multilevel buffered transaction pool that guarantees the transaction sequencing. We analyze and prove the security of AsyncSC, simulate an asynchronous communication environment, and conduct a comprehensive evaluation. The results show that AsyncSC outperforms SOTA schemes, improving throughput by an average of 1.21 to 3.96 times, reducing transaction latency by 59.76% to 83.61%, and maintaining comparable resource overhead. Copyright © 2024, The Authors. All rights reserved.

关键词：

Spatial sparse subspace clustering for compressive spectral imaging

学校读者我要写书评

暂无评论

arXiv 2019年

作者： Zhu, Jianchen Zhang, Tong Zhao, Shengjie Hinojosa, Carlos Liu, Zengli Arce, Gonzalo R. Key Laboratory of Embedded System and Service Computing Ministry of Education School of Software Engineering Tongji University Shanghai201804 China School of Electronic and Information Engineering Tongji University Shanghai201804 China Department of System Engineering and Informatics Universidad Industrial de Santander Bucaramanga680002 Colombia Institute of information engineering and automation Computer Center Kunming University of Science and Technology Kunming650500 China Department of Electrical and Computer Engineering University of Delaware NewarkDE19716 United States

This paper aims at developing a clustering approach with spectral images directly from CASSI compressive measurements. The proposed clustering method first assumes that compressed measurements lie in the union of multiple low-dimensional subspaces. Therefore, sparse subspace clustering (SSC) is an unsupervised method that assigns compressed measurements to their respective subspaces. In addition, a 3D spatial regularizer is added into the SSC problem, thus taking full advantages of the spatial information contained in spectral images. The performance of the proposed spectral image clustering approach is improved by taking optimal CASSI measurements obtained when optimal coded apertures are used in CASSI system. Simulation with one real dataset illustrates the accuracy of the proposed spectral image clustering approach. Copyright © 2019, The Authors. All rights reserved.

关键词： Spectroscopy

Towards High-resolution 3D Anomaly Detection via Group-Level Feature Contrastive Learning

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Zhu, Hongze Xie, Guoyang Hou, Chengbin Dai, Tao Gao, Can Wang, Jinbao Shen, Linlin National Engineering Laboratory for Big Data System Computing Technology Shenzhen University Shenzhen China Department of Computer Science City University of Hong Kong Hong Kong Department of Intelligent Manufacturing CATL Ningde China Fuzhou Fuyao Institute for Advanced Study Fuyao University of Science and Technology Fuzhou China College of Computer Science and Software Engineering Shenzhen University Shenzhen China Guangdong Provincial Key Laboratory of Intelligent Information Processing Shenzhen China Shenzhen University Shenzhen China Shenzhen Institute of Artificial Intelligence and Robotics for Society Shenzhen China

High-resolution point clouds (HRPCD) anomaly detection (AD) plays a critical role in precision machining and high-end equipment manufacturing. Despite considerable 3D-AD methods that have been proposed recently, they still cannot meet the requirements of the HRPCD-AD task. There are several challenges: i) It is difficult to directly capture HRPCD information due to large amounts of points at the sample level;ii) The advanced transformer-based methods usually obtain anisotropic features, leading to degradation of the representation;iii) The proportion of abnormal areas is very small, which makes it difficult to characterize. To address these challenges, we propose a novel group-level feature-based network, called Group3AD, which has a significantly efficient representation ability. First, we design an Intercluster Uniformity Network (IUN) to present the mapping of different groups in the feature space as several clusters, and obtain a more uniform distribution between clusters representing different parts of the point clouds in the feature space. Then, an Intracluster Alignment Network (IAN) is designed to encourage groups within the cluster to be distributed tightly in the feature space. In addition, we propose an Adaptive Group-Center Selection (AGCS) based on geometric information to improve the pixel density of potential anomalous regions during inference. The experimental results verify the effectiveness of our proposed Group3AD, which surpasses Reg3D-AD by the margin of 5% in terms of object-level AUROC on Real3DAD. We provide the code and supplementary information on our website: https://***/M-3LAB/Group3AD. Copyright © 2024, The Authors. All rights reserved.

关键词： Anomaly detection

Joint learning of discriminative low-dimensional image representations based on dictionary learning and two-layer orthogonal projections

学校读者我要写书评

暂无评论

arXiv 2019年

作者： Wei, Xian Shen, Hao Li, Yuanxiang Tang, Xuan Jin, Bo Zhao, Lijun Murphey, Yi Lu Fujian Institute of Research on the Structure of Matter Chinese Academy of Sciences China Technical University of Munich Germany and fortiss GmbH Munich Germany Shanghai Key Lab for Trustworthy Computing School of Computer Science and Software Engineering East China Normal University China School of Aeronautics & Astronautics Shanghai Jiao Tong University Shanghai200240 China State Key Laboratory of Robotics and System Harbin Institute of Technology Harbin150006 China Department of Electrical and Computer Engineering University of Michigan-Dearborn DearbornMI48128 United States

This work investigates the problem of efficiently learning discriminative low-dimensional representations of multi-class large-scale image objects. We propose a generic deep learning approach by taking advantages of Convolutional Neural Networks (CNN), sparse dictionary learning, and orthogonal projections. CNN is not only powerful on feature extraction, but also robust to spatial variance and changes. Sparse dictionary learning is well known for disentangling nonlinear underlying discriminative factors in data. The orthogonal projection is a notable efficient tool to project multi-class data onto low dimensional discriminative subspace. The proposed procedure can be summarized as follows. At first, a CNN is employed to extract high-dimensional (HD) preliminary convolutional features. Secondly, to avoid the high computational cost of direct sparse coding on HD CNN features, we present to learn sparse representation (SR) in an orthogonal projected space over a task-driven sparsifying dictionary. We then exploit the discriminative projection on SR. The whole learning process is treated as a joint optimization problem of trace quotient maximization, which involves the CNN parameters, the orthogonal projection on CNN features, the dictionary and the discriminative projection on sparse codes. The related cost function is well defined on product manifold of the Stiefel manifold, the Oblique manifold, and the Grassmann manifold. It is optimized via a geometrical stochastic gradient descent algorithm. Finally, the quality of dictionary and projections learned by the proposed approach is further investigated in terms of image classification. The experimental results show that the approach can achieve a strongly competitive performance with state-of-the-art image classification methods. Copyright © 2019, The Authors. All rights reserved.

关键词： Convolution

Depth-Aware Multi-Modal Fusion for Generalized Zero-Shot Learning

学校读者我要写书评

暂无评论

Depth-Aware Multi-Modal Fusion for Generalized Zero-Shot Lea...

IEEE International Conference on Industrial Informatics (INDIN)

作者： Weipeng Cao Xuyang Yao Zhiwu Xu Yinghui Pan Yixuan Sun Dachuan Li Bohua Qiu Muheng Wei Guangdong Laboratory of Artificial Intelligence and Digital Economy (Shenzhen) Shenzhen China National Engineering Laboratory for Big Data System Computing Technology Shenzhen University Shenzhen China College of Computer Science and Software Engineering Shenzhen University Shenzhen China Stony Brook University New York United States Research Institute of Trustworthy Autonomous Systems Southern University of Science and Technology Shenzhen China Department of Computer Science and Engineering Southern University of Science and Technology Shenzhen China ZhenDui Industry Artificial Intelligence Co. Ltd Shenzhen China Department of Automation Shanghai Jiao Tong University Shanghai China Key Laboratory of System Control and Information Processing Ministry of Education of China Shanghai China

ISBN: (数字)9798331527471

ISBN: (纸本)9798331527488

Realizing Generalized Zero-Shot Learning (GZSL) based on large models is emerging as a prevailing trend. However, most existing methods merely regard large models as black boxes, solely leveraging the features output by the final layer while disregarding potential performance enhancements from other layers. Indeed, numerous researchers have visually depicted variations in the features learned across different layers of neural networks. Motivated by this observation, we propose a Vision Transformer (ViT)-based GZSL method named Depth-Aware Multi-Modal ViT (DAM2ViT), which exploits multi-level features of ViT. DAM2ViT incorporates a multi-modal interaction block to align semantic information of categories across multiple layers, thereby augmenting the model's capacity to learn associations between visual and semantic spaces. Extensive experiments conducted on three benchmark datasets (i.e., CUB, SUN, AWA2) have showcased that DAM2ViT achieves competitive results compared to state-of-the-art methods.

关键词： Visualization Adaptation models Semantics Zero shot learning Neural networks Termination of employment Transformers Market research Sun Optimization