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

UAV-Aided Secure Communication With Deployment Optimization and Cooperative Jamming 11

学校读者我要写书评

暂无评论

UAV-Aided Secure Communication With Deployment Optimization ...

11th International Conference on intelligent Control and information processing, ICICIP 2021

作者： Li, Hongbing Wu, Juan Luo, Lei Xiong, Jiang Chongqing Three Gorges University Key Lab. of Intelligent Information Processing and Control of Chongqing Municipal Institutions Chongqing Engineering Research Center of Internet of Things and Intelligent Control Technology Wanzhou China Chongqing Three Gorges University Chongqing Key Laboratory of Geological Environment Monitoring and Disaster Early-Warning Wanzhou China Beijing University of Posts and Telecommunications School of Artificial Intelligence Beijing China

ISBN: (纸本)9781665425155

This paper investigates the jointly transmit power and unmanned aerial vehicle (UAV)/jammer deployment optimization problem for UAV enabled jammer-assisted secure communication systems, where a jammer is exploited to assist transmitting data from a source node to a legitimate destination node in the presence of multiple eavesdroppers. To increase the secrecy energy efficiency, which is defined as the achievable secrecy rate per energy consumption unit, we formulate a secrecy energy efficiency maximization problem by jointly optimizing the transmit power and UAV/jammer deployment. The resulting optimization problem is shown to be a non-convex and fractional optimization problem, which is challenging to solve. As such, we decompose the original problem into two sub-problems, and then, an efficient iterative algorithm is proposed by leveraging the extensive search method and Dinkelbach method in combination with successive convex approximation (SCA) techniques. Numerical simulation results show that the proposed scheme significantly improves the secrecy energy efficiency of the system. © 2021 IEEE.

关键词： Energy efficiency

Rapid synthesis of Pd single‐atom/cluster as highly active catalysts for Suzuki coupling reactions

学校读者我要写书评

暂无评论

Chinese Journal of Catalysis 2022年第4期43卷 1058-1065页

作者： Hehe Wei Xiaoyang Li Bohan Deng Jialiang Lang Ya Huang Xingyu Hua Yida Qiao Binghui Ge Jun Ge Hui Wu State Key Laboratory of New Ceramics and Fine Processing School of Materials Science and EngineeringTsinghua UniversityBeijing 100084China Key Lab for Industrial Biocatalysis Ministry of EducationDepartment of Chemical EngineeringTsinghua UniversityBeijing 100084China Institutes of Physical Science and Information Technology Anhui UniversityHefei 230601AnhuiChina Key Laboratory for Advanced Materials Center for Computational Chemistry and Research Institute of Industrial CatalysisEast China University of Science and TechnologyShanghai 200237China

Palladium(Pd)‐based catalysts are essential to drive high‐performance Suzuki coupling reactions,which are powerful tools for the synthesis of functional organic ***,we developed a solution‐rapid‐annealing process to stabilize nitrogen‐mesoporous carbon supported Pd single‐atom/cluster(Pd/NMC)material,which provided a catalyst with superior performance for Suzuki coupling *** comparison with commercial palladium/carbon(Pd/C)catalysts,the Pd/NMC catalyst exhibited significantly boosted activity(100%selectivity and 95%yield)and excellent stability(almost no decay in activity after 10 reuse cycles)for the Suzuki coupling reactions of chlorobenzenes,together with superior yield and excellent selectivity in the fields of the board scope of the ***,our newly developed rapid annealing process of precursor solutions is applied as a generalized method to stabilize metal clusters(***,Pt,Ru),opening new possibilities in the construction of efficient highly dispersed metal atom and sub‐nanometer cluster catalysts with high performance.

关键词： Pd single‐atom/cluster catalyst Suzuki coupling reactions Solution rapid annealing Energy barrier High yield

Quantifying robustness to adversarial word substitutions

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Yang, Yuting Huang, Pei Ma, Fei Fei Cao, Juan Zhang, Meishan Zhang, Jian Li, Jintao Key Lab Of Intelligent Information Processing Institute Of Computing Technology Chinese Academy Of Sciences Beijing100190 China University Of Chinese Academy Of Sciences Beijing100049 China Beijing100190 China Laboratory Of Parallel Software And Computational Science ISCAS Beijing100190 China China

Deep-learning-based NLP models are found to be vulnerable to word substitution perturbations. Before they are widely adopted, the fundamental issues of robustness need to be addressed. Along this line, we propose a formal framework to evaluate word-level robustness. First, to study safe regions for a model, we introduce robustness radius which is the boundary where the model can resist any perturbation. As calculating the maximum robustness radius is computationally hard, we estimate its upper and lower bound. We repurpose attack methods as ways of seeking upper bound and design a pseudo-dynamic programming algorithm for a tighter upper bound. Then verification method is utilized for a lower bound. Further, for evaluating the robustness of regions outside a safe radius, we reexamine robustness from another view: quantification. A robustness metric with a rigorous statistical guarantee is introduced to measure the quantification of adversarial examples, which indicates the model's susceptibility to perturbations outside the safe radius. The metric helps us figure out why state-of-the-art models like BERT can be easily fooled by a few word substitutions, but generalize well in the presence of real-world noises. Copyright © 2022, The Authors. All rights reserved.

关键词： Dynamic programming

Hierarchical Object-to-Zone Graph for Object Navigation

学校读者我要写书评

暂无评论

Hierarchical Object-to-Zone Graph for Object Navigation

International Conference on Computer Vision (ICCV)

作者： Sixian Zhang Xinhang Song Yubing Bai Weijie Li Yakui Chu Shuqiang Jiang Key Lab of Intelligent Information Processing Laboratory of the Chinese Academy of Sciences (CAS) Institute of Computing Technology Beijing University of Chinese Academy of Sciences Beijing Huawei Application Innovate Laboratory Beijing Institute of Intelligent Computing Technology Suzhou CAS

ISBN: (纸本)9781665428132

The goal of object navigation is to reach the expected objects according to visual information in the unseen environments. Previous works usually implement deep models to train an agent to predict actions in real-time. However, in the unseen environment, when the target object is not in egocentric view, the agent may not be able to make wise decisions due to the lack of guidance. In this paper, we propose a hierarchical object-to-zone (HOZ) graph to guide the agent in a coarse-to-fine manner, and an online-learning mechanism is also proposed to update HOZ according to the real-time observation in new environments. In particular, the HOZ graph is composed of scene nodes, zone nodes and object nodes. With the pre-learned HOZ graph, the real-time observation and the target goal, the agent can constantly plan an optimal path from zone to zone. In the estimated path, the next potential zone is regarded as sub-goal, which is also fed into the deep reinforcement learning model for action prediction. Our methods are evaluated on the AI2-Thor simulator. In addition to widely used evaluation metrics SR and SPL, we also propose a new evaluation metric of SAE that focuses on the effective action rate. Experimental results demonstrate the effectiveness and efficiency of our proposed method. The code is available at https://***/sx-zhang/***.

关键词： Measurement Weight measurement Visualization Computer vision Codes Navigation Reinforcement learning

Variational quantum eigensolver with linear depth problem-inspired ansatz for solving portfolio optimization in finance

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Wang, Shengbin Wang, Peng Li, Guihui Zhao, Shubin Zhao, Dongyi Wang, Jing Fang, Yuan Dou, Menghan Gu, Yongjian Wu, Yu-Chun Guo, Guo-Ping Origin Quantum Computing Company Limited Anhui Hefei230026 China CAS Key Laboratory of Quantum Information University of Science and Technology of China Anhui Hefei230026 China Intelligent Information Sensing and Processing Lab College of Electronic Engineering Ocean University of China Shandong Qingdao266000 China College of Physics and Optoelectronic Engineering Ocean University of China Shandong Qingdao266100 China Institute of Artificial Intelligence Hefei Comprehensive National Science Center Anhui Hefei230088 China

Great efforts have been dedicated in recent years to explore practical applications for noisy intermediate-scale quantum (NISQ) computers, which is a fundamental and challenging problem in quantum computing. As one of the most promising methods, the variational quantum eigensolver (VQE) has been extensively studied. In this paper, VQE is applied to solve portfolio optimization problems in finance by designing two hardware-efficient Dicke state ansatze that reach a maximum of 2n two-qubit 2 gate depth and n2/4 parameters, with n being the number of qubits used. Both ansatze are partitioning-friendly, allowing for the proposal of a highly scalable quantum/classical hybrid distributed computing (HDC) scheme. Combining simultaneous sampling, problem-specific measurement error mitigation, and fragment reuse techniques, we successfully implement the HDC experiments on a superconducting quantum computer with up to 55 qubits. The simulation and experimental results illustrate that the restricted expressibility of the ansatze, induced by the small number of parameters and limited entanglement, is advantageous for solving classical optimization problems with the cost function of the conditional value-at-risk (CVaR) for the NISQ era and beyond. Furthermore, the HDC scheme shows great potential for achieving quantum advantage in the NISQ era. We hope that the heuristic idea presented in this paper can motivate fruitful investigations in current and future quantum computing paradigms. Copyright © 2024, The Authors. All rights reserved.

关键词： Optimization

Improving the trainability of VQE on NISQ computers for solving portfolio optimization using convex interpolation

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Wang, Shengbin Li, Guihui Chen, Zhaoyun Wang, Peng Dou, Menghan Zheng, Haiyong Wang, Zhimin Gu, Yongjian Wu, Yu-Chun Guo, Guo-Ping Origin Quantum Computing Company Limited Anhui Hefei230026 China CAS Key Laboratory of Quantum Information University of Science and Technology of China Anhui Hefei230026 China Intelligent Information Sensing and Processing Lab College of Electronic Engineering Ocean University of China Shandong Qingdao266000 China Institute of Artificial Intelligence Hefei Comprehensive National Science Center Anhui Hefei230088 China College of Physics and Optoelectronic Engineering Ocean University of China Shandong Qingdao266100 China

Solving combinatorial optimization problems using variational quantum algorithms (VQAs) represents one of the most promising applications in the NISQ era. However, the limited trainability of VQAs could hinder their scalability to large problem sizes. In this paper, we improve the trainability of variational quantum eigensolver (VQE) by utilizing convex interpolation to solve portfolio optimization. The idea is inspired by the observation that the Dicke state possesses an inherent clustering property. Consequently, the energy of a state with a larger Hamming distance from the ground state intuitively results in a greater energy gap away from the ground state energy in the overall distribution trend. Based on convex interpolation, the location of the ground state can be evaluated by learning the property of a small subset of basis states in the Hilbert space. This enlightens naturally the proposals of the strategies of close-to-solution initialization, regular cost function landscape, and recursive ansatz equilibrium partition. The successfully implementation of a 40-qubit experiment using only 10 superconducting qubits demonstrates the effectiveness of our proposals. Furthermore, the quantum inspiration has also spurred the development of a prototype greedy algorithm. Extensive numerical simulations indicate that the hybridization of VQE and greedy algorithms achieves a mutual complementarity, combining the advantages of both global and local optimization methods. Our proposals can be extended to improve the trainability for solving other large-scale combinatorial optimization problems that are widely used in real applications, paving the way to unleash quantum advantages of NISQ computers in the near future. Copyright © 2024, The Authors. All rights reserved.

关键词： Ground state

ClickVOS: Click Video Object Segmentation

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Guo, Pinxue Hong, Lingyi Zhou, Xinyu Gao, Shuyong Li, Wanyun Li, Jinglun Chen, Zhaoyu Li, Xiaoqiang Zhang, Wei Zhang, Wenqiang the Shanghai Engineering Research Center of AI&Robotics Academy for Engineering&Technology Fudan University Shanghai China the Shanghai Key Lab of Intelligent Information Processing School of Computer Science Fudan University Shanghai China the School of Computer Engineering and Science Shanghai University Shanghai China Engineering Research Center of AI&Robotics Ministry of Education Academy for Engineering&Technology Fudan University Shanghai China

—Video Object Segmentation (VOS) task aims to segment objects in videos. However, previous settings either require time-consuming manual masks of target objects at the first frame during inference or lack the flexibility to specify arbitrary objects of interest. To address these limitations, we propose the setting named Click Video Object Segmentation (ClickVOS) which segments objects of interest across the whole video according to a single click per object in the first frame. And we provide the extended datasets DAVIS-P and YouTubeVOS-P that with point annotations to support this task. ClickVOS is of significant practical applications and research implications due to its only 1-2 seconds interaction time for indicating an object, comparing annotating the mask of an object needs several minutes. However, ClickVOS also presents increased challenges. To address this task, we propose an end-to-end baseline approach named called Attention Before Segmentation (ABS), motivated by the attention process of humans. ABS utilizes the given point in the first frame to perceive the target object through a concise yet effective segmentation attention. Although the initial object mask is possibly inaccurate, in our ABS, as the video goes on, the initially imprecise object mask can self-heal instead of deteriorating due to error accumulation, which is attributed to our designed improvement memory that continuously records stable global object memory and updates detailed dense memory. In addition, we conduct various baseline explorations utilizing off-the-shelf algorithms from related fields, which could provide insights for the further exploration of ClickVOS. The experimental results demonstrate the superiority of the proposed ABS approach. Extended datasets and codes will be available at https://***/PinxueGuo/ClickVOS. Copyright © 2024, The Authors. All rights reserved.

关键词： Motion compensation

BCIM: Budget and capacity constrained influence maximization in multilayer networks

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Zhang, Su-Su Liu, Chuang Wang, Huijuan Chen, Yang Zhan, Xiu-Xiu Research Center for Complexity Sciences Hangzhou Normal University Hangzhou311121 China College of Media and International Culture Zhejiang University Hangzhou310058 China Faculty of Electrical Engineering Mathematics and Computer Science Delft University of Technology Mekelweg 4 Delft2628 CD Netherlands Shanghai Key Lab of Intelligent Information Processing School of Computer Science Fudan University Shanghai200433 China

Influence maximization (IM), which aims to select a set of seed nodes that can maximize their influence within a network, can be applied to various domains, such as viral marketing, disease control, and political campaigns. One of the extended IM problems, i.e., budgeted Influence Maximization (BIM), adds a budgeted constraint, which considers that different nodes may have different costs. However, the definition of the current BIM problem has limitations, as it only imposes a budget constraint. This may lead to solutions with a large number of low-cost nodes that are not applicable to real-world scenarios. Furthermore, since users can transmit information on multiple social networking platforms, solving the BIM problem across different platforms could better optimize resource usage. To address these issues, we propose a Budget and Capacity Constrained Influence Maximization (BCIM) problem in multilayer networks and design a Multilayer Multi-Population Genetic Algorithm (MMGA) to solve it. In MMGA, a repair module addresses budget constraints, while a multi-population parallel module handles capacity (seed size) constraints. Additionally, the initialization module, which considers multilayer network properties, and the multi-population parallel module significantly enhance the algorithm's efficiency. Extensive experiments upon various synthetic and empirical multilayer networks indicate that MMGA achieves at least a 10% improvement in spreading performance under budget and capacity constraints compared to baseline methods extended from various classical IM problems. The proposed BCIM problem opens up a new direction in influence maximization, and the proposed method offers an effective and efficient framework to the problem. Copyright © 2024, The Authors. All rights reserved.

关键词： Costs