检索结果-内蒙古大学图书馆

Contourlet Refinement Gate Framework for Thermal Spectrum Distribution Regularized Infrared Image Super-Resolution

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Zou, Yang Chen, Zhixin Zhang, Zhipeng Li, Xingyuan Ma, Long Liu, Jinyuan Wang, Peng Zhang, Yanning School of Computer Science Northwestern Polytechnical University Xi’an710129 China Graduate School of Information Production and Systems Waseda University Fukuoka8080135 Japan School of Software Dalian University of Technology Dalian116024 China School of Mechanical Engineering Dalian University of Technology Dalian116024 China The National Engineering Laboratory for Integrated Aero-Space-Ground-Ocean Big Data Application Technology China

Image super-resolution (SR) is a classical yet still active low-level vision problem that aims to reconstruct high-resolution (HR) images from their low-resolution (LR) counterparts, serving as a key technique for image enhancement. Current approaches to address SR tasks, such as transformer-based and diffusion-based methods, are either dedicated to extracting RGB image features or assuming similar degradation patterns, neglecting the inherent modal disparities between infrared and visible images. When directly applied to infrared image SR tasks, these methods inevitably distort the infrared spectral distribution, compromising the machine perception in downstream tasks. In this work, we emphasize the infrared spectral distribution fidelity and propose a Contourlet refinement gate framework to restore infrared modal-specific features while preserving spectral distribution fidelity. Our approach captures high-pass subbands from multi-scale and multi-directional infrared spectral decomposition to recover infrared-degraded information through a gate architecture. The proposed Spectral Fidelity Loss regularizes the spectral frequency distribution during reconstruction, which ensures the preservation of both high- and low-frequency components and maintains the fidelity of infrared-specific features. We propose a two-stage prompt-learning optimization to guide the model in learning infrared HR characteristics from LR degradation. Extensive experiments demonstrate that our approach outperforms existing image SR models in both visual and perceptual tasks while notably enhancing machine perception in downstream tasks. Our code is available at https://***/hey-it-s-me/*** Codes 68T45 Copyright © 2024, The Authors. All rights reserved.

关键词： Infrared imaging

DeepfakeBench: a comprehensive benchmark of deepfake detection 23

学校读者我要写书评

暂无评论

DeepfakeBench: a comprehensive benchmark of deepfake detecti...

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

作者： Zhiyuan Yan Yong Zhang Xinhang Yuan Siwei Lyu Baoyuan Wu School of Data Science The Chinese University of Hong Kong Shenzhen (CUHK-Shenzhen) China Tencent AI Lab Department of Computer Science and Engineering University at Buffalo State University of New York

A critical yet frequently overlooked challenge in the field of deepfake detection is the lack of a standardized, unified, comprehensive benchmark. This issue leads to unfair performance comparisons and potentially misleading results. Specifically, there is a lack of uniformity in data processing pipelines, resulting in inconsistent data inputs for detection models. Additionally, there are noticeable differences in experimental settings, and evaluation strategies and metrics lack standardization. To fill this gap, we present the first comprehensive benchmark for deepfake detection, called DeepfakeBench, which offers three key contributions: 1) a unified data management system to ensure consistent input across all detectors, 2) an integrated framework for state-of-the-art methods implementation, and 3) standardized evaluation metrics and protocols to promote transparency and reproducibility. Featuring an extensible, modular-based codebase, DeepfakeBench contains 15 state-of-the-art detection methods, 9 deepfake datasets, a series of deepfake detection evaluation protocols and analysis tools, as well as comprehensive evaluations. Moreover, we provide new insights based on extensive analysis of these evaluations from various perspectives (e.g., data augmentations, backbones). We hope that our efforts could facilitate future research and foster innovation in this increasingly critical domain. All codes, evaluations, and analyses of our benchmark are publicly available at https://***/SCLBD/DeepfakeBench.

关键词：

Integrated Sensing-Communication-Computation for Over-the-Air Edge AI Inference

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Zhuang, Zeming Wen, Dingzhu Shi, Yuanming Zhu, Guangxu Wu, Sheng Niyato, Dusit Network Intelligence Center School of Information Science and Technology ShanghaiTech University Shanghai China Shenzhen Research Institute of Big Data Shenzhen China The School of Information and Communication Engineering Beijing University of Posts and Telecommunications Beijing100876 China School of Computer Science and Engineering Nanyang Technological University Singapore

Edge-device co-inference refers to deploying well-trained artificial intelligent (AI) models at the network edge under the cooperation of devices and edge servers for providing ambient intelligent services. For enhancing the utilization of limited network resources in edge-device co-inference tasks from a systematic view, we propose a task-oriented scheme of integrated sensing, computation and communication (ISCC) in this work. In this system, all devices sense a target from the same wide view to obtain homogeneous noise-corrupted sensory data, from which the local feature vectors are extracted. All local feature vectors are aggregated at the server using over-the-air computation (AirComp) in a broadband channel with the orthogonal-frequency-division-multiplexing technique for suppressing the sensing and channel noise. The aggregated denoised global feature vector is further input to a server-side AI model for completing the downstream inference task. A novel task-oriented design criterion, called maximum minimum pairwise discriminant gain, is adopted for classification tasks. It extends the distance of the closest class pair in the feature space, leading to a balanced and enhanced inference accuracy. Under this criterion, a problem of joint sensing power assignment, transmit precoding and receive beamforming is formulated. The challenge lies in three aspects: the coupling between sensing and AirComp, the joint optimization of all feature dimensions' AirComp aggregation over a broadband channel, and the complicated form of the maximum minimum pair-wise discriminant gain. To solve this problem, a task-oriented ISCC scheme with AirComp is proposed. Experiments based on a human motion recognition task are conducted to verify the advantages of the proposed scheme over the existing scheme and a baseline. Copyright © 2023, The Authors. All rights reserved.

关键词： Motion estimation

Audio Steganography Based Backdoor Attack for Speech Recognition Software

学校读者我要写书评

暂无评论

Audio Steganography Based Backdoor Attack for Speech Recogni...

IEEE Annual International computer Software and Applications Conference (COMPSAC)

作者： Mengyuan Zhang Shunhui Ji Hanbo Cai Hai Dong Pengcheng Zhang Yunhe Li Key Laboratory of Water Big Data Technology of Ministry of Water Resources Hohai University Nanjing China College of Computer Science and Software Engineering Hohai University Nanjing China School of Computing Technologies RMIT University Melbourne Australia

ISBN: (数字)9798350376968

ISBN: (纸本)9798350376975

With the growing prevalence of deep learning in the speech area, speech recognition, voice control, and related applications have become integral parts of people's lives. However, the rise of malicious third-party platforms has introduced significant security concerns, particularly through backdoor attacks. These attacks implant triggers that manipulate speech recognition models to produce specific labels, thereby compromising the system's integrity. Studying speech backdoor attacks is crucial for evaluating the security of speech recognition software, and iden-tifying and addressing potential vulnerabilities. Existing methods for speech backdoor attacks usually employ fixed perturbations as triggers. However, these perturbations may be discernible to the human ear, making them easily detectable. To address this issue, we propose a frequency domain-embedded backdoor attack method based on echo hiding. Echo hiding is a steganography technique based on audio. This method embeds hidden information into the frequency spectrum of the echo signal, leveraging the masking property of the human auditory system. It is difficult to arouse suspicion or detect the presence of hidden information since echo is perceived as a natural phenomenon in auditory perception. Furthermore, it does not cause a significant decrease in audio quality. Experimental results show the effectiveness of our method in different settings.

关键词： Training Steganography Perturbation methods Frequency-domain analysis Speech recognition Ear Implants

Decomposed linear dynamical systems (dLDS) for learning the latent components of neural dynamics

学校读者我要写书评

暂无评论

The Journal of Machine Learning Research

The Journal of Machine Learning Research 2024年第1期25卷 2962-2973页

作者： Noga Mudrik Yenho Chen Eva Yezerets Christopher J. Rozell Adam S. Charles Department of Biomedical Engineering Center for Imaging Science Kavli NDI Johns Hopkins University Baltimore MD Department of Biomedical Engineering Georgia Institute of Technology Atlanta GA Department of Biomedical Engineering Center for Imaging Science Johns Hopkins University Baltimore MD School of Electrical and Computer Engineering Georgia Institute of Technology Atlanta GA Department of Biomedical Engineering Center for Imaging Science Mathematical Institute for Data Science Kavli NDI Johns Hopkins University Baltimore MD

Learning interpretable representations of neural dynamics at a population level is a crucial first step to understanding how observed neural activity relates to perception and behavior. Models of neural dynamics often focus on either low-dimensional projections of neural activity or on learning dynamical systems that explicitly relate to the neural state over time. We discuss how these two approaches are interrelated by considering dynamical systems as representative of flows on a low-dimensional manifold. Building on this concept, we propose a new decomposed dynamical system model that represents complex non-stationary and nonlinear dynamics of time series data as a sparse combination of simpler, more interpretable components. Our model is trained through a dictionary learning procedure, where we leverage recent results in tracking sparse vectors over time. The decomposed nature of the dynamics is more expressive than previous switched approaches for a given number of parameters and enables modeling of overlapping and non-stationary dynamics. In both continuous-time and discrete-time instructional examples, we demonstrate that our model effectively approximates the original system, learns efficient representations, and captures smooth transitions between dynamical modes. Furthermore, we highlight our model's ability to efficiently capture and demix population dynamics generated from multiple independent subnetworks, a task that is computationally impractical for switched models. Finally, we apply our model to neural "full brain" recordings of C. elegans data, illustrating a diversity of dynamics that is obscured when classified into discrete states.

关键词：

AGHINT: Attribute-Guided Representation Learning on Heterogeneous Information Networks with Transformer

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Yuan, Jinhui Lu, Shan Duan, Peibo He, Jieyue School of Computer Science and Engineering Southeast University Nanjing China Nanjing FiberHome Tiandi Co. Ltd. Nanjing China Department of Data Science and Artificial Intelligent Faculty of Information Technology Monash University Suzhou China

Recently, heterogeneous graph neural networks (HGNNs) have achieved impressive success in representation learning by capturing long-range dependencies and heterogeneity at the node level. However, few existing studies have delved into the utilization of node attributes in heterogeneous information networks (HINs). In this paper, we investigate the impact of inter-node attribute disparities on HGNNs performance within the benchmark task, i.e., node classification, and empirically find that typical models exhibit significant performance decline when classifying nodes whose attributes markedly differ from their neighbors. To alleviate this issue, we propose a novel Attribute-Guided heterogeneous Information Networks representation learning model with Transformer (AGHINT), which allows a more effective aggregation of neighbor node information under the guidance of attributes. Specifically, AGHINT transcends the constraints of the original graph structure by directly integrating higher-order similar neighbor features into the learning process and modifies the message-passing mechanism between nodes based on their attribute disparities. Extensive experimental results on three real-world heterogeneous graph benchmarks with target node attributes demonstrate that AGHINT outperforms the state-of-the-art. Copyright © 2024, The Authors. All rights reserved.

关键词： Graph neural networks

DomainDrop: Suppressing Domain-Sensitive Channels for Domain Generalization

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Guo, Jintao Qi, Lei Shi, Yinghuan State Key Laboratory for Novel Software Technology Nanjing University China National Institute of Healthcare Data Science Nanjing University China School of Computer Science and Engineering Southeast University Bangladesh

Deep Neural Networks have exhibited considerable success in various visual tasks. However, when applied to unseen test datasets, state-of-the-art models often suffer performance degradation due to domain shifts. In this paper, we introduce a novel approach for domain generalization from a novel perspective of enhancing the robustness of channels in feature maps to domain shifts. We observe that models trained on source domains contain a substantial number of channels that exhibit unstable activations across different domains, which are inclined to capture domain-specific features and behave abnormally when exposed to unseen target domains. To address the issue, we propose a DomainDrop framework to continuously enhance the channel robustness to domain shifts, where a domain discriminator is used to identify and drop unstable channels in feature maps of each network layer during forward propagation. We theoretically prove that our framework could effectively lower the generalization bound. Extensive experiments on several benchmarks indicate that our framework achieves state-of-the-art performance compared to other competing methods. Our code is available at https://***/lingeringlight/DomainDrop. Copyright © 2023, The Authors. All rights reserved.

关键词： Deep neural networks

Towards Exploratory Query Optimization for Template-Based Sql

学校读者我要写书评

暂无评论

SSRN

SSRN 2023年

作者： Feng, Jieming Li, Zhanhuai Chen, Qun School of Computer Science and Engineering Northwestern Polytechnical University Xi’an710072 China Key Laboratory of Big Data Storage and Management Northwestern Polytechnical University Ministry of Industry and Information Technology China

SQL query optimization aims to choose an optimal Query Execution Plan (QEP) for a query. The existing optimizers usually choose the plan with the minimal execution cost. However, in some real scenarios (e.g., cloud OLAP), it is a business imperative to minimize the cost of an entire workload. Unfortunately, the greedy optimizers are prone to generating execution plans that are only suboptimal from the workload perspective. In this paper, we propose a novel QEP optimization approach for template-based SQL that aims to minimize the execution cost of an entire workload instead of individual queries. While choosing an execution plan for a query, the proposed approach considers a plan's impact on future query execution as well as its own execution cost. We first define an exploratory metric, Plan Exploration Value (PEV), to measure a plan's potential benefit to future query execution. Then, we model exploratory plan selection as an optimization problem with cost constraints, and present an efficient algorithm based on dynamic programming for its solution. Finally, we evaluate the performance of the proposed approach by a comparative study on benchmark workloads. Our extensive experiments have shown that it generates more efficient workload execution plans than the existing alternatives. © 2023, The Authors. All rights reserved.

关键词： Dynamic programming

Electromagnetic Signature of Hilbert Curve-Based Chipless RFID Tags Using Numerical Analysis

学校读者我要写书评

暂无评论

Electromagnetic Signature of Hilbert Curve-Based Chipless RF...

Mediterrannean Microwave Symposium (MMS)

作者： Mohammad Nasrat Zaqumi Lotfi Ladhar Hatem Rmili Ali Lalbakhsh Mohammed Aseeri School of Engineering Macquarie University Sydney Australia Electrical and Computer Engineering King Abdulaziz University Jeddah Saudi Arabia School of Engineering Macquarie University School of Electrical and Data Engineering University of Technology Sydney (UTS) Sydney Australia King Abdulaziz City of Science and Technology (KACST) National Center for Telecommunications and Defense System Technologies (TDST) Riyadh Saudi Arabia

This study describes a chipless Radiofrequency Identification (RFID) tag that is based on the Hilbert Curve Filling technique. The traditional RFID has some security vulnerabilities, so an unauthorized party could obtain information. One alternative is to use fractal (irregular) shaped tags to store information as an electromagnetic signature. It is a chipless passive tag made of irregular unit cells and full-wave Electromagnetic analysis (EM) of the designed tags in Matlab is investigated by exporting them in computer Simulation Technology (CST) in the frequency range of 2 to 12 GHz. The performance of the tags is analyzed by observing the radar cross-section (RCS) of the tag in linear polarization, which was obtained for four iterations after the simulation.

关键词：