检索结果-内蒙古大学图书馆

arXiv 2024年

作者： Meng, Benyuan Xu, Qianqian Wang, Zitai Cao, Xiaochun Huang, Qingming Institute of Information Engineering CAS China School of Cyber Security University of Chinese Academy of Sciences China Key Lab. of Intelligent Information Processing Institute of Computing Technology CAS China Peng Cheng Laboratory China School of Cyber Science and Tech. Shenzhen Campus of Sun Yat-sen University China School of Computer Science and Tech. University of Chinese Academy of Sciences China Key Laboratory of Big Data Mining and Knowledge Management CAS China

Diffusion models are initially designed for image generation. Recent research shows that the internal signals within their backbones, named activations, can also serve as dense features for various discriminative tasks such as semantic segmentation. Given numerous activations, selecting a small yet effective subset poses a fundamental problem. To this end, the early study of this field performs a large-scale quantitative comparison of the discriminative ability of the activations. However, we find that many potential activations have not been evaluated, such as the queries and keys used to compute attention scores. Moreover, recent advancements in diffusion architectures bring many new activations, such as those within embedded ViT modules. Both combined, activation selection remains unresolved but overlooked. To tackle this issue, this paper takes a further step with a much broader range of activations evaluated. Considering the significant increase in activations, a full-scale quantitative comparison is no longer operational. Instead, we seek to understand the properties of these activations, such that the activations that are clearly inferior can be filtered out in advance via simple qualitative evaluation. After careful analysis, we discover three properties universal among diffusion models, enabling this study to go beyond specific models. On top of this, we present effective feature selection solutions for several popular diffusion models. Finally, the experiments across multiple discriminative tasks validate the superiority of our method over the SOTA competitors. Our code is available at this url. © 2024, CC BY.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Suppress Content Shift: Better Diffusion Features via Off-the-Shelf Generation Techniques

arXiv

引用

arXiv 2024年

作者： Meng, Benyuan Xu, Qianqian Wang, Zitai Yang, Zhiyong Cao, Xiaochun Huang, Qingming Institute of Information Engineering CAS China School of Cyber Security University of Chinese Academy of Sciences China Key Lab. of Intelligent Information Processing Institute of Computing Technology CAS China Peng Cheng Laboratory China School of Computer Science and Tech. University of Chinese Academy of Sciences China Key Laboratory of Big Data Mining and Knowledge Management CAS China School of Cyber Science and Tech. Sun Yat-sen University Shenzhen Campus China

Diffusion models are powerful generative models, and this capability can also be applied to discrimination. The inner activations of a pre-trained diffusion model can serve as features for discriminative tasks, namely, diffusion feature. We discover that diffusion feature has been hindered by a hidden yet universal phenomenon that we call content shift. To be specific, there are content differences between features and the input image, such as the exact shape of a certain object. We locate the cause of content shift as one inherent characteristic of diffusion models, which suggests the broad existence of this phenomenon in diffusion feature. Further empirical study also indicates that its negative impact is not negligible even when content shift is not visually perceivable. Hence, we propose to suppress content shift to enhance the overall quality of diffusion features. Specifically, content shift is related to the information drift during the process of recovering an image from the noisy input, pointing out the possibility of turning off-the-shelf generation techniques into tools for content shift suppression. We further propose a practical guideline named GATE to efficiently evaluate the potential benefit of a technique and provide an implementation of our methodology. Despite the simplicity, the proposed approach has achieved superior results on various tasks and datasets, validating its potential as a generic booster for diffusion features. Our code is available at this url. © 2024, CC BY.

关键词：

来源：评论

学校读者我要写书评

暂无评论

GenFace: A Large-Scale Fine-Grained Face Forgery Benchmark and Cross Appearance-Edge Learning

arXiv

引用

arXiv 2024年

作者： Zhang, Yaning Yu, Zitong Wang, Tianyi Huang, Xiaobin Shen, Linlin Gao, Zan Ren, Jianfeng Computer Vision Institute College of Computer Science and Software Engineering Shenzhen University Shenzhen518060 China School of Computing and Information Technology Great Bay University Dongguan523000 China National Engineering Laboratory for Big Data System Computing Technology Shenzhen University Shenzhen518060 China Nanyang Technological University 50 Nanyang Ave Block N 4 639798 Singapore Shenzhen Institute of Artificial Intelligence and Robotics for Society Shenzhen518129 China Guangdong Key Laboratory of Intelligent Information Processing Shenzhen University China Jinan250014 China Key Laboratory of Computer Vision and System Ministry of Education Tianjin University of Technology Tianjin300384 China School of Computer Science University of Nottingham Ningbo China

The rapid advancement of photorealistic generators has reached a critical juncture where the discrepancy between authentic and manipulated images is increasingly indistinguishable. Thus, benchmarking and advancing techniques detecting digital manipulation become an urgent issue. Although there have been a number of publicly available face forgery datasets, the forgery faces are mostly generated using GAN-based synthesis technology, which does not involve the most recent technologies like diffusion. The diversity and quality of images generated by diffusion models have been significantly improved and thus a much more challenging face forgery dataset shall be used to evaluate SOTA forgery detection literature. In this paper, we propose a large-scale, diverse, and fine-grained high-fidelity dataset, namely GenFace, to facilitate the advancement of deepfake detection, which contains a large number of forgery faces generated by advanced generators such as the diffusion-based model and more detailed labels about the manipulation approaches and adopted generators. In addition to evaluating SOTA approaches on our benchmark, we design an innovative Cross Appearance-Edge Learning (CAEL) detector to capture multi-grained appearance and edge global representations, and detect discriminative and general forgery traces. Moreover, we devise an Appearance-Edge Cross-Attention (AECA) module to explore the various integrations across two domains. Extensive experiment results and visualizations show that our detection model outperforms the state of the arts on different settings like cross-generator, cross-forgery, and cross-dataset evaluations. Code and datasets will be available at https://***/Jenine-321/GenFace. Copyright © 2024, The Authors. All rights reserved.

关键词： Image enhancement

来源：评论

学校读者我要写书评

暂无评论

CodeEnhance: A Codebook-Driven Approach for Low-Light Image Enhancement

arXiv

引用

arXiv 2024年

作者： Wu, Xu Hou, XianXu Lai, Zhihui Zhou, Jie Zhang, Ya-Nan Pedrycz, Witold Shen, Linlin The Computer Vision Institute College of Computer Science and Software Engineering Shenzhen University Shenzhen518060 China Shenzhen Institute of Artificial Intelligence and Robotics for Society Shenzhen518060 China Guangdong Key Laboratory of Intelligent Information Processing Shenzhen University Shenzhen518060 China School of AI and Advanced Computing Xi’an Jiaotong-Liverpool University China National Engineering Laboratory for Big Data System Computing Technology Shenzhen University SZU Branch Shenzhen Institute of Artificial Intelligence and Robotics for Society Guangdong Shenzhen518060 China The Department of Electrical & Computer Engineering University of Alberta University of Alberta Canada

Low-light image enhancement (LLIE) aims to improve low-illumination images. However, existing methods face two challenges: (1) uncertainty in restoration from diverse brightness degradations;(2) loss of texture and color information caused by noise suppression and light enhancement. In this paper, we propose a novel enhancement approach, CodeEnhance, by leveraging quantized priors and image refinement to address these challenges. In particular, we reframe LLIE as learning an image-to-code mapping from low-light images to discrete codebook, which has been learned from high-quality images. To enhance this process, a Semantic Embedding Module (SEM) is introduced to integrate semantic information with low-level features, and a Codebook Shift (CS) mechanism, designed to adapt the pre-learned codebook to better suit the distinct characteristics of our low-light dataset. Additionally, we present an Interactive Feature Transformation (IFT) module to refine texture and color information during image reconstruction, allowing for interactive enhancement based on user preferences. Extensive experiments on both real-world and synthetic benchmarks demonstrate that the incorporation of prior knowledge and controllable information transfer significantly enhances LLIE performance in terms of quality and fidelity. The proposed CodeEnhance exhibits superior robustness to various degradations, including uneven illumination, noise, and color distortion. Copyright © 2024, The Authors. All rights reserved.

关键词： Image enhancement

来源：评论

学校读者我要写书评

暂无评论

Sequential Manipulation Against Rank Aggregation: Theory and Algorithm

arXiv

引用

arXiv 2024年

作者： Ma, Ke Xu, Qianqian Zeng, Jinshan Liu, Wei Cao, Xiaochun Sun, Yingfei Huang, Qingming The School of Electronic Electrical and Communication Engineering University of Chinese Academy of Sciences Beijing100049 China The Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences Beijing100190 China The School of Computer and Information Engineering Jiangxi Normal University Jiangxi Nanchang330022 China The Tencent Data Platform Shenzhen518054 China The School of Cyber Science and Technology Shenzhen Campus of Sun Yat-Sen University Shenzhen518107 China The School of Computer Science and Technology University of Chinese Academy of Sciences Beijing100049 China University of Chinese Academy of Sciences Beijing100049 China

Rank aggregation with pairwise comparisons is widely encountered in sociology, politics, economics, psychology, sports, etc. Given the enormous social impact and the consequent incentives, the potential adversary has a strong motivation to manipulate the ranking list. However, the ideal attack opportunity and the excessive adversarial capability cause the existing methods to be impractical. To fully explore the potential risks, we leverage an online attack on the vulnerable data collection process. Since it is independent of rank aggregation and lacks effective protection mechanisms, we disrupt the data collection process by fabricating pairwise comparisons without knowledge of the future data or the true distribution. From the game-theoretic perspective, the confrontation scenario between the online manipulator and the ranker who takes control of the original data source is formulated as a distributionally robust game that deals with the uncertainty of knowledge. Then we demonstrate that the equilibrium in the above game is potentially favorable to the adversary by analyzing the vulnerability of the sampling algorithms such as Bernoulli and reservoir methods. According to the above theoretical analysis, different sequential manipulation policies are proposed under a Bayesian decision framework and a large class of parametric pairwise comparison models. For attackers with complete knowledge, we establish the asymptotic optimality of the proposed policies. To increase the success rate of the sequential manipulation with incomplete knowledge, a distributionally robust estimator, which replaces the maximum likelihood estimation in a saddle point problem, provides a conservative data generation solution. Finally, the corroborating empirical evidence shows that the proposed method manipulates the results of rank aggregation methods in a sequential manner. © 2024, CC BY.

关键词： Maximum likelihood estimation

来源：评论

学校读者我要写书评

暂无评论

CLSDRL:A routing optimization method for traffic feature extraction

CLSDRL:A routing optimization method for traffic feature ext...

引用

International Conference on Networking and Network Applications (NaNA)

作者： Hong Xia Jianguo Li Yanping Chen Ning Lv ZhongMin Wang Qingyi Dong School of Computer Science and Technology Xi’an University of Posts and Telecommunications Xi’an Shaanxi China Shaanxi Key Laboratory of Network Data Analysis and Intelligent Processing Xi’an Shaanxi China Xi’an Key Laboratory of Big Data and Intelligent Computing Xi’an Shaanxi China

In order to solve the impact of the temporal and spatial characteristics of traffic on network routing optimization, this paper proposes convolution long-short memory neural network deep reinforcement learning (CLSDRL) model for routing optimization. The CLSDRL model consists of deep deterministic policy gradients (DDPG) deep couple with convolution neural network (CNN) and long-short memory neural network (LSTM). After extracting the spatial and temporal characteristics of network traffic with CNN and LSTM, routing decisions are made with DDPG algorithm. Experiments are conducted under different load intensities, and the network performance is evaluated by the average network delay and packet loss rate, experimental results show that this method can improve significantly network performance.

关键词： Training Convolution Neural networks Optimization methods Packet loss Reinforcement learning Telecommunication traffic

来源：评论

学校读者我要写书评

暂无评论

Copula Guided Parallel Gibbs Sampling for Nonparametric and Coherent Topic Discovery (Extended Abstract)

Copula Guided Parallel Gibbs Sampling for Nonparametric and ...

引用

International Conference on data Engineering

作者： Lihui Lin Yanghui Rao Haoran Xie Raymond Y. K. Lau Jian Yin Fu Lee Wang Qing Li School of Computer Science and Engineering Sun Yat-sen University Guangzhou China Department of Computing and Decision Sciences Lingnan University New Territories Hong Kong SAR Department of Information Systems City University of Hong Kong Kowloon Hong Kong SAR Guangdong Key Laboratory of Big Data Analysis and Processing Sun Yat-sen University Guangzhou China School of Science and Technology Hong Kong Metropolitan University Kowloon Hong Kong SAR Department of Computing The Hong Kong Polytechnic University Kowloon Hong Kong SAR

In terms of the generative process, the Gamma-Gamma-Poisson Process (G2PP) is equivalent to the nonparametric topic model of Hierarchical Dirichlet Process (HDP). Considering the high computational cost of estimating parameters in HDP, a parallel G2PP was developed to generate topics efficiently via multi-threading. Unfortunately, the above model needs to predefine the number of topics. To address this issue, we first propose a Topic Self-Adaptive Model (TSAM) for nonparametric and parallel topic discovery. In TSAM, a monitor-executor mechanism is developed to manage the global topic information using a hierarchical structure of threads. Based on the apparatus of copulas, we further extend our TSAM to TSAMcop for coherent topic modeling by exploiting a copula guided parallel Gibbs sampling algorithm. Extensive experiments validate the effectiveness of both TSAM and TSAMcop.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Edge computing-enabled energy efficiency prediction of immersion cooling system for supercomputing centers

Cleaner Engineering and Technology

引用

Cleaner Engineering and technology 2025年 27卷

作者： Ma, Shuaiyin Cao, Yichun Liu, Yang School of Computer Science and Technology Xi'an University of Posts and Telecommunications Xi'an 710121 China Shaanxi Key Laboratory of Network Data Analysis and Intelligent Processing Xi'an University of Posts and Telecommunications Xi'an 710121 China Xi'an Key Laboratory of Big Data and Intelligent Computing Xi'an 710121 China Shaanxi Union Research Centre of University and Enterprise for 5G+ Industrial Internet Communication Terminal Technology Xi'an University of Posts and Telecommunications Xi'an 710121 China Department of Management and Engineering Linköping University Linköping SE-581 83 Sweden Industrial Engineering and Management University of Oulu Oulu 90570 Finland

Within the context of cleaner production, enhancing energy efficiency and sustainability has emerged as a central focus in supercomputing center development. To address the challenges in predicting energy consumption, this study proposes an architecture of edge computing-enabled energy efficiency prediction of immersion cooling system for supercomputing centers. This architecture combines time-series generative adversarial network (TimeGAN) for data augmentation with the neural basis expansion analysis for time series (N-BEATS) for prediction, providing a robust solution for accurate energy consumption prediction. TimeGAN enhances the training dataset by generating high-quality synthetic time-series data, effectively mitigating issues of data sparsity and imbalance. N-BEATS, with its modular architecture and strong adaptability to temporal data, ensures precise predictions by capturing both global trends and local variations in energy usage. Experimental results demonstrate the effectiveness of the proposed architecture, exhibiting superior performance across key metrics when compared to traditional models. Specifically, the RMSE of TimeGAN-N-BEATS reduced by more than 8 %, the MSE decreased by over 18 %, and the R² reached 97.31 %, outperforming baseline models such as long short-term memory and gated recurrent unit, and their attention-enhanced variants. This study highlights the potential of integrating generative and predictive models to optimize energy efficiency in liquid cooling systems, offering valuable insights for sustainable supercomputing operations. © 2025 The Authors

关键词： Edge computing Liquid cooling system N-BEATS Supercomputing centers TimeGAN

来源：评论

学校读者我要写书评

暂无评论

Fully Synthetic Videos and Random Background-Pasting Method for Flame Segmentation

SSRN

引用

SSRN 2022年

作者： Jia, Yang Zhang, Xinmeng Kuang, Yaxi Chen, Yanping Wang, Gang Zhang, Qixing School of Computer Science Xi'an University of Posts and Telecommunications 710121 China Shaanxi Key Laboratory of Network Data Intelligent Processing Xi'an University of Posts and Telecommunications 710121 China Xi'an Key Laboratory of Big Data and Intelligent Computing Xi'an University of Posts and Telecommunications 710121 China School of Information Science and Technology University of Science and Technology of China 230026 China XNIF262 710061 China State Key Laboratory of Fire Science University of Science and Technology of China 230026 China

Video-based flame detection (VFD) aims to recognize fire events by the image features. Flame segmentation is an essential task in VFD, which provides suspected regions for feature analysis and object recognition. The development of deep learning has promoted VFD performances to a higher level. However, due to the rarity of recorded fire events, it is challenging to get tremendous positive flame samples for model training. Existing deep learning-based VFD methods are limited to the lack of flame samples under different scenarios. In this paper, we propose an assumption that we can train a segmentation model with virtual flame images and design experiments to prove it. We take many virtual flame videos to extend existing flame datasets, which provide adequate flame samples for deep learning-based VFD methods. We also take a random background-pasting method to distribute the flame images among different scenarios. The proposed method trains a flame segmentation model with zero real flame image. Moreover, we perform segmentation testing with real flame images, which the model has never touched, to see if the model trained with ‘fake’ images can segment real objects. We trained four segmentation models based on FCN, U-Net, Deeplabv3, and Mask-RCNN with synthetic flame video frames, and obtained the highest mPA of 0.783 and mIoU of 0.515. The experimental results on FIRE-SMOKE-dataSET and Fire-Detection-Image-dataset demonstrate that the ‘fake’ flame samples generated by the proposed random background-pasting method can improve the performances of existing state-of-the-art flame segmentation methods obviously on cross-dataset evaluation settings. © 2022, The Authors. All rights reserved.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

SASA-Net: A spatial-aware self-attention mechanism for building protein 3D structure directly from inter-residue distances

SASA-Net: A spatial-aware self-attention mechanism for build...

引用

IEEE International Conference on Bioinformatics and Biomedicine (BIBM)

作者： Tiansu Gong Fusong Ju Shiwei Sun Dongbo Bu Chinese Academy of Sciences Key Lab of Intelligent Information Processing Institute of Computing Technology Beijing China University of Chinese Academy of Sciences Beijing China Zhongke Big Data Academy Zhengzhou Henan China

ISBN: (纸本)9781665429825

Protein structure prediction has achieved considerable progresses mainly due to the increased accuracy of inter-residue distance estimation and the application of deep learning *** of the distance-based ab initio prediction approaches adopt a two-step diagram: constructing a potential function based on the estimated inter-residue distances, and then build a 3D structure that minimizes the potential function. These approaches have proven very promising; however, they still suffer from several limitations, especially the inaccuracies incurred by the handcrafted potential ***, we present SASA-Net, a deep learning-based approach that directly learns protein 3D structure from the estimated inter-residue distances. Unlike the existing approach simply representing protein structures as coordinates of atoms, SASA-Net represents protein structures using pose of residues, i.e., the coordinate system of each individual residue in which all backbone atoms of this residue are fixed. The key element of SASA-Net is a spatial-aware self-attention mechanism, which is able to adjust a residue’s pose according to all other residues’ features and the estimated distances between residues. By iteratively applying the spatial-aware self-attention mechanism, SASA-Net continuously improves the structure and finally acquires a structure with high accuracy. Using the CATH35 proteins as representatives, we demonstrate that SASA-Net is able to accurately and efficiently build structures from the estimated inter-residue distances. The high accuracy and efficiency of SASA-Net enables an end-to-end neural network model for protein structure prediction through combining SASA-Net and an neural network for inter-residue distance prediction. Source code of SASA-Net is available at https://*** gongtiansu/SASA-Net/

关键词： Proteins Deep learning Protein engineering Solid modeling Three-dimensional displays Conferences Neural networks

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：