检索结果-内蒙古大学图书馆

A Norm Regularization Training Strategy for Robust Image Quality Assessment Models

International Journal of computer Vision 2025年 1-15页

作者： Liu, Yujia Yang, Chenxi Li, Dingquan Jiang, Tingting Huang, Tiejun School of Computer Science Peking University Beijing China National Key Laboratory for Multimedia Information Processing Peking University Beijing China National Engineering Research Center of Visual Technology Peking University Beijing China School of Mathematical Sciences Peking University Beijing China Department of Networked Intelligence Pengcheng Laboratory Shenzhen China

Image Quality Assessment (IQA) models predict the quality score of input images. They can be categorized into Full-Reference (FR-) and No-Reference (NR-) IQA models based on the availability of reference images. These models are essential for performance evaluation and optimization guidance in the media industry. However, researchers have observed that introducing imperceptible perturbations to input images can notably influence the predicted scores of both FR- and NR-IQA models, resulting in inaccurate assessments of image quality. This phenomenon is known as adversarial attacks. In this paper, we initially define attacks targeted at both FR-IQA and NR-IQA models. Subsequently, we introduce a defense approach applicable to both types of models, aimed at enhancing the stability of predicted scores and boosting the adversarial robustness of IQA models. To be specific, we present theoretical evidence showing that the magnitude of score changes is related to the $$\ell _1$$ norm of the model’s gradient with respect to the input image. Building upon this theoretical foundation, we propose a norm regularization training strategy aimed at reducing the $$\ell _1$$ norm of the gradient, thereby boosting the robustness of IQA models. Experiments conducted on three FR-IQA and four NR-IQA models demonstrate the effectiveness of our strategy in reducing score changes in the presence of adversarial attacks. To the best of our knowledge, this work marks the first attempt to defend against adversarial attacks on both FR- and NR-IQA models. Our study offers valuable insights into the adversarial robustness of IQA models and provides a foundation for future research in this area.

关键词：

来源：评论

学校读者我要写书评

暂无评论

D4M: Dataset Distillation via Disentangled Diffusion Model

D4M: Dataset Distillation via Disentangled Diffusion Model

引用

Conference on computer Vision and Pattern Recognition (CVPR)

作者： Duo Su Junjie Hou Weizhi Gao Yingjie Tian Bowen Tang UCAS School of Computer Science and Technology Research Center on Fictitious Economy and Data Science CAS Key Laboratory of Big Data Mining and Knowledge Management CAS UCAS Sino-Danish College Department of Computer Science NCSU UCAS School of Economics and Management UCAS MOE Social Science Laboratory of Digital Economic Forecasts and Policy Simulation CAS Institute of Computing Technology

ISBN: (数字)9798350353006

ISBN: (纸本)9798350353013

Dataset distillation offers a lightweight synthetic dataset for fast network training with promising test accuracy. To imitate the performance of the original dataset, most approaches employ bi-level optimization and the distillation space relies on the matching architecture. Nevertheless, these approaches either suffer significant computational costs on large-scale datasets or experience performance decline on cross-architectures. We advocate for designing an economical dataset distillation framework that is independent of the matching architectures. With empirical observations, we argue that constraining the consistency of the real and synthetic image spaces will enhance the cross-architecture generalization. Motivated by this, we introduce Dataset Distillation via Disentangled Diffusion Model (D 4 M), an efficient framework for dataset distillation. Compared to architecture-dependent methods, D 4 M employs latent diffusion model to guarantee consistency and incorporates label information into category prototypes. The distilled datasets are versatile, eliminating the need for repeated generation of distinct datasets for various architectures. Through comprehensive experiments, D4M demonstrates superior performance and robust generalization, surpassing the SOTA methods across most aspects.

关键词： Training computer vision Computational modeling Prototypes computer architecture Diffusion models Pattern recognition

来源：评论

学校读者我要写书评

暂无评论

Optimizing Multi-DNN Inference on Mobile Devices through Heterogeneous Processor Co-Execution

arXiv

引用

arXiv 2025年

作者： Gao, Yunquan Zhang, Zhiguo Donta, Praveen Kumar Dehury, Chinmaya Kumar Wang, Xiujun Niyato, Dusit Zhang, Qiyang School of Computer Science and Technology Anhui Engineering Research Center for Intelligent Applications and Security of Industrial Internet Anhui University of Technology Anhui Ma’anshan243032 China Computer Science and Technology Anhui University of Technology Anhui Ma’anshan243032 China Department of Computer and Systems Sciences Stockholm University Stockholm106 91 Sweden Institute of Computer Science University of Tartu IISER Berhampur India College of Computing and Data Science Nanyang Technological University Singapore639798 Singapore Computer Science School Peking University Beijing100876 China

Deep Neural Networks (DNNs) are increasingly deployed across diverse industries, driving a growing demand to enable their capabilities on mobile devices. However, existing mobile inference frameworks are often rely on a single processor to handle each model’s inference, limiting hardware utilization and leading to suboptimal performance and energy efficiency. Expanding DNNs accessibility on mobile platforms requires more adaptive and resource-efficient solutions to meet increasing computational demands without compromising device functionality. Nevertheless, parallel inference of multiple DNNs on heterogeneous processors remains a significant challenge. Several works have explored partitioning DNN operations into subgraphs to enable parallel execution across heterogeneous processors. However, these approaches typically generate excessive subgraphs based solely on hardware compatibility, increasing scheduling complexity and memory management overhead. To address these limitations, we propose an Advanced Multi-DNN Model Scheduling (ADMS) strategy that optimizes multi-DNN inference across heterogeneous processors on mobile devices. ADMS constructs an optimal subgraph partitioning strategy offline, considering both hardware support of operations and scheduling granularity, while employing a processor-state-aware scheduling algorithm that dynamically balances workloads based on real-time operational conditions. This ensures efficient workload distribution and maximizes the utilization of available processors. Experimental results show that, compared to vanilla inference frameworks, ADMS reduced multi-DNN inference latency by 4.04×.MSC Codes 68T07, 68W40 Copyright © 2025, The Authors. All rights reserved.

关键词： Parallel processing systems

来源：评论

学校读者我要写书评

暂无评论

Improving Model's Focus Improves Performance of Deep Learning-Based Synthetic Face Detectors

arXiv

引用

arXiv 2023年

作者： Piland, Jacob Czajka, Adam Sweet, Christopher Department of Computer Science and Engineering University of Notre Dame Notre DameIN46556 United States Center for Research Computing University of Notre Dame Notre DameIN46556 United States

Deep learning-based models generalize better to unknown data samples after being guided "where to look" by incorporating human perception into training strategies. We made an observation that the entropy of the model's salience trained in that way is lower when compared to salience entropy computed for models training without human perceptual intelligence. Thus the question: does further increase of model's focus, by lowering the entropy of model's class activation map, help in further increasing the performance? In this paper we propose and evaluate several entropy-based new loss function components controlling the model's focus, covering the full range of the level of such control, from none to its "aggresive" minimization. We show, using a problem of synthetic face detection, that improving the model's focus, through lowering entropy, leads to models that perform better in an open-set scenario, in which the test samples are synthesized by unknown generative models. We also show that optimal performance is obtained when the model's loss function blends three aspects: regular classification, low-entropy of the model's focus, and human-guided saliency. Copyright © 2023, The Authors. All rights reserved.

关键词： Entropy

来源：评论

学校读者我要写书评

暂无评论

SSFlowNet: Semi-supervised Scene Flow Estimation On Point Clouds With Pseudo Label

arXiv

引用

arXiv 2023年

作者： Chen, Jingze Yao, Junfeng Lin, Qiqin Zhou, Rongzhou Li, Lei Center for Digital Media Computing School of Film School of Informatics Xiamen University China Institute of Artificial Intelligence Xiamen University China Department of Computer Science University of Copenhagen Denmark

In the domain of supervised scene flow estimation, the process of manual labeling is both time-intensive and financially demanding. This paper introduces SSFlowNet, a semi-supervised approach for scene flow estimation, that utilizes a blend of labeled and unlabeled data, optimizing the balance between the cost of labeling and the precision of model training. SSFlowNet stands out through its innovative use of pseudo-labels, mainly reducing the dependency on extensively labeled datasets while maintaining high model accuracy. The core of our model is its emphasis on the intricate geometric structures of point clouds, both locally and globally, coupled with a novel spatial memory feature. This feature is adept at learning the geometric relationships between points over sequential time frames. By identifying similarities between labeled and unlabeled points, SSFlowNet dynamically constructs a correlation matrix to evaluate scene flow dependencies at individual points level. Furthermore, the integration of a flow consistency module within SSFlowNet enhances its capability to consistently estimate flow, an essential aspect for analyzing dynamic scenes. Empirical results demonstrate that SSFlowNet surpasses existing methods in pseudo-label generation and shows adaptability across varying data volumes. Moreover, our semi-supervised training technique yields promising outcomes even with different smaller ratio labeled data, marking a substantial advancement in the field of scene flow estimation. Copyright © 2023, The Authors. All rights reserved.

关键词： Machine learning

来源：评论

学校读者我要写书评

暂无评论

ScoreHypo: Probabilistic Human Mesh Estimation with Hypothesis Scoring

ScoreHypo: Probabilistic Human Mesh Estimation with Hypothes...

引用

Conference on computer Vision and Pattern Recognition (CVPR)

作者： Yuan Xu Xiaoxuan Ma Jiajun Su Wentao Zhu Yu Qiao Yizhou Wang Center on Frontiers of Computing Studies School of Computer Science Peking University International Digital Economy Academy (IDEA) School of Electronic Information and Electrical Engineering Shanghai Jiao Tong University Inst. for Artificial Intelligence Peking University Nat'1 Eng. Research Center of Visual Technology Nat'1 Key Lab of General Artificial Intelligence

ISBN: (数字)9798350353006

ISBN: (纸本)9798350353013

Monocular 3D human mesh estimation is an ill-posed problem, characterized by inherent ambiguity and occlusion. While recent probabilistic methods propose generating multiple solutions, little attention is paid to obtaining high-quality estimates from them. To address this limitation, we introduce ScoreHypo, a versatile framework by first leveraging our novel HypoNet to generate multiple hy-potheses, followed by employing a meticulously designed scorer, ScoreNet, to evaluate and select high-quality esti-mates. ScoreHypo formulates the estimation process as a re-verse denoising process, where HypoNet produces a diverse set of plausible estimates that effectively align with the im-age cues. Subsequently, ScoreNet is employed to rigorously evaluate and rank these estimates based on their quality and finally identify superior ones. Experimental results demon-strate that HypoNet outperforms existing state-of-the-art probabilistic methods as a multi-hypothesis mesh estimator. Moreover, the estimates selected by ScoreNet significantly outperform random generation or simple averaging. Notably, the trained ScoreNet exhibits generalizability, as it can effectively score existing methods and significantly reduce their errors by more than 15%. Code and models are available at ht tps: / /xy02- 05. gi thub. io/ScoreHypo.

关键词： computer vision Three-dimensional displays Accuracy Codes Noise reduction Estimation Benchmark testing

来源：评论

学校读者我要写书评

暂无评论

DELTA: AN ONLINE DOCUMENT-LEVEL TRANSLATION AGENT BASED ON MULTI-LEVEL MEMORY

arXiv

引用

arXiv 2024年

作者： Wang, Yutong Zeng, Jiali Liu, Xuebo Wong, Derek F. Meng, Fandong Zhou, Jie Zhang, Min Institute of Computing and Intelligence Harbin Institute of Technology Shenzhen China Pattern Recognition Center WeChat AI Tencent Inc China NLP2CT Lab Department of Computer and Information Science University of Macau China

Large language models (LLMs) have achieved reasonable quality improvements in machine translation (MT). However, most current research on MT-LLMs still faces significant challenges in maintaining translation consistency and accuracy when processing entire documents. In this paper, we introduce DELTA, a Document-levEL Translation Agent designed to overcome these limitations. DELTA features a multi-level memory structure that stores information across various granularities and spans, including Proper Noun Records, Bilingual Summary, Long-Term Memory, and Short-Term Memory, which are continuously retrieved and updated by auxiliary LLM-based components. Experimental results indicate that DELTA significantly outperforms strong baselines in terms of translation consistency and quality across four open/closed-source LLMs and two representative document translation datasets, achieving an increase in consistency scores by up to 4.58 percentage points and in COMET scores by up to 3.16 points on average. DELTA employs a sentence-by-sentence translation strategy, ensuring no sentence omissions and offering a memory-efficient solution compared to the mainstream method. Furthermore, DELTA improves pronoun and context-dependent translation accuracy, and the summary component of the agent also shows promise as a tool for query-based summarization tasks. The code and data of our approach are released at https://***/YutongWang1216/DocMTAgent. © 2024, CC BY.

关键词： computer aided language translation

来源：评论

学校读者我要写书评

暂无评论

Gaussian Kernel Variance For an Adaptive Learning Method on Signals Over Graphs

arXiv

引用

arXiv 2022年

作者： Zhao, Yue Ayanoglu, Ender Center for Pervasive Computing and Communications Department of Electrical Engineering and Computer Science University of California Irvine IrvineCA United States

This paper discusses a special kind of a simple yet possibly powerful algorithm, called single-kernel Gradraker (SKG), which is an adaptive learning method predicting unknown nodal values in a network using known nodal values and the network structure. We aim to find out how to configure the special kind of the model in applying the algorithm. To be more specific, we focus on SKG with a Gaussian kernel and specify how to find a suitable variance for the kernel. To do so, we introduce two variables with which we are able to set up requirements on the variance of the Gaussian kernel to achieve (near-) optimal performance and can better understand how SKG works. Our contribution is that we introduce two variables as analysis tools, illustrate how predictions will be affected under different Gaussian kernels, and provide an algorithm finding a suitable Gaussian kernel for SKG with knowledge about the training network. Simulation results on real datasets are provided. © 2022, CC BY.

关键词： Gaussian distribution

来源：评论

学校读者我要写书评

暂无评论

Quantum Algorithms for Sampling Log-Concave Distributions and Estimating Normalizing Constants

arXiv

引用

arXiv 2022年

作者： Childs, Andrew M. Li, Tongyang Liu, Jin-Peng Wang, Chunhao Zhang, Ruizhe Joint Center for Quantum Information and Computer Science Department of Computer Science Institute for Advanced Computer Studies University of Maryland United States Center on Frontiers of Computing Studies School of Computer Science Peking University China Simons Institute Department of Mathematics UC Berkeley United States Department of Computer Science and Engineering Pennsylvania State University United States Department of Computer Science The University of Texas Austin United States

Given a convex function f: Rd → R, the problem of sampling from a distribution ∝ e−f (x) is called log-concave sampling. This task has wide applications in machine learning, physics, statistics, etc. In this work, we develop quantum algorithms for sampling log-concave distributions and for estimating their normalizing constants (Equation presented). First, we use underdamped Langevin diffusion to develop quantum algorithms that match the query complexity (in terms of the condition number κ and dimension d) of analogous classical algorithms that use gradient (first-order) queries, even though the quantum algorithms use only evaluation (zeroth-order) queries. For estimating normalizing constants, these algorithms also achieve quadratic speedup in the multiplicative error ∊. Second, we develop quantum Metropolis-adjusted Langevin algorithms with query complexity (Equation presented) and (Equation presented) for log-concave sampling and normalizing constant estimation, respectively, achieving polynomial speedups in κ, d, ∊ over the best known classical algorithms by exploiting quantum analogs of the Monte Carlo method and quantum walks. We also prove a 1/∊1−o(1) quantum lower bound for estimating normalizing constants, implying near-optimality of our quantum algorithms in ǫ. Copyright © 2022, The Authors. All rights reserved.

关键词： Monte Carlo methods

来源：评论

学校读者我要写书评

暂无评论

Empowering Donors: How Blockchain Technology Can Help Ensure Their Contributions Reach the Right Recipients

Empowering Donors: How Blockchain Technology Can Help Ensure...

引用

Business Analytics for Technology and Security (ICBATS), International Conference on

作者： Sahar Ajmal Muteeb Bin Muzammil Muhammad Shoaib Muhammad Hassaan Mehmood Department of Software Engineering National University of Computer and Emmerging Sciences Chiniot-Faisalabad Pakistan College of Computing Riphah International University Faisalabad Pakistan Department of Computer Science University of Engineering and Technology Lahore Pakistan School of Computer Science NCBA&E Lahore Pakistan Applied School Research Center Applied Science Private University Amman Jordan

Charity giving is a fundamental aspect of society, but there are concerns about the accountability and transparency of the donation process. Blockchain technology has emerged as a potential solution, offering a secure and auditable platform for managing charitable contributions. In this paper, we explore the concept of empowering donors through blockchain technology and examine how it can help ensure that contributions reach the right recipients. We review existing literature on the topic and identify key areas for future research, including the development of hybrid blockchain solutions along with the implementation of novel consensus mechanisms. Moreover, providing the idea of decentralized autonomous organizations, self-executing smart contracts, and integration of blockchain with artificial intelligence and Internet of things. By providing a comprehensive overview of the current state of the field and outlining a roadmap for future research, we hope to stimulate further exploration of the potential of blockchain technology to revolutionize charity giving, and create a more accountable and transparent system for managing charitable funds. Some research questions are designed for each novel idea. Our analysis suggests that blockchain has the potential to empower donors and ensure that their contributions make a positive impact in the world, but further research is needed to fully realize its potential.

关键词： Decentralized autonomous organization Smart contracts Transforms Blockchains Consensus protocol Internet of Things Security

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：