检索结果-内蒙古大学图书馆

IEEE Transactions on Intelligent Vehicles 2024年 1-12页

作者： Li, Jinlong Xu, Runsheng Liu, Xinyu Ma, Jin Li, Baolu Zou, Qin Ma, Jiaqi Yu, Hongkai Department of Computer Science Cleveland State University Cleveland OH USA Department of Civil and Environmental Engineering University of California Los Angeles CA USA Department of Electrical and Computer Engineering Cleveland State University Cleveland OH USA School of Computer Science Wuhan University Wuhan China

Typically, object detection methods for autonomous driving that rely on supervised learning make the assumption of a consistent feature distribution between the training and testing data, this such assumption may fail in different weather conditions. Due to the domain gap, a detection model trained under clear weather may not perform well in foggy and rainy conditions. Overcoming detection bottlenecks in foggy and rainy weather is a real challenge for autonomous vehicles deployed in the wild. To bridge the domain gap and improve the performance of object detection in foggy and rainy weather, this paper presents a novel framework for domain-adaptive object detection. The adaptations at both the image-level and objectlevel are intended to minimize the differences in image style and object appearance between domains. Furthermore, in order to improve the model's performance on challenging examples, we introduce a novel adversarial gradient reversal layer that conducts adversarial mining on difficult instances in addition to domain adaptation. Additionally, we suggest generating an auxiliary domain through data augmentation to enforce a new domain-level metric regularization. Experimental findings on public V2V benchmark exhibit a substantial enhancement in object detection specifically for foggy and rainy driving scenarios IEEE

关键词： Feature extraction

来源：评论

学校读者我要写书评

暂无评论

MindScore: quantifying human preference for text-to-image generation through multi-view lens

引用

science China(Information sciences) 2025年第6期68卷 72-85页

作者： Yiqi TONG Jiarui ZHANG Shaohang WEI Wei GUO Fuzhen ZHUANG Deqing WANG Xi YANG Richeng XUAN School of Artificial Intelligence Beihang University School of Computer Science and Engineering Beihang University Department of Computer Science and Engineering Shanghai Jiao Tong University School of Computer Science Peking University State Key Laboratory of Complex & Critical Software Environment Beihang University Beijing Academy of Artificial Intelligence

Understanding and quantifying the capabilities of foundation models, particularly in text-to-image(T2I) generation, is crucial for verifying their alignment with human expectations and practical requirements. However, evaluating T2I foundation models presents significant challenges due to the complex, multi-dimensional psychological factors that influence human preferences for generated images. In this work, we propose MindScore, a multi-view framework for assessing the generation capacity of T2I models through the lens of human preference. Specifically, MindScore decomposes the evaluation into four complementary modules that align with human cognitive processing of images: matching, faithfulness, quality,and realness. The matching module quantifies the semantic alignment between generated images and prompt text, while the faithfulness module measures how accurately the images reflect specific prompt details. Furthermore, we incorporate quality and realness modules to capture deeper psychological preferences, recognizing that unpleasant or distorted images often trigger adverse human responses. Extensive experiments on three T2I datasets with human preference annotations clearly validate the superiority of our proposed MindScore over various state-of-the-art baselines. Our case studies further reveal that MindScore offers valuable insights into T2I generation from a human-centric perspective.

关键词： text-to-image generation foundation models human preference evaluation multi-view assessment language and vision

来源：评论

学校读者我要写书评

暂无评论

Optimal Codes Correcting a Substring Edit

引用

IEEE Transactions on Information Theory 2025年第7期71卷 5178-5191页

作者： Li, Yuting Tang, Yuanyuan Lou, Hao Gabrys, Ryan Farnoud, Farzad University of Virginia Department of Computer Science United States University of Virginia Department of Electrical and Computer Engineering United States Calit2 University of California-San Diego United States University of Virginia Department of Electrical and Computer Engineering Department of Computer Science United States

The substring edit error replaces a substring u of x with another string v, where the lengths of u and v are bounded by a given constant k. It encompasses localized insertions, deletions, and substitutions within a window. Codes correcting one substring edit have redundancy at least log n + k. In this paper, we construct codes correcting one substring edit with redundancy log n + Ok(log log n), which is almost optimal. We also study the average-case document-exchange problem under one substring edit and construct a hash with an expected length of approximately 2 log n + Ok(log log n) for any iid distribution for the documents. © 1963-2012 IEEE.

关键词： Redundancy

来源：评论

学校读者我要写书评

暂无评论

Wide field of view large aperture meta-doublet eyepiece

引用

Light(science & Applications) 2025年第1期14卷 167-176页

作者： Anna Wirth-Singh Johannes E.Fröch Fan Yang Louis Martin Hanyu Zheng Hualiang Zhang Quentin T.Tanguy Zhihao Zhou Luocheng Huang Demis DJohn Biljana Stamenic Juejun Hu Tian Gu Arka Majumdar Department of Physics University of WashingtonSeattleWAUSA Department of Electrical and Computer Engineering University of WashingtonSeattleWAUSA Department of Materials Science and Engineering Massachusetts Institute of TechnologyCambridgeMAUSA Department of Electrical and Computer Engineering University of MassachusettsLowellMAUSA Department of Electrical and Computer Engineering University of CaliforniaSanta BarbaraCAUSA

Wide field of view and light weight optics are critical for advanced eyewear,with applications in augmented/virtual reality and night *** refractive lenses are often stacked to correct aberrations at a wide field of view,leading to limited performance and increased size and *** particular,simultaneously achieving a wide field of view and large aperture for light collection is desirable but challenging to realize in a compact ***,we demonstrate a wide field of view(greater than 60°)meta-optic doublet eyepiece with an entrance aperture of 2.1 *** the design wavelength of 633 nm,the meta-optic doublet achieves comparable performance to a refractive lens-based eyepiece *** meta-doublet eyepiece illustrates the potential for meta-optics to play an important role in the development of high-quality monochrome near-eye displays and night vision systems.

关键词： optics refractive illustrate

来源：评论

学校读者我要写书评

暂无评论

BrandCrafter AI, an AI-Based Brand Identity Generation Platform 15

BrandCrafter AI, an AI-Based Brand Identity Generation Platf...

引用

15th IEEE Annual Computing and Communication Workshop and Conference, CCWC 2025

作者： Gawad, Selim Kim, Mira College of Engineering and Computer Science California State University Department of Computer Science Fullerton United States

ISBN: (纸本)9798331507695

In today's dynamic and highly competitive market, brand differentiation has become both essential and complex. The growth of social media and enhanced digital accessibility have transformed brand promotion into a multifaceted challenge, requiring a strategic and ongoing connection with target audiences to build loyalty and deter them from migrating to competitors. The constant evolution of social media trends and search engine optimization has added layers of complexity, creating an ongoing challenge for brands to remain visible and relevant. For new entrepreneurs, the cost of professional branding consultants is often beyond reach. This paper explores the potential of large language models (LLMs) as a cost-effective, automated solution for generating comprehensive, customized brand identity guidelines. We investigate the effectiveness of LLMs in creating cohesive branding strategies, encompassing brand tone, visual elements, and audience alignment, thus offering a scalable alternative to traditional consultancy services. We conducted a pilot study involving two participants, demonstrating positive outcomes, showing that LLM-generated brand identity guidelines were relevant and consistent and provided valuable support in the branding process. © 2025 IEEE.

关键词： AI Brand Identity LLM Personalization

来源：评论

学校读者我要写书评

暂无评论

K-Gate Lock: Multi-Key Logic Locking Using Input Encoding Against Oracle-Guided Attacks 25

K-Gate Lock: Multi-Key Logic Locking Using Input Encoding Ag...

引用

30th Asia and South Pacific Design Automation Conference, ASP-DAC 2025

作者： Lopez, Kevin Rezaei, Amin Computer Engineering and Computer Science Department California State University Long Beach United States

ISBN: (纸本)9798400706356

Logic locking has emerged to prevent piracy and overproduction of integrated circuits ever since the split of the design house and manufacturing foundry was established. While there has been a lot of research using a single global key to lock the circuit, even the most sophisticated single-key locking methods have been shown to be vulnerable to powerful SAT-based oracle-guided attacks that can extract the correct key with the help of an activated chip bought off the market and the locked netlist leaked from the untrusted foundry. To address this challenge, we propose, implement, and evaluate a novel logic locking method called K-Gate Lock that encodes input patterns using multiple keys that are applied to one set of key inputs at different operational times. Our comprehensive experimental results confirm that using multiple keys will make the circuit secure against oracle-guided attacks and increase attacker efforts to an exponentially time-consuming brute force search. K-Gate Lock has reasonable power and performance overheads, making it a practical solution for real-world hardware intellectual property protection. © 2025 Institute of Electrical and Electronics Engineers Inc.. All rights reserved.

关键词： Locks (fasteners)

来源：评论

学校读者我要写书评

暂无评论

xCCL:A Survey of Industry-Led Collective Communication Libraries for Deep Learning

引用

Journal of computer science & Technology 2023年第1期38卷 166-195页

作者： Adam Weingram 李雨珂戚昊 Darren Ng 代柳瑶鲁小亿 Department of Computer Science and Engineering University of CaliforniaMercedMerced 95343U.S.A.

Machine learning techniques have become ubiquitous both in industry and academic *** model sizes and training data volumes necessitate fast and efficient distributed training *** communications greatly simplify inter-and intra-node data transfer and are an essential part of the distributed training process as information such as gradients must be shared between processing *** this paper,we survey the current state-of-the-art collective communication libraries(namely xCCL,including NCCL,oneCCL,RCCL,MSCCL,ACCL,and Gloo),with a focus on the industry-led ones for deep learning *** investigate the design features of these xCCLs,discuss their use cases in the industry deep learning workloads,compare their performance with industry-made benchmarks(i.e.,NCCL Tests and PARAM),and discuss key take-aways and interesting *** believe our survey sheds light on potential research directions of future designs for xCCLs.

关键词： collective deep learning distributed training GPUDirect RDMA(remote direct memory access)

来源：评论

学校读者我要写书评

暂无评论

Generating Synthetic Data for Machine Learning Models from the Pediatric Heart Network Fontan I Dataset

引用

Congenital Heart Disease 2025年第1期20卷 115-127页

作者： Vatche Bahudian John Valdovinos Department of Electrical and Computer Engineering California State University NorthridgeNorthridgeCA 91330USA

Background: The population of Fontan patients, patients born with a single functioningventricle, is growing. There is a growing need to develop algorithms for this population that can predicthealth outcomes. Artiffcial intelligence models predicting short-term and long-term health outcomes forpatients with the Fontan circulation are needed. Generative adversarial networks (GANs) provide a solutionfor generating realistic and useful synthetic data that can be used to train such models. Methods: Despitetheir promise, GANs have not been widely adopted in the congenital heart disease research communitydue, in some part, to a lack of knowledge on how to employ them. In this research study, a GAN was usedto generate synthetic data from the Pediatric Heart Network Fontan I dataset. A subset of data consistingof the echocardiographic and BNP measures collected from Fontan patients was used to train the *** sets of synthetic data were created to understand the effect of data missingness on synthetic datageneration. Synthetic data was created from real data in which the missing values were imputed usingMultiple Imputation by Chained Equations (MICE) (referred to as synthetic from imputed real samples). Inaddition, synthetic data was created from real data in which the missing values were dropped (referred to assynthetic from dropped real samples). Both synthetic datasets were evaluated for ffdelity by using visualmethods which involved comparing histograms and principal component analysis (PCA) plots. Fidelitywas measured quantitatively by (1) comparing synthetic and real data using the Kolmogorov-Smirnovtest to evaluate the similarity between two distributions and (2) training a neural network to distinguishbetween real and synthetic samples. Both synthetic datasets were evaluated for utility by training aneural network with synthetic data and testing the neural network on its ability to classify patients thathave ventricular dysfunction using echocardiograph measures an

关键词： Synthetic data congenital heart disease Fontan circulation

来源：评论

学校读者我要写书评

暂无评论

Clustered Reinforcement Learning

引用

Frontiers of computer science 2025年第4期19卷 43-57页

作者： Xiao MA Shen-Yi ZHAO Zhao-Heng YIN Wu-Jun LI National Key Laboratory for Novel Software Technology Department of Computer Science and TechnologyNanjing UniversityNanjing 210023China Department of Electrical Engineering and Computer Sciences University of CaliforniaBerkeleyCA 94720-1770USA

Exploration strategy design is a challenging problem in reinforcement learning(RL),especially when the environment contains a large state space or sparse *** exploration,the agent tries to discover unexplored(novel)areas or high reward(quality)*** existing methods perform exploration by only utilizing the novelty of *** novelty and quality in the neighboring area of the current state have not been well utilized to simultaneously guide the agent’s *** address this problem,this paper proposes a novel RL framework,called clustered reinforcement learning(CRL),for efficient exploration in *** adopts clustering to divide the collected states into several clusters,based on which a bonus reward reflecting both novelty and quality in the neighboring area(cluster)of the current state is given to the *** leverages these bonus rewards to guide the agent to perform efficient ***,CRL can be combined with existing exploration strategies to improve their performance,as the bonus rewards employed by these existing exploration strategies solely capture the novelty of *** on four continuous control tasks and six hard-exploration Atari-2600 games show that our method can outperform other state-of-the-art methods to achieve the best performance.

关键词： deep reinforcement learning exploration count-based method clustering K-means

来源：评论

学校读者我要写书评

暂无评论

Question Selection for Multi-Modal Code Search Synthesis using Probabilistic Version Spaces

引用

IEEE Transactions on Software engineering 2025年第6期51卷 1724-1744页

作者： Wu, Jiarong Jiang, Yanyan Wei, Lili Xu, Congying Cheung, Shing-Chi Xu, Chang The Hong Kong University of Science and Technology Department of Computer Science and Engineering Hong Kong McGill University Department of Electrical and Computer Engineering Montreal Canada Nanjing University State Key Laboratory for Novel Software Technology Department of Computer Science and Technology Nanjing China

Searching the occurrences of specific code patterns (code search) is a common task in software engineering, and programming by example (PBE) techniques have been applied to ease customizing code patterns. However, previous PBE tools only synthesize programs meeting the input-output examples, which may not always align with the user intent. To bridge this gap, this paper proposes Excalibur, a multi-modal (example and natural language description) and interactive synthesizer for code search. Excalibur ensures that the generated programs are correct for the provided examples (soundness) and include the user-intended program (bounded completeness). Furthermore, Excalibur helps the user identify the user-intended program through question-answer interaction. To minimize the required interaction efforts, question selection is crucial. To improve question selection for code search, we propose probabilistic version spaces (ProbVS), in which the user-intended program’s probability is high and others are low. ProbVS combines traditional version spaces for compactly representing extensive programs and large language models (on the user-provided natural language description) for adjusting programs’ probabilities to align with users’ intents. Extensive experiments on a benchmark of 44 tasks demonstrated the effectiveness of Excalibur and ProbVS and demystified how ProbVS affects probability distributions and how the configurable parameters affect ProbVS. © 1976-2012 IEEE.

关键词： Normal distribution

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：