检索结果-内蒙古大学图书馆

From Missing Pieces to Masterpieces: Image Completion with Context-Adaptive Diffusion

IEEE Transactions on Pattern Analysis and Machine Intelligence 2025年第7期47卷 6073-6087页

作者： Shamsolmoali, Pourya Zareapoor, Masoumeh Zhou, Huiyu Felsberg, Michael Tao, Dacheng Li, Xuelong University of York Department of Computer Science United Kingdom University of Leicester School of Computing and Mathematical Sciences United Kingdom Linkoping University Computer Vision Laboratory Sweden Nanyang Technological University College of Computing & Data Science Singapore China Northwestern Polytechnical University Key Laboratory of Intelligent Interaction and Applications Ministry of Industry and Information Technology Xi'an China

Image completion is a challenging task, particularly when ensuring that generated content seamlessly integrates with existing parts of an image. While recent diffusion models have shown promise, they often struggle with maintaining coherence between known and unknown (missing) regions. This issue arises from the lack of explicit spatial and semantic alignment during the diffusion process, resulting in content that does not smoothly integrate with the original image. Additionally, diffusion models typically rely on global learned distributions rather than localized features, leading to inconsistencies between the generated and existing image parts. In this work, we propose ConFill, a novel framework that introduces a Context-Adaptive Discrepancy (CAD) model to ensure that intermediate distributions of known and unknown regions are closely aligned throughout the diffusion process. By incorporating CAD, our model progressively reduces discrepancies between generated and original images at each diffusion step, leading to contextually aligned completion. Moreover, ConFill uses a new Dynamic Sampling mechanism that adaptively increases the sampling rate in regions with high reconstruction complexity. This approach enables precise adjustments, enhancing detail and integration in restored areas. Extensive experiments demonstrate that ConFill outperforms current methods, setting a new benchmark in image completion. © 1979-2012 IEEE.

关键词： computer aided design

来源：评论

学校读者我要写书评

暂无评论

Hierarchical Text Classification Using Language Models with Global Label-Wise Attention Mechanisms 4th

Hierarchical Text Classification Using Language Models with...

引用

4th Southern African Conference for Artificial Intelligence Research, SACAIR 2023

作者： du Toit, Jaco Dunaiski, Marcel Department of Mathematical Science Computer Science Division Stellenbosch University Stellenbosch South Africa School for Data Science and Computational Thinking Stellenbosch University Stellenbosch South Africa

ISBN: (纸本)9783031490019

Hierarchical text classification (HTC) is a natural language processing task with the objective of categorising text documents into a set of classes from a structured class hierarchy. Recent HTC approaches combine encodings of the class hierarchy with the language understanding capabilities of pre-trained language models (PLMs) to improve classification performance. Furthermore, label-wise attention mechanisms have been shown to improve performance in HTC tasks by placing larger weight on more important parts of the document for each class individually to obtain label-specific representations of the document. However, using label-wise attention mechanisms to fine-tune PLMs for downstream HTC tasks has not been comprehensively investigated in previous work. In this paper, we evaluate the performance of a HTC approach which adds label-wise attention mechanisms, along with a label-wise classification layer, to a PLM which is subsequently fine-tuned on the downstream HTC dataset. We evaluate several existing label-wise attention mechanisms and propose an adaptation to one of the approaches which separates the attention mechanisms for the different levels of the hierarchy. Our proposed approach allows the prediction task at a certain level to leverage the information gained from the predictions performed at all ancestor levels. We compare the different label-wise attention mechanisms on three HTC benchmark datasets and show that our proposed approach generally outperforms the other label-wise attention mechanisms. Furthermore, we show that without using the complex techniques proposed in recent HTC approaches, our relatively simple approach outperforms state-of-the-art approaches on two of the three benchmark datasets. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Classification (of information)

来源：评论

学校读者我要写书评

暂无评论

Epidermis Bruise Analysis Using Deep Learning 6

Epidermis Bruise Analysis Using Deep Learning

引用

6th International Conference on Computational Intelligence and Communication Technologies, CCICT 2024

作者： Sharma, Vansheta Rani, Rupa Pathak, Priya Chakraborty, Sudeshna Department of Computer Science & Engineering- Data Science ABES Institute of Technology U.P. Ghaziabad India Department of Computer Science & Engineering Ajay Kumar Garg Engineering College U.P. Ghaziabad India Depatment of Computer Science & Engineering Banasthali Vidyapith Rajasthan India Department School of Computer Application and Technology Galgotias University UP India

ISBN: (纸本)9798350374629

Among the most vital organs that protect the body of a human from the external environment is the skin. Early skin illness identification is essential for reducing mortality because it prevents skin cancer, and any other skin disease from developing. But because it resembles skin patches, insect bites etc in appearance, early detection that might lengthen life expectancy is a fantastic experiment. We would be working with different skin diseases namely ‘Acne’, ‘Eczema or Atopic Dermatitis’, ‘melanoma’. A working model that uses image analysis and machine learning to classify and identify skin conditions. A brand-new, cutting edge automated system that can swiftly and accurately identify skin lesions is needed to deal with biomedical pictures. There is growing curiosity concerning the application of deep learning to the diagnosis and management of different diseases. For the early detection of skin disease, we therefore suggested a deep learning model based on CNN and the merger of the U-Net and ResNet models is presented as a fusion model that has been used to perform encoding decoding of the disorders using skin scans. This model integrates image processing, image enhancement, machine learning and segmentation techniques. The model yielded an overall accuracy of 95.6%. Incorporate additional skin conditions in the future to strengthen our model's suitability for medical applications. ©2024 IEEE.

关键词： Image enhancement

来源：评论

学校读者我要写书评

暂无评论

BATON: symphony of random testing and concolic testing through machine learning and taint analysis

引用

science China(Information sciences) 2023年第3期66卷 97-117页

作者： Bihuan CHEN Yang LIU Xin PENG Yijian WU Shengchao QIN School of Computer Science Fudan University Shanghai Key Laboratory of Data Science Fudan University School of Computer Science and Engineering Nanyang Technological University School of Computing Teesside University

Random testing is scalable but often fails to hit corner program behaviors,while systematic testing （e.g.,concolic execution） is promising to cover corner program behaviors but is not scalable to explore all program *** attempts to integrate random testing with systematic testing lack targeted *** this paper,we propose a guided hybrid testing approach,named BATON,to synergize random testing with concolic *** integrates the knowledge inside test cases and their executions into a conditional execution graph,and uses such knowledge to guide test case ***,we learn classification models for some conditionals in the conditional execution graph in a demand-driven *** models are used to guide random testing to reach and cover partially-covered *** further employ targeted concolic testing to cover conditionals that cannot be fully covered by guided random *** implemented BATONfor Java and evaluated it on three *** results show that BATONimproved branch coverage and mutation score over random testing by 16.2%–29.4%and 19.0%–30.0%,over adaptive random testing by 16.8%–33.8%and 19.4%–34.2%,over concolic testing by 2.3%–29.9%and 2.9%–30.1%,and over simple hybrid testing by 1.6%–14.5%and 1.4%–18.7%.

关键词： system testing random testing concolic testing

来源：评论

学校读者我要写书评

暂无评论

Causal fMRI-Mamba: Causal State Space Model for Neural Decoding and Brain Task States Recognition

Causal fMRI-Mamba: Causal State Space Model for Neural Decod...

引用

2025 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2025

作者： Deng, Weihao Han, Fei Ling, Qinghua Liu, Qing Han, Henry School of Computer Science and Communication Engineering JiangSu University China Jiangsu Engineering Research Center of Big Data Ubiquitous Perception and Intelligent Agriculture Applications China School of Computer Jiangsu University of Science and Technology China School of Electronic and Information Engineering West Anhui University China School of Engineering and Computer Science Baylor University United States

ISBN: (纸本)9798350368741

Deep learning advances neural decoding in functional magnetic resonance imaging (fMRI) tasks with convolution and attention-based methods. However, these methods struggle with capturing global spatiotemporal information due to high dimensionality, noise and inter-individual difference of fMRI, which also increase computational complexity and prior bias. To this end, a novel causal state space model, Causal fMRI-Mamba, is proposed for neural decoding and task state mapping. It effectively captures global spatiotemporal information via eliminating local redundancies and capturing long-distance dependencies. Meanwhile, a causal representation framework is designed to extract invariant high-order features and disentangle related causal features, enhancing model performance. Furthermore, a dense connection module is expanded to prevent significant causal information loss in hidden states of inter layers. On the HCP brain task state classification task, Causal fMRI-Mamba achieves better performance and generalization than comparison methods. © 2025 IEEE.

关键词： causal representation learning Neuro-decoding state space model task-based fMRI

来源：评论

学校读者我要写书评

暂无评论

Artificial intelligence in physiological characteristics recognition for internet of things authentication

引用

Digital Communications and Networks 2024年第3期10卷 740-755页

作者： Zhimin Zhang Huansheng Ning Fadi Farha Jianguo Ding Kim-Kwang Raymond Choo School of Computer and Communication Engineering University of Science and Technology BeijingBeijing100083China Beijing Engineering Research Center for Cyberspace Data Analysis and Applications Beijing100083China Faculty of Informatics Engineering Aleppo UniversityAleppoSyria Department of Computer Science Blekinge Institute of Technology37179KarlskronaSweden Department of Information Systems and Cyber Security University of Texas at San AntonioSan AntonioTX78249-0631USA

Effective user authentication is key to ensuring equipment security,data privacy,and personalized services in Internet of Things(IoT)***,conventional mode-based authentication methods(e.g.,passwords and smart cards)may be vulnerable to a broad range of attacks(e.g.,eavesdropping and side-channel attacks).Hence,there have been attempts to design biometric-based authentication solutions,which rely on physiological and behavioral *** characteristics need continuous monitoring and specific environmental settings,which can be challenging to implement in ***,we can also leverage Artificial Intelligence(AI)in the extraction and classification of physiological characteristics from IoT devices processing to facilitate ***,we review the literature on the use of AI in physiological characteristics recognition pub-lished after *** use the three-layer architecture of the IoT(i.e.,sensing layer,feature layer,and algorithm layer)to guide the discussion of existing approaches and their *** also identify a number of future research opportunities,which will hopefully guide the design of next generation solutions.

关键词： Physiological characteristics recognition Artificial intelligence Internet of things Biological-driven authentication

来源：评论

学校读者我要写书评

暂无评论

A Hybrid Model Using Coordinate Attention Mechanisms for Stock Price Prediction 24

A Hybrid Model Using Coordinate Attention Mechanisms for Sto...

引用

2024 International Conference on Digital Economy, Blockchain and Artificial Intelligence, DEBAI 2024

作者： Sun, Ying Zhang, Bowen Peng, Cheng The Institute for Sustainable Development Macau University of Science and Technology China College of Big Data and Internet Shenzhen Technology University Shenzhen China School of Computer Science University of Electronic Science and Technology of China Zhongshan China

ISBN: (纸本)9798400710261

Predicting stock prices is a complex and challenging task in financial markets due to the intricate and non-linear nature of stock price movements. This study explores the application of Coordinate Attention mechanisms within advanced Temporal Convolutional Network (TCN) frameworks for stock price prediction based solely on historical stock price data. We present a hybrid model that combines the advantages of modern TCNs with Coordinate Attention mechanisms to improve the precision and robustness of stock prediction models. Extensive experiments are conducted on the well-known TSLA stock dataset. The results show varying levels of alignment with actual stock prices, highlighting the strengths and weaknesses of each model. © 2024 Copyright held by the owner/author(s).

关键词： Prediction models

来源：评论

学校读者我要写书评

暂无评论

PipeMoE: Accelerating Mixture-of-Experts through Adaptive Pipelining 42

PipeMoE: Accelerating Mixture-of-Experts through Adaptive Pi...

引用

42nd IEEE International Conference on computer Communications, INFOCOM 2023

作者： Shi, Shaohuai Pan, Xinglin Chu, Xiaowen Li, Bo Harbin Institute of Technology School of Computer Science and Technology Shenzhen China Hong Kong Baptist University Department of Computer Science Hong Kong Data Science and Analytics Thrust Hong Kong The Hong Kong University of Science and Technology Department of Computer Science and Engineering Hong Kong

ISBN: (纸本)9798350334142

Large models have attracted much attention in the AI area. The sparsely activated mixture-of-experts (MoE) technique pushes the model size to a trillion-level with a sub-linear increase of computations as an MoE layer can be equipped with many separate experts, but only one or two experts need to be trained for each input data. However, the feature of dynamically activating experts of MoE introduces extensive communications in distributed training. In this work, we propose PipeMoE to adaptively pipeline the communications and computations in MoE to maximally hide the communication time. Specifically, we first identify the root reason why a higher pipeline degree does not always achieve better performance in training MoE models. Then we formulate an optimization problem that aims to minimize the training iteration time. To solve this problem, we build performance models for computation and communication tasks in MoE and develop an optimal solution to determine the pipeline degree such that the iteration time is minimal. We conduct extensive experiments with 174 typical MoE layers and two real-world NLP models on a 64-GPU cluster. Experimental results show that our PipeMoE almost always chooses the best pipeline degree and outperforms state-of-the-art MoE training systems by 5%-77% in training time. © 2023 IEEE.

关键词： Pipelines

来源：评论

学校读者我要写书评

暂无评论

DivLog: Log Parsing with Prompt Enhanced In-Context Learning 24

DivLog: Log Parsing with Prompt Enhanced In-Context Learning

引用

44th ACM/IEEE International Conference on Software Engineering, ICSE 2024

作者： Xu, Junjielong Yang, Ruichun Huo, Yintong Zhang, Chengyu He, Pinjia The Chinese University of Hong Kong Dept. of Computer Science & Engineering Hong Kong Eth Zurich Switzerland School of Data Science The Chinese University of Hong Kong Shenzhen China Shenzhen Research Institute of Big Data China

ISBN: (纸本)9798400702174

Log parsing, which involves log template extraction from semi-structured logs to produce structured logs, is the first and the most critical step in automated log analysis. However, current log parsers suffer from limited effectiveness for two reasons. First, traditional data-driven log parsers solely rely on heuristics or handcrafted features designed by domain experts, which may not consistently perform well on logs from diverse systems. Second, existing super-vised log parsers require model tuning, which is often limited to fixed training samples and causes sub-optimal performance across the entire log source. To address this limitation, we propose Di-vLog, an effective log parsing framework based on the in-context learning (ICL) ability of large language models (LLMs). Specifically, before log parsing, DivLog samples a small amount of offline logs as candidates by maximizing their diversity. Then, during log parsing, DivLog selects five appropriate labeled candidates as examples for each target log and constructs them into a prompt. By mining the semantics of examples in the prompt, DivLog generates a target log template in a training-free manner. In addition, we design a straightforward yet effective prompt format to extract the output and enhance the quality of the generated log templates. We conducted experiments on 16 widely-used public datasets. The results show that DivLog achieves (1) 98.1% Parsing Accuracy, (2) 92.1% Precision Template Accuracy, and (3) 92.9% Recall Template Accuracy on average, exhibiting state-of-the-art performance. © 2024 ACM.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Semi-supervised Learning for Fine-Grained Entity Typing with Mixed Label Smoothing and Pseudo Labeling 28th

Semi-supervised Learning for Fine-Grained Entity Typing wit...

引用

28th International Conference on database Systems for Advanced Applications, DASFAA 2023

作者： Xu, Bo Zhang, Zhengqi Du, Ming Wang, Hongya Song, Hui Xiao, Yanghua School of Computer Science and Technology Donghua University Shanghai China Shanghai Key Laboratory of Data Science School of Computer Science Fudan University Shanghai China Fudan-Aishu Cognitive Intelligence Joint Research Center Shanghai China

ISBN: (纸本)9783031306747

Distant supervision (DS) has been proposed to automatically annotate data and achieved significant success in fine-grained entity typing(FET). Despite its efficiency, distant supervision often suffers from the noisy labeling problem. To solve the noisy labeling problem, existing approaches assume the existence of "clean" and "noisy" sets in the training data and use different types of methods to utilize them. However, they still suffer from the confirmation bias problem in the "noisy" set and the false positive problem in the "clean" set. To address these issues, we propose a novel semi-supervised learning method with mixed label smoothing and pseudo labeling for distantly supervised fine-grained entity typing. Specifically, to solve the false positive problem on the "clean" set, we propose a mixed label smoothing method to smooth the labels of the "clean" set to train the FET model. To solve the confirmation bias problem on the "noisy" set, we do not consider the labels in the "noisy" set and use a pseudo labeling technique to deal with the "noisy" set. Extensive experiments conducted on three widely used FET datasets show the effectiveness of our proposed approach. The source code is publicly available at https://***/xubodhu/NFETC-SSL. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Learning systems

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：