检索结果-内蒙古大学图书馆

Proceedings of the Digital Image Computing: Technqiues and Applications (DICTA)

作者： Tauseef Tajwar Muftiqur Rahman Taukir Azam Chowdhury Sabbir Ahmed Moshiur Farazi Md. Hasanul Kabir Department of Computer Science and Engineering Islamic University of Technology Gazipur Bangladesh Department of Computer Science and Engineering United International University Dhaka Bangladesh Data61-CSIRO Imaging and Computer Vision Group Canberra Australia

Zero-shot Semantic Segmentation (ZS3) is a challenging task that segments objects belonging to classes that are completely unseen during training. An established and intuitive approach is to formulate ZS3 as a combination of two subtasks where, at first, mask proposals are generated and then each pixel in those regions is assigned a class label. Most of the existing works struggle to generate masks with high generalization capability, which results in significant underperformance in unseen classes. In this connection, we propose the use of ‘Dynamic Kernels’ to help a ZS3 model better ‘understand’ the objects in the training phase by taking advantage of their inherent inductive biases to generate better mask proposals. They act as specialized agents that are updated based on their corresponding contents from the seen classes and then utilize that knowledge to understand unseen objects. The proposed pipeline also leverages the Contrastive Language-Image Pre-Training (CLIP) architecture to perform segment classification which further improves the generalization performance by exploiting its cross-modal training. Dynamic kernels go hand-in-hand with CLIP since it is able to process the granularity of CLIP from image level to pixel level resulting in performance improvement for both the seen and unseen classes. Our method, ‘Zero-Shot dynamic Kernel Network’ (ZSK-Net), outperforms the previous works by achieving +6.4h IoU on the Pascal VOC dataset. It also achieves state-of-the-art result on the COCO-Stuff dataset by +0.9h IoU on a single prompt setting.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Detecting and Corrupting Convolution-based Unlearnable Examples 39

Detecting and Corrupting Convolution-based Unlearnable Examp...

引用

39th Annual AAAI Conference on Artificial Intelligence, AAAI 2025

作者： Li, Minghui Wang, Xianlong Yu, Zhifei Hu, Shengshan Zhou, Ziqi Zhang, Longling Zhang, Leo Yu School of Software Engineering Huazhong University of Science and Technology China Hubei Key Laboratory of Distributed System Security Hubei Engineering Research Center on Big Data Security China School of Cyber Science and Engineering Huazhong University of Science and Technology China School of Computer Science and Technology Huazhong University of Science and Technology China School of Information and Communication Technology Griffith University Australia

ISBN: (纸本)157735897X

Convolution-based unlearnable examples (UEs) employ class-wise multiplicative convolutional noise to training samples, severely compromising model performance. This fire-new type of UEs have successfully countered all defense mechanisms against UEs. The failure of such defenses can be attributed to the absence of norm constraints on convolutional noise, leading to severe blurring of image features. To address this, we first design an Edge Pixel-based Detector (EPD) to identify convolution-based UEs. Upon detection of them, we propose the first defense scheme against convolution-based UEs, COrrupting these samples via random matrix multiplication by employing bilinear INterpolation (COIN) such that disrupting the distribution of class-wise multiplicative noise. To evaluate the generalization of our proposed COIN, we newly design two convolution-based UEs called VUDA and HUDA to expand the scope of convolution-based UEs. Extensive experiments demonstrate the effectiveness of detection scheme EPD and that our defense COIN outperforms 11 state-of-the-art (SOTA) defenses, achieving a significant improvement on the CIFAR and ImageNet datasets. Copyright © 2025, Association for the Advancement of Artificial Intelligence (***). All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Transforming Skin Disease Diagnosis: Harnessing Compound-Scaled AI Network for Enhanced Image Analysis and Precision Medicine 3

Transforming Skin Disease Diagnosis: Harnessing Compound-Sca...

引用

3rd International Conference on Disruptive Technologies, ICDT 2025

作者： Santhoshkumar, S.P. Ravichandra, Torthi Mounika, Nandipati Ranjani, R. Gajalakshmi, S. Philip, Jim Mathew Vel Tech Rangarajan Dr. Sagunthala R&d Institute of Science and Technology Department of Computer Science and Engineering Avadi Chennai India Ellenki College of Engineering and Technology Department of Electronics and Communication Engineering Patelguda Sangareddy Bhel India Ellenki College of Engineering and Technology Department of Computer Science and Engineering Patelguda Sangareddy Bhel India Vel Tech High Tech Dr. Rangarajan Dr. Sakunthala Engineering College Department of Artificial intelligence and data science Avadi Chennai India Department of Computer Science and Engineering Rathinam Technical Campus Tamil Nadu Coimbatore India Sri Ramakrishna Institute of Technology Department of Computer Science and Engineering Tamil Nadu Coimbatore India

ISBN: (纸本)9798331519582

Millions worldwide suffer from skin conditions, making prompt and precise diagnosis essential to successful treatment. However, conventional diagnostic techniques are time-consuming, dependent on physician knowledge, and frequently unavailable in low-resource locations. The compound-scaled AI network, an advanced deep-learning model, addresses these challenges by providing precise and scalable image analysis. Utilizing high-resolution imaging and compound scaling, it can accurately detect, classify, and segment various skin disorders, including benign and malignant lesions. While questions remain about whether AI matches human specialists in diagnosing all pigmented skin lesions, studies have compared AI performance against experts in identifying clinically significant cases. This research highlights the compound-scaled AI network's potential in dermatology, particularly for telemedicine, early cancer detection, and clinical workflow integration. By enhancing diagnostic accessibility and accuracy, this AI model could transform dermatology, enabling more personalized and equitable treatment worldwide. Impressively, it achieved 99.6% training accuracy and 98.4% testing accuracy, demonstrating deep learning's effectiveness in automating skin disorder detection and classification. © 2025 IEEE.

关键词： Dermatitis

来源：评论

学校读者我要写书评

暂无评论

Recognition of data Breach Method from Story Using Advanced Deep Learning

Recognition of Data Breach Method from Story Using Advanced ...

引用

Innovation in Technology (INOCON), IEEE International Conference for

作者： Samiha Maisha Jeba Tanjim Taharat Aurpa Md Samiul Alom Md. Wadud Mahmud Joy Asm Shakil Ahamed Satya Ranjan Dash Md Shoaib Ahmed Dept. of Computer Science and Engineering International University of Business Agriculture and Technology Bangladesh Department of Data Science Bangabandhu Sheikh Mujibur Rahman Digital University Bangladesh School of Computer Applications KIIT University Odisha India Department of Computer Science Boise State University Boise Idaho USA

We often open our eyes in the morning with the appalling news of data breaches of different popular companies. This is a significant threat not only to giant companies but also to the general people’s privacy. Various methods are maneuvered for data breaches, and identifying these methods in a short can help understand the loss and take proper steps against these incidents. Researchers nowadays focus on the data breaches issue to reduce its threats to the tech industry. In this research, we have used advanced deep learning methods(e.g., BERT, XLNet, and Electra) to predict data breach methods using the data breach story. The proposed classifier has provided an accuracy of 92.86%.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Conformalized Generative Bayesian Imaging: An Uncertainty Quantification Framework for Computational Imaging

arXiv

引用

arXiv 2025年

作者： Ekmekci, Canberk Cetin, Mujdat Department of Electrical and Computer Engineering University of Rochester RochesterNY14627 United States Department of Electrical and Computer Engineering Goergen Institute for Data Science University of Rochester RochesterNY14627 United States

Uncertainty quantification plays an important role in achieving trustworthy and reliable learning-based computational imaging. Recent advances in generative modeling and Bayesian neural networks have enabled the development of uncertainty-aware image reconstruction methods. Current generative model-based methods seek to quantify the inherent (aleatoric) uncertainty on the underlying image for given measurements by learning to sample from the posterior distribution of the underlying image. On the other hand, Bayesian neural network-based approaches aim to quantify the model (epistemic) uncertainty on the parameters of a deep neural network-based reconstruction method by approximating the posterior distribution of those parameters. Unfortunately, an ongoing need for an inversion method that can jointly quantify complex aleatoric uncertainty and epistemic uncertainty patterns still persists. In this paper, we present a scalable framework that can quantify both aleatoric and epistemic uncertainties. The proposed framework accepts an existing generative model-based posterior sampling method as an input and introduces an epistemic uncertainty quantification capability through Bayesian neural networks with latent variables and deep ensembling. Furthermore, by leveraging the conformal prediction methodology, the proposed framework can be easily calibrated to ensure rigorous uncertainty quantification. We evaluated the proposed framework on magnetic resonance imaging, computed tomography, and image inpainting problems and showed that the epistemic and aleatoric uncertainty estimates produced by the proposed framework display the characteristic features of true epistemic and aleatoric uncertainties. Furthermore, our results demonstrated that the use of conformal prediction on top of the proposed framework enables marginal coverage guarantees consistent with frequentist principles. Copyright © 2025, The Authors. All rights reserved.

关键词： Inverse problems

来源：评论

学校读者我要写书评

暂无评论

ASAnalyzer: Attention based Sentiment analyzer for Real-world Sentiment Analysis

ASAnalyzer: Attention based Sentiment analyzer for Real-worl...

引用

Frontiers of Information Technology (FIT)

作者： Khadim Hussain Muhammad Azhar Bumshik Lee Asma Iqbal Muhammad Affan Sajid Ullah Khan Department of Computer Science Comsats University Islamabad Sahiwal Pakistan Department of Applied Data Science Hong Kong Shue Yan University Hong Kong Department of Computer Science and Software Engineering Chosun University Korea Department of Computer Science Tsinghua University China Department of Computer Science University of Lakki Marwat

In this era of big data, a lot of data is produced in various forms every second through various sources. Text data is one of those types that is produced mainly through social media like Twitter, Facebook, YouTube comments, WhatsApp, etc. To know the public's point of view on a specific issue, we can perform sentiment analysis on the text data collected from the above sites. Even though various algorithms have been proposed for sentiment analysis, these algorithms have issues of high time complexity and low context awareness, leading to low classification accuracy. To resolve the above issues, we propose an attention-based sentiment analyzer for real-world sentiment analysis named ‘ASAnalyzer’, which uses CNN+Attention-Based BiGRU. CNN is used to extract local features from the tweets, and then these features are used by Attention-Based BiGRU to learn the contextual information of the tweets and the long-term dependencies in both directions of the text, which helps to improve accuracy. To validate our algorithm, we used tweet data about the anti-COVID-19 vaccine from Twitter, and the results have shown that our method outperformed other state-of-the-art methods.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Investigation on Nail Denting or Crumbling from Nail Psoriasis Patient Ailment data using the Machine Learning Algorithm and data Mining Techniques

Investigation on Nail Denting or Crumbling from Nail Psorias...

引用

International conference of Electronics, Communication and Aerospace Technology (ICECA)

作者： K. Janani S. P. Santhoshkumar D. Vikram S. Priya M. Vijayaraj M. Priyanga Department of Data science and Computer Applications Manipal Institute of Technology Manipal India Department of Computer Science and Engineering Vel Tech Rangarajan Dr. Sagunthala R&D Institute of Science and Technology Avadi Chennai Department of Artificial Intelligence and Data Science Rathinam Technical Campus Coimbatore India Department of Information Technology Rathinam Technical Campus Coimbatore India

ISBN: (数字)9798350367904

ISBN: (纸本)9798350367911

Nail denting or crumbling may result from nail psoriasis. A nail condition known as psoriatic onychodystrophy or psoriatic nails. Psoriasis sufferers frequently experience it; reported occurrences range from 10% to 78%. Psoriatic nails are more common in the elderly and in people with psoriatic arthritis. By examining the nails on a human hand, numerous illnesses can be found early in the diagnosing process. The nail color of an individual can help in the diagnosis of specific medical disorders. In this case, the recommended method results in the decision-making process for sickness diagnosis. The system is fed by human nail art. The technique recognizes nail features unique to a given condition by analyzing images of nails. The suggested technique makes advantage of the various distinctive characteristics of human nails to detect illness by changing the colour of the nails. The first training set data, which is derived from an image of a patient’s nails with a particular ailment, is handled by the Weka tool. To get the desired results, the feature discoveries of the picture are compared to the training dataset. The distortion of the nail unit is known as nail disease. Nail units have their own disease class due to their own indications, symptoms, causes, and consequences, which may or may not be related to other medical disorders. Nail problems are still difficult and ambiguous to identify. A novel machine learning method for recognising and classifying nail problems from photographs is presented in this study. This framework combines CNN models with data mining techniques to extract characteristics. This research was also contrasted with certain other province algorithms (Support vector, ANN, K - nearest neighbors, and RF) evaluated on datasets and showed positive results. The accuracy numbers show how well the model can distinguish nail conditions. This ground-breaking discovery lays the groundwork for precise diagnosis in dermatology, medical image processing, a

关键词： Training Accuracy Machine learning algorithms Image color analysis Psoriasis Nails Vectors Topology data mining Biomedical image processing

来源：评论

学校读者我要写书评

暂无评论

Entropic Gromov-Wasserstein distances: stability and algorithms

The Journal of Machine Learning Research

引用

The Journal of Machine Learning Research 2024年第1期25卷 17738-17789页

作者： Gabriel Rioux Ziv Goldfeld Kengo Kato Center for Applied Mathematics Cornell University Ithaca NY School of Electrical and Computer Engineering Cornell University Ithaca NY Department of Statistics and Data Science Cornell University Ithaca NY

The Gromov-Wasserstein (GW) distance quantifies discrepancy between metric measure spaces and provides a natural framework for aligning heterogeneous datasets. Alas, as exact computation of GW alignment is NP-complete, entropic regularization provides an avenue towards a computationally tractable proxy. Leveraging a recently derived variational representation for the quadratic entropic GW (EGW) distance, this work derives the first efficient algorithms for solving the EGW problem subject to formal, nonasymptotic convergence guarantees. To that end, we derive smoothness and convexity properties of the objective in this variational problem, which enables its resolution by the accelerated gradient method. Our algorithms employ Sinkhorn's fixed point iterations to compute an approximate gradient, which we model as an inexact oracle. We furnish convergence rates towards local and even global solutions (the latter holds under a precise quantitative condition on the regularization parameter), characterize the effects of gradient inexactness, and prove that stationary points of the EGW problem converge towards a stationary point of the unregularized GW problem, in the limit of vanishing regularization. We provide numerical experiments that validate our theory and empirically demonstrate the state-of-the-art empirical performance of our algorithm.

关键词： Algorithms convergence rate global guarantees Gromov-Wasserstein distances entropic regularization inexact gradient methods

来源：评论

学校读者我要写书评

暂无评论

Causal Modeling in Multi-Context Systems: Distinguishing Multiple Context-Specific Causal Graphs which Account for Observational Support

arXiv

引用

arXiv 2024年

作者： Rabel, Martin Günther, Wiebke Runge, Jakob Gerhardus, Andreas Institute of Data Science Jena Germany Dresden Germany Leipzig Germany Technische Universität Dresden Faculty of Computer Science Dresden Germany Technische Universität Berlin Institute of Computer Engineering and Microelectronics Berlin Germany

Causal structure learning with data from multiple contexts carries both opportunities and challenges. Opportunities arise from considering shared and context-specific causal graphs enabling to generalize and transfer causal knowledge across contexts. However, a challenge that is currently understudied in the literature is the impact of differing observational support between contexts on the identifiability of causal graphs. Here we study in detail recently introduced [6] causal graph objects that capture both causal mechanisms and data support, allowing for the analysis of a larger class of context-specific changes, characterizing distribution shifts more precisely. We thereby extend results on the identifiability of context-specific causal structures and propose a framework to model context-specific independence (CSI) within structural causal models (SCMs) in a refined way that allows to explore scenarios where these graph objects differ. We demonstrate how this framework can help explaining phenomena like anomalies or extreme events, where causal mechanisms change or appear to change under different conditions. Our results contribute to the theoretical foundations for understanding causal relations in multi-context systems, with implications for generalization, transfer learning, and anomaly detection. Future work may extend this approach to more complex data types, such as time-series. © 2024, CC BY-SA.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

DC-APIC: A decomposed compatible affine particle in cell transfer scheme for non-sticky solid–fluid interactions in MPM

引用

Graphical Models 2025年 139卷

作者： Wang, Chenhui Zhang, Jianyang Li, Chen Wang, Changbo School of Computer Science and Technology East China Normal University 3663N. Zhongshan Road Shanghai200062 China School of Computer Science and Engineering Tianjin University of Technology No. 391 Bin Shui Xi Dao Road Tianjin300384 China School of Data Science and Engineering East China Normal University 3663N. Zhongshan Road Shanghai200062 China

Despite the material point method (MPM) provides a unified particle simulation framework for coupling of different materials, MPM suffers from sticky numerical artifacts, which is inherently restricted to sticky and no-slip interactions. In this paper, we propose a novel transfer scheme called Decomposed Compatible Affine Particle in Cell (DC-APIC) within the MPM framework for simulating the two-way coupled interaction between elastic solids and incompressible fluids under free-slip boundary conditions on a unified background grid. Firstly, we adopt particle-grid compatibility to describe the relationship between grid nodes and particles at the fluid–solid interface, which serves as the guideline for subsequent particle–grid–particle transfers. Then we develop a phase-field gradient method to track the compatibility and normal directions at the interface. Secondly, to facilitate automatic MPM collision resolution during solid–fluid coupling, in the proposed DC-APIC integrator, the tangential component will not be transferred between incompatible grid nodes to prevent velocity smoothing in another phase, while the normal component is transferred without limitations. Finally, our comprehensive results confirm that our approach effectively reduces diffusion and unphysical viscosity compared to traditional MPM. © 2025 The Authors

关键词： Incompressible flow

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：