检索结果-内蒙古大学图书馆

unsupervised image segmentation with robust virtual class contrast

PATTERN RECOGNITION LETTERS 2023年第1期173卷 10-16页

作者： Nguyen, Khang Do, Kien Vu, Truong Than, Khoat Hanoi Univ Sci & Technol Hanoi Vietnam Deakin Univ Appl Artificial Intelligence Inst A2I2 Burwood Australia

unsupervised image segmentation (UIS) is a challenging problem in computer vision that aims to classify pixels in an image into different semantic classes without using any labels. Among the various UIS methods, Mask Contrast performs well when dealing with complex objects containing lots of detail. It utilizes prior knowledge from a pretrained saliency detection model to identify foreground pixels and leverages contrastive learning to learn the representations of those foreground pixels. However, this method is not designed to handle situations where foreground pixels belong to multiple semantic classes. To mitigate this problem, we propose a novel method for UIS called Robust Virtual Class Contrast (RVCC), which characterizes foreground pixels based on their "virtual classes" rather than just saliency masks. A virtual class can be viewed as the representation of some unknown object in the training data. Our method employs K-means clustering to find the pseudo virtual class label for every foreground pixel at the start of each training epoch. These pseudo-labels are then used to guide the learning of pixel representations. Additionally, to avoid the overconfidence of pseudo-label prediction, RVCC incorporates an additional regularization term that encourages consistency between the predictions under weak and strong augmentations. Our experiments demonstrate that RVCC outperforms existing baselines on the Pascal VOC2012 and MSRCv2 datasets, showcasing its capability for the UIS problem.

关键词： unsupervised image segmentation Contrastive learning

来源：评论

学校读者我要写书评

暂无评论

unsupervised image segmentation using triplet Markov fields

引用

COMPUTER VISION AND image UNDERSTANDING 2005年第3期99卷 476-498页

作者： Benboudjema, D Pieczynski, W GETIINT Dept CITI F-91000 Evry France

Hidden Markov fields (HMF) models are widely applied it) Narious problems arising in image processing. In these models, the hidden process of interest X is a Markov field and must be estimated from its observable noisy version Y. The success of I I M F is mainly due to (lie fact that the conditional probability distribution of the hidden process with respect to the observed one remains Markovian, which facilitates different processing strategic,,, such its Bayesian restoration. HMF have been recently generalized to "pairwise" Markov fields (PMF), which offer similar processing advantages and superior modeling capabilities, In PMF one directly assumes the Markovianity of the pair (X, Y). Afterwards. "triplet" Markov fields (TMF), ill which the distribution of the pair (X, Y) is the marginal distribution of a Markov field M U, 1), where U is all auxiliary process. have been proposed and still allow restoration processing. The aim of this paper is to propose it new parameter estimation method adapted to TMF, and to study the corresponding unsupervised image segmentation methods. The hitter are validated via experiments and real image processing, (c) 2005 Elsevier Inc. All rights reserved.

关键词： hidden Markov fields pairwise Markov fields triplet Markov fields Bayesian classification mixture estimation iterative conditional estimations Stochastic gradient unsupervised image segmentation

来源：评论

学校读者我要写书评

暂无评论

unsupervised image segmentation Using Comparative Reasoning and Random Walks

Unsupervised Image Segmentation Using Comparative Reasoning ...

引用

3rd IEEE Global Conference on Signal and Information Processing (GlobalSIP)

作者： Kulkarni, Anuva Condessa, Filipe Kovacevic, Jelena Carnegie Mellon Univ Dept Elect & Comp Engn Pittsburgh PA 15213 USA Univ Lisbon Inst Telecomunicacoes Lisbon Portugal Univ Lisbon Inst Super Tecn Lisbon Portugal Carnegie Mellon Univ Dept Biomed Engn Pittsburgh PA 15213 USA

ISBN: (纸本)9781479975914

An image segmentation method that does not need training data can provide faster results than methods using complex optimization. Motivated by this idea, we present an unsupervised image segmentation method that combines comparative reasoning with graph-based clustering. Comparative reasoning enables fast similarity search on the image, and these search results are used with the Random Walks algorithm, which is used for clustering and calculating class probabilities. Our method is validated on diverse image modalities such as biomedical images, natural images and texture images. The performance of the method is measured through cluster purity based on available ground truth. Our results are compared to existing segmentation methods using Global Consistency Error scores.

关键词： unsupervised image segmentation hashing Winner Take All hash comparative reasoning Random Walks

来源：评论

学校读者我要写书评

暂无评论

Artificial immune kernel clustering network for unsupervised image segmentation

引用

Progress in Natural Science:Materials International 2008年第4期18卷 455-461页

作者： Wenlong Huang , Licheng Jiao Institute of Intelligent Information Processing, Xidian University, Xi’an 710071, China Institute of Intelligent Information Processing Xidian University Xi’an 710071 China

An immune kernel clustering network (IKCN) is proposed based on the combination of the artificial immune network and the sup- port vector domain description (SVDD) for the unsupervised image segmentation. In the network, a new antibody neighborhood and an adaptive learning coeffcient, which is inspired by the long-term memory in cerebral cortices are presented. Starting from IKCN algo- rithm, we divide the image feature sets into subsets by the antibodies, and then map each subset into a high dimensional feature space by a mercer kernel, where each antibody neighborhood is represented as a support vector hypersphere. The clustering results of the local support vector hyperspheres are combined to yield a global clustering solution by the minimal spanning tree (MST), where a predfined number of clustering is not needed. We compare the proposed methods with two common clustering algorithms for the artificial synthetic data set and several image data sets, including the synthetic texture images and the SAR images, and encouraging experimental results are obtained.

关键词： Artificial immune network Kernel mapping Nonsubsampled contourlet transform unsupervised image segmentation

来源：评论

学校读者我要写书评

暂无评论

Q-Seg: Quantum Annealing-Based unsupervised image segmentation

引用

IEEE COMPUTER GRAPHICS AND APPLICATIONS 2024年第5期44卷 27-39页

作者： Venkatesh, Supreeth Mysore Macaluso, Antonio Nuske, Marlon Klusch, Matthias Dengel, Andreas German Res Ctr Artificial Intelligence D-66123 Saarbrucken Germany

We present Q-Seg, a novel unsupervised image segmentation method based on quantum annealing, tailored for existing quantum hardware. We formulate the pixelwise segmentation problem, which assimilates spectral and spatial information of the image, as a graph-cut optimization task. Our method efficiently leverages the interconnected qubit topology of the D-wave advantage device, offering superior scalability over existing quantum approaches and outperforming several tested state-of-the-art classical methods. Empirical evaluations on synthetic datasets have shown that Q-Seg has better runtime performance than the state-of-the-art classical optimizer Gurobi. The method has also been tested on earth observation image segmentation, a critical area with noisy and unreliable annotations. In the era of noisy intermediate-scale quantum, Q-Seg emerges as a reliable contender for real-world applications in comparison to advanced techniques like Segment Anything. Consequently, Q-Seg offers a promising solution using available quantum hardware, especially in situations constrained by limited labeled data and the need for efficient computational runtime.

关键词： image segmentation Quantum Computing Annealing Quantum Annealing image Edge Detection Optimization Measurement image segmentation unsupervised image segmentation Computer Vision unsupervised Methods segmentation Method Solution Space Edge Detection Earth Observation Quantum Computing Optimization Task segmentation Problem segmentation Quality image segmentation Methods Flood Mapping Multi Object Tracking Special Case Training Data Intensity Values Similarity Measure Edge Weights Minimum Cut Noisy Labels Grid Graph Gradient Boosting Decision Tree Real Devices Synthetic Aperture Radar Binary segmentation Specific Use Case segmentation Task

来源：评论

学校读者我要写书评

暂无评论

Consistent Estimation of the Max-Flow Problem: Towards unsupervised image segmentation

引用

IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE 2022年第5期44卷 2346-2357页

作者： Iquebal, Ashif Sikandar Bukkapatnam, Satish Texas A&M Univ Dept Ind & Syst Engn College Stn TX 77843 USA

Advances in the image-based diagnostics of complex biological and manufacturing processes have brought unsupervised image segmentation to the forefront of enabling automated, on the fly decision making. However, most existing unsupervised segmentation approaches are either computationally complex or require manual parameter selection (e.g., flow capacities in max-flow/min-cut segmentation). In this work, we present a fully unsupervised segmentation approach using a continuous max-flow formulation over the image domain while optimally estimating the flow parameters from the image characteristics. More specifically, we show that the maximum a posteriori estimate of the image labels can be formulated as a continuous max-flow problem given the flow capacities are known. The flow capacities are then iteratively obtained by employing a novel Markov random field prior over the image domain. We present theoretical results to establish the posterior consistency of the flow capacities. We compare the performance of our approach using brain tumor image segmentation, defect identification in additively manufactured components using electron microscopic images, and segmentation of multiple real-world images. Comparative results with several state-of-the-art supervised as well as unsupervised methods suggest that the present method performs statistically similar to the supervised methods, but results in more than 90 percent improvement in the Dice score when compared to the state-of-the-art unsupervised methods.

关键词： image segmentation Minimization TV Estimation Tumors Markov processes Manuals Continuous max-flow unsupervised image segmentation maximum a posteriori estimation posterior consistency

来源：评论

学校读者我要写书评

暂无评论

Information fusion for unsupervised image segmentation using stochastic watershed and Hessian matrix

引用

IET image PROCESSING 2018年第4期12卷 525-531页

作者： Chahine, Chaza Vachier-Lagorre, Corinne Chenoune, Yasmina El Berbari, Racha El Fawal, Ziad Petit, Eric Univ Paris Est LISSI Creteil France Lebanese Univ Doctoral Sch Sci & Technol Beirut Lebanon ESME Sudria Lab Ingn Syst Traitement Informat Ivry France

This study deals with information fusion for image segmentation. The evidence theory (or the Dempster-Shafer theory) allows the modellisation of uncertainty and imprecision in the information as well as the combination of different sources. Here, this approach is used in an unsupervised framework to combine the stochastic watershed segmentation which provides several segmentation results, with a Hessian operator in order to obtain a unique and efficient segmentation. The method is tested on natural images from the Berkeley dataset and evaluated using several evaluation metrics. The fusion results surpass those obtained with stochastic watershed alone.

关键词： Hessian matrices image segmentation unsupervised learning Information fusion unsupervised image segmentation stochastic watershed Hessian matrix Berkeley dataset

来源：评论

学校读者我要写书评

暂无评论

Bayesian learning, global competition and unsupervised image segmentation

引用

PATTERN RECOGNITION LETTERS 2000年第2期21卷 107-116页

作者： Guo, GD Ma, SD Nanyang Technol Univ Sch Elect & Elect Engn Intelligent Machine Res Lab Singapore 639798 Singapore CAS NLPR Inst Automat Beijing 100080 Peoples R China

A novel approach to unsupervised stochastic model-based image segmentation is presented and the problems of parameter estimation and image segmentation are formulated as Bayesian learning. In order to draw samples corresponding to different classes, a global competition strategy is adopted for label commitment based on the "powervalue" (PV) associated with each sample (or site). The smaller the value, the more powerful the sample to compete. Parameter estimation and image segmentation are executed in the same process. Bayesian modeling of images by Markov random fields (MRFs) makes it easy to represent the power of each site for competition. The new procedure to unsupervised image segmentation is performed on synthetic and real images to show its success. (C) 2000 Elsevier Science B.V. All rights reserved.

关键词： Bayesian learning global competition unsupervised image segmentation Markov random field parameter estimation

来源：评论

学校读者我要写书评

暂无评论

A Nonsymmetric Mixture Model for unsupervised image segmentation

引用

IEEE TRANSACTIONS ON CYBERNETICS 2013年第2期43卷 751-765页

作者： Thanh Minh Nguyen Wu, Q. M. Jonathan Univ Windsor Dept Elect & Comp Engn Windsor ON N9B 3P4 Canada

Finite mixture models with symmetric distribution have been widely used for many computer vision and pattern recognition problems. However, in many applications, the distribution of the data has a non-Gaussian and nonsymmetric form. This paper presents a new nonsymmetric mixture model for image segmentation. The advantage of our method is that it is simple, easy to implement, and intuitively appealing. In this paper, each label is modeled with multiple D-dimensional Student's t-distribution, which is heavily tailed and more robust than Gaussian distribution. Expectation-maximization algorithm is adopted to estimate model parameters and to maximize the lower bound on the data log-likelihood from observations. Numerical experiments on various data types are conducted. The performance of the proposed model is compared with that of other mixture models, demonstrating the robustness, accuracy, and effectiveness of our method.

关键词： Expectation-maximization (EM) algorithm non-Gaussian distribution nonsymmetric mixture model (NSMM) unsupervised image segmentation

来源：评论

学校读者我要写书评

暂无评论

Pixel-level clustering network for unsupervised image segmentation

引用

ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE 2024年第PartB期127卷

作者： Hoang, Cuong Manh Kang, Byeongkeun Seoul Natl Univ Sci & Technol Dept Elect Engn 232 Gongneung Ro Seoul 01811 South Korea

While image segmentation is crucial in various computer vision applications, such as autonomous driving, grasping, and robot navigation, annotating all objects at the pixel-level for training is nearly impossible. There-fore, the study of unsupervised image segmentation methods is essential. In this paper, we present a pixel-level clustering framework for segmenting images into regions without using ground truth annotations. The proposed framework includes feature embedding modules with an attention mechanism, a feature statistics computing module, image reconstruction, and superpixel segmentation to achieve accurate unsupervised segmentation. Additionally, we propose a training strategy that utilizes intra-consistency within each superpixel, inter-similarity/dissimilarity between neighboring superpixels, and structural similarity between images. To avoid potential over-segmentation caused by superpixel-based losses, we also propose a post-processing method. Furthermore, we present an extension of the proposed method for unsupervised semantic segmentation. We conducted experiments on three publicly available datasets (Berkeley segmentation dataset, PASCAL VOC 2012 dataset, and COCO-Stuff dataset) to demonstrate the effectiveness of the proposed framework. The experimental results show that the proposed framework outperforms previous state-of-the-art methods.

关键词： unsupervised image segmentation Convolutional neural networks Clustering unsupervised semantic segmentation

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：