检索结果-内蒙古大学图书馆

One-sided Frank-Wolfe algorithms for saddle problems

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Kolmogorov, Vladimir Pock, Thomas Institute of Science and Technology Austria Institute of Computer Graphics and Vision Graz University of Technology

We study a class of convex-concave saddle-point problems of the form minx maxy(Kx, y) + fP(x) - h∗(y) where K is a linear operator, fP is the sum of a convex function f with a Lipschitz-continuous gradient and the indicator function of a bounded convex polytope P, and h∗ is a convex (possibly nonsmooth) function. Such problem arises, for example, as a Lagrangian relaxation of various discrete optimization problems. Our main assumptions are the existence of an efficient linear minimization oracle (lmo) for fP and an efficient proximal map (prox) for h∗ which motivate the solution via a blend of proximal primal-dual algorithms and Frank-Wolfe algorithms. In case h∗ is the indicator function of a linear constraint and function f is quadratic, we show a O(1/n2) convergence rate on the dual objective, requiring O(n log n) calls of lmo. If the problem comes from the constrained optimization problem minx∈d{fP(x) | Ax - b = 0} then we additionally get bound O(1/n2) both on the primal gap and on the infeasibility gap. In the most general case, we show a O(1/n) convergence rate of the primal-dual gap again requiring O(n log n) calls of lmo. To the best of our knowledge, this improves on the known convergence rates for the considered class of saddle-point problems. We show applications to labeling problems frequently appearing in machine learning and computer vision. Copyright © 2021, The Authors. All rights reserved.

关键词： Mathematical operators

Removing fences from sweep motion videos using global 3D reconstruction and fence-aware light field rendering

学校读者我要写书评

暂无评论

Computational Visual Media 2019年第1期5卷 21-32页

作者： Chanya Lueangwattana Shohei Mori Hideo Saito Department of Science and Technology Keio University Institute of Computer Graphics and Vision Graz University of Technology

Diminishing the appearance of a fence in an image is a challenging research area due to the characteristics of fences(thinness, lack of texture, etc.) and the need for occluded background restoration. In this paper, we describe a fence removal method for an image sequence captured by a user making a sweep motion, in which occluded background is potentially observed. To make use of geometric and appearance information such as consecutive images, we use two well-known approaches: structure from motion and light field rendering. Results using real image sequences show that our method can stably segment fences and preserve background details for various fence and background combinations. A new video without the fence, with frame coherence, can be successfully provided.

关键词： video fence video repair diminished reality(DR) structure from motion(SfM) light field rendering(LFR)

Weighting Attributes Based on the Greedy Algorithm Properties

学校读者我要写书评

暂无评论

Procedia computer Science 2024年 246卷 4883-4892页

作者： Beata Zielosko Urszula Stańczyk Kamil Jabloński University of Silesia in Katowice Institute of Computer Science Bȩdzińska 39 41-200 Sosnowiec Poland Department of Computer Graphics Vision and Digital Systems Faculty of Automatic Control Electronics and Computer Science Silesian University of Technology Akademicka 2A 44-100 Gliwice Poland

Estimation of importance for considered features is an important issue for any knowledge exploration process and it can be executed by a variety of approaches. In the research reported in this study, the primary aim was the development of a methodology for creating attribute rankings. Based on the properties of the greedy algorithm for inducing decision rules, a new application of this algorithm has been proposed. Instead of constructing a single ordering of features, attributes were weighted multiple times. The input datasets were discretised with several algorithms representing supervised and unsupervised discretisation approaches. Each resulting discrete data variant was exploited to construct a ranking of attributes. The effectiveness of the obtained rankings was confirmed through a rule filtering process governed by weighted attributes. The methodology was applied to the stylometric task of authorship attribution. The experimental outcomes demonstrate the value of the proposed research method, as it generally led to improved predictions while taking into account a noticeably decreased sets of attributes and decision rules.

关键词： Greedy algorithm Weighting attributes Decision rules Rule filtering Authorship attribution

MATE: Masked Autoencoders are Online 3D Test-Time Learners

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Mirza, M. Jehanzeb Shin, Inkyu Lin, Wei Schriebl, Andreas Sun, Kunyang Choe, Jaesung Possegger, Horst Kozinski, Mateusz Kweon, In So Yoon, Kuk-Jin Bischof, Horst Institute for Computer Graphics and Vision Graz University of Technology Austria Christian Doppler Laboratory for Embedded Machine Learning Korea Republic of Southeast University China

Our MATE is the first Test-Time-Training (TTT) method designed for 3D data, which makes deep networks trained for point cloud classification robust to distribution shifts occurring in test data. Like existing TTT methods from the 2D image domain, MATE also leverages test data for adaptation. Its test-time objective is that of a Masked Autoencoder: a large portion of each test point cloud is removed before it is fed to the network, tasked with reconstructing the full point cloud. Once the network is updated, it is used to classify the point cloud. We test MATE on several 3D object classification datasets and show that it significantly improves robustness of deep networks to several types of corruptions commonly occurring in 3D point clouds. We show that MATE is very efficient in terms of the fraction of points it needs for the adaptation. It can effectively adapt given as few as 5% of tokens of each test sample, making it extremely lightweight. Our experiments show that MATE also achieves competitive performance by adapting sparsely on the test data, which further reduces its computational overhead, making it ideal for real-time applications. © 2022, CC BY.

关键词： Classification (of information)

Mapillary Planet-Scale Depth Dataset 16th

学校读者我要写书评

暂无评论

Mapillary Planet-Scale Depth Dataset

16th European Conference on computer vision, ECCV 2020

作者： Antequera, Manuel López Gargallo, Pau Hofinger, Markus Bulò, Samuel Rota Kuang, Yubin Kontschieder, Peter Facebook Menlo Park United States Institute of Computer Graphics and Vision Graz University of Technology Graz Austria

ISBN: (纸本)9783030585358

Learning-based methods produce remarkable results on single image depth tasks when trained on well-established benchmarks, however, there is a large gap from these benchmarks to real-world performance that is usually obscured by the common practice of fine-tuning on the target dataset. We introduce a new depth dataset that is an order of magnitude larger than previous datasets, but more importantly, contains an unprecedented gamut of locations, camera models and scene types while offering metric depth (not just up-to-scale). Additionally, we investigate the problem of training single image depth networks using images captured with many different cameras, validating an existing approach and proposing a simpler alternative. With our contributions we achieve excellent results on challenging benchmarks before fine-tuning, and set the state of the art on the popular KITTI dataset after fine-tuning. The dataset is available at ***/dataset/depth. © 2020, Springer Nature Switzerland AG.

关键词： Cameras

CC-DCNet: Dynamic Convolutional Neural Network with Contrastive Constraints for Identifying Lung Cancer Subtypes on Multi-modality Images

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Jin, Yuan Ma, Gege Chen, Geng Lyu, Tianling Egger, Jan Lyu, Junhui Zhang, Shaoting Zhu, Wentao Zhejiang Lab 311121 China Institute of Computer Graphics and Vision Graz University of Technology Graz8010 Austria School of Computer Science and Engineering Northwestern Polytechnical University Shaanxi Xi’an710072 China The Zhejiang University School of Medicine Sir Run Run Shaw Hospital Hangzhou310016 China Shanghai Artificial Intelligence Laboratory Shanghai200120 China

The accurate diagnosis of pathological subtypes of lung cancer is of paramount importance for follow-up treatments and prognosis managements. Assessment methods utilizing deep learning technologies have introduced novel approaches for clinical diagnosis. However, the majority of existing models rely solely on single-modality image input, leading to limited diagnostic accuracy. To this end, we propose a novel deep learning network designed to accurately classify lung cancer subtype with multi-dimensional and multi-modality images, i.e., CT and pathological images. The strength of the proposed model lies in its ability to dynamically process both paired CT-pathological image sets as well as independent CT image sets, and consequently optimize the pathology-related feature extractions from CT images. This adaptive learning approach enhances the flexibility in processing multi-dimensional and multi-modality datasets and results in performance elevating in the model testing phase. We also develop a contrastive constraint module, which quantitatively maps the cross-modality associations through network training, and thereby helps to explore the "gold standard" pathological information from the corresponding CT scans. To evaluate the effectiveness, adaptability, and generalization ability of our model, we conducted extensive experiments on a large-scale multi-center dataset and compared our model with a series of state-of-the-art classification models. The experimental results demonstrated the superiority of our model for lung cancer subtype classification, showcasing significant improvements in accuracy metrics such as ACC, AUC, and F1-score. Copyright © 2024, The Authors. All rights reserved.

关键词： Lung cancer

Automatically Annotating Indoor Images with CAD Models via RGB-D Scans

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Ainetter, Stefan Stekovic, Sinisa Fraundorfer, Friedrich Lepetit, Vincent Institute for Computer Graphics and Vision Graz University of Technology Graz Austria LIGM École des Ponts Univ Gustave Eiffel CNRS Marne-la-Vallée France

We present an automatic method for annotating images of indoor scenes with the CAD models of the objects by relying on RGB-D scans. Through a visual evaluation by 3D experts, we show that our method retrieves annotations that are at least as accurate as manual annotations, and can thus be used as ground truth without the burden of manually annotating 3D data. We do this using an analysis-by-synthesis approach, which compares renderings of the CAD models with the captured scene. We introduce a'cloning procedure' that identifies objects that have the same geometry, to annotate these objects with the same CAD models. This allows us to obtain complete annotations for the ScanNet dataset and the recent ARKitScenes dataset. Source code and data will be available at https://***/stefan-ainetter/SCANnotate. Copyright © 2022, The Authors. All rights reserved.

关键词： computer aided design

MultiAR: A Multi-User Augmented Reality Platform for Biomedical Education

学校读者我要写书评

暂无评论

MultiAR: A Multi-User Augmented Reality Platform for Biomedi...

Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC)

作者： Markus Perz Gijs Luijten Jens Kleesiek Dieter Schmalstieg Jan Egger Christina Gsaxner Institute of Computer Graphics and Vision Graz University of Technology Graz Austria Institute for Artificial Intelligence in Medicine University Medicine Essen Essen Germany Cancer Research Center Cologne Essen West German Cancer Center Essen Germany Institute for Visualization and Interactive Systems University of Stuttgart Stuttgart Germany Virtual and Extended Reality in Medicine (ZvRM) University Hospital Essen Essen Germany

ISBN: (数字)9798350371499

ISBN: (纸本)9798350371505

This paper addresses the growing integration of Augmented Reality (AR) in biomedical sciences, emphasizing collaborative learning experiences. We present MultiAR, a versatile, domain-specific platform enabling multi-user interactions in AR for biomedical education. Unlike platform-specific solutions, MultiAR supports various AR devices, including handheld and head-mounted options. The framework extends across domains, augmenting biomedical education applications with collaborative capabilities. We define essential requirements for a multi-user AR framework in education, detail MultiAR’s design and implementation, and comprehensively evaluate it using anatomy education examples. Quantitative and qualitative analyses, covering system performance, accuracy metrics, and a user study with 20 participants, highlight the urgent need for a tailored collaborative AR platform in biomedical education. Results underscore enthusiasm for collaborative AR technology, endorsing MultiAR as an accessible, versatile solution for developers and end-users in biomedical education.

关键词： Measurement Accuracy Federated learning System performance Education Collaboration Anatomy Engineering in medicine and biology Augmented reality

Stochastic Modeling of Inhomogeneities in the Aortic Wall and Uncertainty Quantification using a Bayesian Encoder-Decoder Surrogate

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Ranftl, Sascha Rolf-Pissarczyk, Malte Wolkerstorfer, Gloria Pepe, Antonio Egger, Jan von der Linden, Wolfgang Holzapfel, Gerhard A. Graz University of Technology Institute of Theoretical and Computational Physics Austria Graz Center for Computational Engineering Graz University of Technology Austria Graz University of Technology Institute of Biomechanics Austria Graz University of Technology Institute of Computer Graphics and Vision Austria University Medicine Essen Institute for AI in Medicine Essen Germany Department of Structural Analysis Trondheim Norway

Inhomogeneities in the aortic wall can lead to localized stress accumulations, possibly initiating dissection. In many cases, a dissection results from pathological changes such as fragmentation or loss of elastic fibers. But it has been shown that even the healthy aortic wall has an inherent heterogeneous microstructure. Some parts of the aorta are particularly susceptible to the development of inhomogeneities due to pathological changes, however, the distribution in the aortic wall and the spatial extent, such as size, shape, and type, are difficult to predict. Motivated by this observation, we describe the heterogeneous distribution of elastic fiber degradation in the dissected aortic wall using a stochastic constitutive model. For this purpose, random field realizations, which model the stochastic distribution of degraded elastic fibers, are generated over a non-equidistant grid. The random field then serves as input for a uniaxial extension test of the pathological aortic wall, solved with the finite-element (FE) method. To include the microstructure of the dissected aortic wall, a constitutive model developed in a previous study is applied, which also includes an approach to model the degradation of interlamellar elastic fibers. Then to assess the uncertainty in the output stress distribution due to this stochastic constitutive model, a convolutional neural network, specifically a Bayesian encoder-decoder, was used as a surrogate model that maps the random input fields to the output stress distribution obtained from the FE analysis. The results show that the neural network is able to predict the stress distribution of the FE analysis while significantly reducing the computational time. In addition, it provides the probability for exceeding critical stresses within the aortic wall, which could allow for the prediction of delamination or fatal rupture. Copyright © 2022, The Authors. All rights reserved.

关键词： Finite element method