检索结果-内蒙古大学图书馆

Enhancing Fairness of Visual Attribute Predictors

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Hänel, Tobias Kumar, Nishant Schlesinger, Dmitrij Li, Mengze Ünal, Erdem Eslami, Abouzar Gumhold, Stefan Computer Graphics and Visualization TU Dresden Germany Carl Zeiss Meditec AG Munich Germany

The performance of deep neural networks for image recognition tasks such as predicting a smiling face is known to degrade with under-represented classes of sensitive attributes. We address this problem by introducing fairness-aware regularization losses based on batch estimates of Demographic Parity, Equalized Odds, and a novel Intersection-over-Union measure. The experiments performed on facial and medical images from CelebA, UTKFace, and the SIIM-ISIC melanoma classification challenge show the effectiveness of our proposed fairness losses for bias mitigation as they improve model fairness while maintaining high classification performance. To the best of our knowledge, our work is the first attempt to incorporate these types of losses in an end-to-end training scheme for mitigating biases of visual attribute predictors. Our code is available at this https URL. © 2022, CC BY.

关键词： Deep neural networks

Teaching Distributed and Heterogeneous Robotic Cells 19

学校读者我要写书评

暂无评论

Teaching Distributed and Heterogeneous Robotic Cells

19th IEEE Annual Consumer Communications and Networking Conference, CCNC 2022

作者： Mey, Johannes Ebert, Sebastian Lin, Tianfang Nguyen, Giang T. Gumhold, Stefan Asmann, Uwe Technische Universität Chair of Software Engineering Dresden Germany Technische Universität Chair of Computer Graphics and Visualization Dresden Germany Technische Universität Chair of Haptic Communication Systems Dresden Germany Dresden Germany

ISBN: (纸本)9781665431620

Teaching heterogeneous robotic cells is difficult and time-consuming. We present a context-aware robot teaching solution based on an open-source framework that decouples the task instruction from the task execution to simplify the teaching workflow significantly. To demonstrate the advantages of the solution, a human operator uses a VR headset and controllers to teach a virtual robot to perform a task, e.g., pick-and-place in a virtual world. The task is automatically adapted to different settings of operation cells and executed by physical robots located at different geographical locations. © 2022 IEEE.

关键词： Virtual reality

Fully Automatic Mechanical Scan Range Extension and Signal to Noise Optimization of a Lens-Shifted Structured Light System

学校读者我要写书评

暂无评论

Fully Automatic Mechanical Scan Range Extension and Signal t...

2021 Eurographics Workshop on graphics and Cultural Heritage, EG GCH 2021

作者： Kutlu, H. Ritz, M. Santos, P. Fellner, D.W. Fraunhofer IGD Germany Graz University of Technology Institute of Computer Graphics and Knowledge Visualization Austria TU Darmstadt Germany

ISBN: (纸本)9783038681410

Digitization of cultural heritage is of growing importance, both for its preservation for coming generations in the face of looming dangers of natural decay or intentional destruction, and current generations, that increasingly have access to virtual cultural heritage for interactive exploring or scientific analysis. These goals can only be achieved by 3D replicas at reasonable quality and resolution, to come as close as possible to the original. This brings about several challenges to overcome. The challenge of digitizing huge numbers of artefacts is addressed by CultLab3D, the first fully automatic 3D digitization system. Another challenge is the size of objects, as each digitization system is designed for a certain optimum measurement range, leaving which results in loss of quality. Due to optical and mechanical constraints, most systems are not able to faithfully reconstruct objects under a certain size limit in their full geometric detail. Historic coins are one good example, where the deterioration of the surface structure in most cases has progressed to a degree that it not even is perceptible through the fingernail. This challenge is addressed by a modular extension of CultLab3D, the MesoScanner, which is a structured light system that breaks limits in depth resolution through a mechanical lens-shifting extension, allowing physically shifting of fringe patterns on top of the well-known multi-period phase shift method. This is where this work adds two major improvements: First, the signal to noise ratio and thus reconstruction quality has been improved significantly through several algorithmic processing steps. Second, the physical limitation of the measurement range was removed using a 2D actuator steering the object mount, thus allowing for a measurement range at theoretically arbitrary size. This opens up the fully automatic handling of two scenarios: Complete digitization of objects exceeding the measurement range, and unsupervised digitization of large c

关键词： Deterioration

FusionINN: Decomposable Image Fusion for Brain Tumor Monitoring

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Kumar, Nishant Tao, Ziyan Singh, Jaikirat Li, Yang Sun, Peiwen Zhao, Binghui Gumhold, Stefan Chair of Computer Graphics and Visualization Faculty of Computer Science Technische Universität Dresden Dresden Germany School of Computer Science and Engineering Shandong University of Science and Technology Qingdao China Department of Radiology Shanghai Tenth People’s Hospital Tongji University Medical School Shanghai China

Image fusion typically employs non-invertible neural networks to merge multiple source images into a single fused image. However, for clinical experts, solely relying on fused images may be insufficient for making diagnostic decisions, as the fusion mechanism blends features from source images, thereby making it difficult to interpret the underlying tumor pathology. We introduce FusionINN, a novel decomposable image fusion framework, capable of efficiently generating fused images and also decomposing them back to the source images. FusionINN is designed to be bijective by including a latent image alongside the fused image, while ensuring minimal transfer of information from the source images to the latent representation. To the best of our knowledge, we are the first to investigate the decomposability of fused images, which is particularly crucial for life-sensitive applications such as medical image fusion compared to other tasks like multi-focus or multiexposure image fusion. Our extensive experimentation validates FusionINN over existing discriminative and generative fusion methods, both subjectively and objectively. Moreover, compared to a recent denoising diffusion-based fusion model, our approach offers faster and qualitatively better fusion results. The source code of the FusionINN framework is available at: https://***/nish03/FusionINN. © 2024, CC BY.

关键词： Image fusion

Automated 3D mass digitization for the GLAM sector

学校读者我要写书评

暂无评论

Automated 3D mass digitization for the GLAM sector

Archiving 2020 Online: Digitization, Preservation, and Access

作者： Santos, Pedro Tausch, Reimar Domajnko, Matevz Ritz, Martin Knuth, Martin Fellner, Dieter Fraunhofer Institute for Computer Graphics Research TU-Darmstadt Germany Graz University of Technology Institute of Computer Graphics and Knowledge Visualization Austria

The European Cultural Heritage Strategy for the 21st century has led to an increased demand for fast, efficient and faithful 3D digitization technologies for cultural heritage artefacts. Yet, unlike the digital acquisition of cultural goods in 2D which is widely used and automated today, 3D digitization often still requires significant manual intervention, time and money. To overcome this, the authors have developed CultLab3D, the world's first fully automatic 3D mass digitization technology for collections of three-dimensional objects. 3D scanning robots such as the CultArm3D-P are specifically designed to automate the entire 3D digitization process thus allowing to capture and archive objects on a large-scale and produce highly accurate photo-realistic representations. © 2020 Society for Imaging Science and Technology

关键词：

Learning to reconstruct the bubble distribution with conductivity maps using Invertible Neural Networks and Error Diffusion

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Kumar, N. Krause, L. Wondrak, T. Eckert, S. Eckert, K. Gumhold, S. Chair of Computer Graphics and Visualization TU Dresden Germany Institute of Process Engineering and Environmental Technology TU Dresden Germany Institute of Fluid Dynamics Helmholtz-Zentrum Dresden-Rossendorf Dresden Germany

Electrolysis is crucial for eco-friendly hydrogen production, but gas bubbles generated during the process hinder reactions, reduce cell efficiency, and increase energy consumption. Additionally, these gas bubbles cause changes in the conductivity inside the cell, resulting in corresponding variations in the induced magnetic field around the cell. Therefore, measuring these gas bubble-induced magnetic field fluctuations using external magnetic sensors and solving the inverse problem of Biot-Savart’s Law allows for estimating the conductivity in the cell and, thus, bubble size and location. However, determining high-resolution conductivity maps from only a few induced magnetic field measurements is an ill-posed inverse problem. To overcome this, we exploit Invertible Neural Networks (INNs) to reconstruct the conductivity field. Our qualitative results and quantitative evaluation using random error diffusion show that INN achieves far superior performance compared to Tikhonov regularization. © 2023, CC BY.

关键词： Cells

Polar, Spherical and Orthogonal Space Subdivisions for an Algorithm Acceleration: O(1) Point-in-Polygon/Polyhedron Test

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Skala, Vaclav The University of West Bohemia Faculty of Applied Sciences Department .of Computer Science and Engineering Center of Computer Graphics and Visualization Univerzitni 8 PlzenCZ 30614 Czech Republic

Acceleration of algorithms is becoming a crucial problem, if larger data sets are to be processed. Evaluation of algorithms is mostly done by using computational geometry approach and evaluation of computational complexity. However in today’s engineering problems this approach does not respect that number of processed items is always limited and a significant role plays also speed of read/write operations. One general method how to speed up an algorithm is application of space subdivision technique and usually the orthogonal space subdivision is used. In this paper non-orthogonal subdivisions are described. The proposed approach can significantly improve memory consumption and run-time complexity. The proposed modified space subdivision techniques are demonstrated on two simple problems Point-in-Convex Polygon and Point-in-Convex Polyhedron *** Codes 65D17, 65D18 © 2022, CC BY.

关键词： Computational geometry

Improving Uncertainty-Error Correspondence in Deep Bayesian Medical Image Segmentation

学校读者我要写书评

暂无评论

TechRxiv

TechRxiv 2023年

作者： Mody, Prerak de Plaza, Nicolas Chaves Astrenidou, Eleftheria de Ridder, Mischa Hoekstra, Nienke Hildebrandt, Klaus Staring, Marius Radiology Leiden University Medical Center Netherlands The Department of Radiation Oncology Leiden University Medical Center Netherlands University Medical Center Utrecht Netherlands The Computer Graphics and Visualization Lab TU Delft Netherlands

Increased usage of automated tools like deep learning in medical image segmentation has alleviated the bottleneck of manual contouring. This has shifted manual labour to quality assessment (QA) of automated contours which involves detecting errors and correcting them. A potential solution to semi-automated QA is to use deep Bayesian uncertainty to recommend potentially erroneous regions, thus reducing time spent on error detection. Previous work has investigated the correspondence between uncertainty and error, however, no work has been done on improving the "utility" of Bayesian uncertainty maps such that it is only present in inaccurate regions and not in the accurate ones. Our work trains the FlipOut model with the Accuracy-vs-Uncertainty (AvU) loss which promotes uncertainty to be present only in inaccurate regions. We apply this method on datasets of two radiotherapy body sites, namely CT scans of head and neck and prostate MRs. Uncertainty heatmaps (i.e. predictive entropy) are evaluated using ROC and Precision-Recall curves. Numerical results show that when compared to the Bayesian baseline the proposed method successfully suppresses uncertainty for accurate voxels, with similar presence of uncertainty for inaccurate voxels. Code to reproduce experiments is available on https://***/prerakmody/ bayesuncertainty-error-correspondence. © 2023, CC BY.

关键词： computerized tomography

Foreword to the special section on 3D object retrieval 2024 symposium (3DOR2024)

学校读者我要写书评

暂无评论

computers and graphics 2025年 129卷

作者： Bustos, Benjamin Biasotti, Silvia Veltkamp, Remco C. Schreck, Tobias Sipiran, Ivan Department of Computer Science University of Chile Chile Chile Istituto di Matematica Applicata e Tecnologie Informatiche "E. Magenes" - CNR Italy Department of Information and Computing Sciences Utrecht University Netherlands Institute of Computer Graphics and Visualization Technical University of Graz Austria