检索结果-内蒙古大学图书馆

A Multi-Armed Bandits Learning-Based Approach to Service Caching in Edge Computing Environment 30th

学校读者我要写书评

暂无评论

A Multi-Armed Bandits Learning-Based Approach to Service Ca...

30th International Conference on Web Services, ICWS 2023

作者： Li, Jinpeng Zhao, Jiale Chen, Peng Xia, Yunni Li, Fan Li, Yin Zeng, Feng Liu, Hui School of Computer Chongqing University Chongqing400030 China School of Computer and Software Engineering Xihua University Chengdu610039 China Key Laboratory of Fundamental Synthetic Vision Graphics and Image Science for National Defense Sichuan University Chengdu610065 China Guangzhou Institute of Software Application Technology Guangzhou510990 China Limited Shenzhen518129 China School of Computer Science and Technology Beijing Institute of Technology Beijing100083 China

ISBN: (纸本)9783031448355

Mobile edge computing (MEC) is a newly emerging concept that provides significant local computing power and reduces end-to-end latency. In MEC environments, caching frequently accessed services on edge servers effectively reduces latency and improves system responsiveness. An ongoing research topic in such a cachable MEC context is to design novel algorithms for yielding high-quality caching decision that guarantee high user-perceived quality-of-service (QoS) and high system responsiveness of delivery of cached content with the difference of caching capacities of edge servers and diversified content popularity appropriately addressed. In this article, we propose a multi-armed bandits learning-based method busing a Thompson sampling for generating caching decisions. We introduce a genetic multi-armed bandits algorithm (GMAB), which synthesizes the genetic algorithm (GA) and multi-armed bandits (MAB), for optimizing caching effectiveness with timing and space constraints. The experiment results show that GMAB outperforms traditional methods in terms of multiple aspects. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Genetic algorithms

Direct Elastic Unrollings of Painted Pottery Surfaces from Sparse Image Sets

学校读者我要写书评

暂无评论

Direct Elastic Unrollings of Painted Pottery Surfaces from S...

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

作者： Houska, Peter Lengauer, Stefan Karl, Stephan Preiner, Reinhold Graz University of Technology Institute of Computer Graphics and Knowledge Visualization Austria University of Graz Institute of Classics Austria

ISBN: (纸本)9783038681410

An important task in archaeological research is the comparison of painted motifs on ancient vessels and the analysis of their painting style. Ideally, the pottery objects are available as scanned 3D models, from which the painted surface can be unrolled and potential distortions minimized, so that the vase painting and its individual motifs can be directly inspected. Unfortunately, the percentage of digitally captured vessels is small compared to the large body of cataloged photographs. In this paper, we present a method that creates distortion-minimized unrollings of painted pottery surfaces directly from a small set of photographs. We achieve this by exploiting prior knowledge about the data, namely that most objects exhibit rotational symmetry and that strict guidelines were followed when capturing photographs of the ancient vases. Based on the distinctly visible object silhouettes in the photographs we are able to extract proxy geometries of the objects which we encode as per-view geometric maps. By stitching the single-view data, we obtain a combined map capturing the geometry and texture of the entire painted surface. This enables us to minimize typical projective distortions by elastic relaxation. Our pipeline works entirely in 2D image space, circumventing time-consuming 3D scans and surface reconstructions of (often inaccessible) vessels. Using a combination of CPU-based image processing and GPU-based relaxation, results are produced in only a few minutes. © 2021 The Eurographics Association.

关键词： Geometry

Surgical Phase Recognition for different hospitals

学校读者我要写书评

暂无评论

Current Directions in Biomedical Engineering 2023年第1期9卷 315-318页

作者： Wisotzky, Eric L. Beckmann, Sophie Eisert, Peter Renz-Kiefel, Lasse Hilsmann, Anna Lünse, Sebastian Mantke, René Fraunhofer Heinrich-Hertz-Institute HHI & Humboldt-University Berlin Germany Computer Vision & Graphics Fraunhofer Heinrich-Hertz-Institute HHI Berlin Germany Brandenburg Medical School Department of Surgery University Hospital Brandenburg Germany Faculty of Health Sciences Joint Faculty of the Brandenburg University of Technology Cottbus - Senftenberg Brandenburg Medical School Theodor Fontane Neuruppin Germany University of Potsdam & Department of Surgery University Hospital Brandenburg Germany

Surgical phase recognition is an important aspect of surgical workflow analysis, as it allows an automatic analysis of the performance and efficiency of surgical procedures. A big challenge for training a neural network for surgical phase recognition is the availability of training data and the large (visual) variability in procedures of different surgeons. Hence, a network must be able to generalize to new data. In this paper, we present an adaptation of a Temporal Convolutional Network for surgical phase recognition in order to ensure the generalization of the network to new scenes with different conditions on the example of cholecystectomy. We used publicly available datasets of 104 surgeries from four different centers for training. The results showed that the network was able to generalize to new scenes and we obtained recognition results with accuracy up to 82% on our own six captured surgeries, performed in a different hospital. This performance is similar for test data from the hospitals of the training data, suggesting that the network can well generalize to new surgical rooms and surgeons. The findings have important implications for the development of automated surgical decision support systems that can be applied in a variety of real-world surgical settings. © 2023 the author(s), published by Walter de Gruyter Berlin/Boston.

关键词： Hospitals

Training β-VAE by Aggregating a Learned Gaussian Posterior with a Decoupled Decoder

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Li, Jianning Fragemann, Jana Ahmadi, Seyed-Ahmad Kleesiek, Jens Egger, Jan Institute for AI in Medicine University Medicine Essen Essen Germany Institute of Computer Graphics and Vision Graz University of Technology Graz Austria NVIDIA Munich Germany

The reconstruction loss and the Kullback-Leibler divergence (KLD) loss in a variational autoencoder (VAE) often play antagonistic roles, and tuning the weight of the KLD loss in β-VAE to achieve a balance between the two losses is a tricky and dataset-specific task. As a result, current practices in VAE training often result in a trade-off between the reconstruction fidelity and the continuity/disentanglement of the latent space, if the weight β is not carefully tuned. In this paper, we present intuitions and a careful analysis of the antagonistic mechanism of the two losses, and propose, based on the insights, a simple yet effective two-stage method for training a VAE. Specifically, the method aggregates a learned Gaussian posterior z ∼ qθ(z|x) with a decoder decoupled from the KLD loss, which is trained to learn a new conditional distribution pφ(x|z) of the input data x. Experimentally, we show that the aggregated VAE maximally satisfies the Gaussian assumption about the latent space, while still achieves a reconstruction error comparable to when the latent space is only loosely regularized by N(0, I). The proposed approach does not require hyperparameter (i.e., the KLD weight β) tuning given a specific dataset as required in common VAE training practices. We evaluate the method using a medical dataset intended for 3D skull reconstruction and shape completion, and the results indicate promising generative capabilities of the VAE trained using the proposed method. Besides, through guided manipulation of the latent variables, we establish a connection between existing autoencoder (AE)-based approaches and generative approaches, such as VAE, for the shape completion problem. Codes and pre-trained weights are available at https://***/Jianningli/skullVAE. © 2022, CC BY-NC-SA.

关键词： Economic and social effects

Enabling and Assessing Trust when Cooperating with Robots in Disaster Response (EASIER)

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Frering, Laurent Eder, Matthias Kubicek, Bettina Albert, Dietrich Kalkofen, Denis Gschwandtner, Thomas Krajnz, Heimo Steinbauer-Wagner, Gerald The Institute of Software Technology Graz University of Technology Graz Austria The Institute of Psychology University of Graz Graz Austria The Institute of Computer Graphics and Vision Graz University of Technology Graz Austria Rosenbauer International AG Linz Austria Professional Fire Brigade Graz Graz Austria

This paper presents a conceptual overview of the EASIER project and its scope. EASIER focuses on supporting emergency forces in disaster response scenarios with a semi-autonomous mobile manipulator. Specifically, we examine the operator's trust in the system and his/her cognitive load generated by its use. We plan to address different research topics, exploring how shared autonomy, interaction design, and transparency relate to trust and cognitive load. Another goal is to develop non-invasive methods to continuously measure trust and cognitive load in the context of disaster response using a multilevel approach. This project is conducted by multiple academic partners specializing in artificial intelligence, interaction design, and psychology, as well as an industrial partner for disaster response equipment and end-users for framing the project and the experiments in real use-cases. © 2022, CC BY.

关键词： Noninvasive medical procedures

SAILOR: Scaling Anchors via Insights into Latent Object Representation

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Malić, Dušan Fruhwirth-Reisinger, Christian Possegger, Horst Bischof, Horst Institute of Computer Graphics and Vision Graz University of Technology Austria Christian Doppler Laboratory for Embedded Machine Learning Austria

LiDAR 3D object detection models are inevitably biased towards their training dataset. The detector clearly exhibits this bias when employed on a target dataset, particularly towards object sizes. However, object sizes vary heavily between domains due to, for instance, different labeling policies or geographical locations. State-of-the-art unsupervised domain adaptation approaches outsource methods to overcome the object size bias. Mainstream size adaptation approaches exploit target domain statistics, contradicting the original unsupervised assumption. Our novel unsupervised anchor calibration method addresses this limitation. Given a model trained on the source data, we estimate the optimal target anchors in a completely unsupervised manner. The main idea stems from an intuitive observation: by varying the anchor sizes for the target domain, we inevitably introduce noise or even remove valuable object cues. The latent object representation, perturbed by the anchor size, is closest to the learned source features only under the optimal target anchors. We leverage this observation for anchor size optimization. Our experimental results show that, without any retraining, we achieve competitive results even compared to state-of-the-art weakly-supervised size adaptation approaches. In addition, our anchor calibration can be combined with such existing methods, making them completely unsupervised. © 2022, CC BY.

关键词： Anchors

Quantum Transport in Open Spin Chains using Neural-Network Quantum States

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Mellak, Johannes Arrigoni, Enrico Pock, Thomas von der Linden, Wolfgang Institute of Theoretical and Computational Physics Graz University of Technology Petersgasse 16/II GrazA-8010 Austria Institute of Computer Graphics and Vision Graz University of Technology Inffeldgasse 16/II GrazA-8010 Austria

In this work we study the treatment of asymmetric open quantum systems with neural-networks based on the restricted Boltzmann machine. In particular, we are interested in the non-equilibrium steady state current in the boundary-driven (anisotropic) Heisenberg spin chain. We address previously published difficulties in treating asymmetric dissipative systems with neural-network quantum states and Monte-Carlo sampling and present an optimization method and a sampling technique that can be used to obtain high-fidelity steady state approximations of such systems. We point out some inherent symmetries of the Lindblad operator under consideration and exploit them during sampling. We show that local observables are not always a good indicator of the quality of the approximation and finally present results for the spin current that are in agreement with known results of simple open Heisenberg chains. Copyright © 2022, The Authors. All rights reserved.

关键词： Monte Carlo methods

MCTS with Refinement for Proposals Selection Games in Scene Understanding

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Stekovic, Sinisa Rad, Mahdi Moradi, Alireza Fraundorfer, Friedrich Lepetit, Vincent Institute for Computer Graphics and Vision Graz University of Technology Graz Austria Université Paris-Est École des Ponts ParisTech Paris France

We propose a novel method applicable in many scene understanding problems that adapts the Monte Carlo Tree Search (MCTS) algorithm, originally designed to learn to play games of high-state complexity. From a generated pool of proposals, our method jointly selects and optimizes proposals that minimize the objective term. In our first application for floor plan reconstruction from point clouds, our method selects and refines the room proposals, modelled as 2D polygons, by optimizing on an objective function combining the fitness as predicted by a deep network and regularizing terms on the room shapes. We also introduce a novel differentiable method for rendering the polygonal shapes of these proposals. Our evaluations on the recent and challenging Structured3D and Floor-SP datasets show significant improvements over the state-of-the-art, without imposing hard constraints nor assumptions on the floor plan configurations. In our second application, we extend our approach to reconstruct general 3D room layouts from a color image and obtain accurate room layouts. We also show that our differentiable renderer can easily be extended for rendering 3D planar polygons and polygon embeddings. Our method shows high performance on the Matterport3D-Layout dataset, without introducing hard constraints on room layout configurations. Copyright © 2022, The Authors. All rights reserved.

关键词： Floors

End-to-end Trainable Deep Neural Network for Robotic Grasp Detection and Semantic Segmentation from RGB

学校读者我要写书评

暂无评论

End-to-end Trainable Deep Neural Network for Robotic Grasp D...

IEEE International Conference on Robotics and Automation (ICRA)

作者： Stefan Ainetter Friedrich Fraundorfer Institute of Computer Graphics and Vision Graz University of Technology Graz Austria

In this work, we introduce a novel, end-to-end trainable CNN-based architecture to deliver high quality results for grasp detection suitable for a parallel-plate gripper, and semantic segmentation. Utilizing this, we propose a novel refinement module that takes advantage of previously calculated grasp detection and semantic segmentation and further increases grasp detection accuracy. Our proposed network delivers state-of-the-art accuracy on two popular grasp dataset, namely Cornell and Jacquard. As additional contribution, we provide a novel dataset extension for the OCID dataset, making it possible to evaluate grasp detection in highly challenging scenes. Using this dataset, we show that semantic segmentation can additionally be used to assign grasp candidates to object classes, which can be used to pick specific objects in the scene.

关键词： Deep learning Automation Conferences Semantics Feature extraction Convolutional neural networks Grippers