检索结果-内蒙古大学图书馆

Brain tumor cell density estimation from multi-modal MR images based on a synthetic tumor growth model

学校读者我要写书评

暂无评论

Brain tumor cell density estimation from multi-modal MR imag...

15th International Conference on Medical Image Computing and computer-Assisted Intervention, MICCAI 2012

作者： Geremia, Ezequiel Menze, Bjoern H. Prastawa, Marcel Weber, M.-A. Criminisi, Antonio Ayache, Nicholas Asclepios Research Project INRIA Sophia-Antipolis France Computer Science and Artificial Intelligence Laboratory MIT United States Computer Vision Laboratory ETH Zurich Switzerland Scientific Computing and Imaging Institute University of Utah United States Diagnostic and Interventional Radiology Heidelberg University Hospital Germany Machine Learning and Perception Group Microsoft Research Cambridge United Kingdom

ISBN: (纸本)9783642366192

This paper proposes to employ a detailed tumor growth model to synthesize labelled images which can then be used to train an efficient data-driven machine learning tumor predictor. Our MR image synthesis step generates images with both healthy tissues as well as various tumoral tissue types. Subsequently, a discriminative algorithm based on random regression forests is trained on the simulated ground truth to predict the continuous latent tumor cell density, and the discrete tissue class associated with each voxel. The presented method makes use of a large synthetic dataset of 740 simulated cases for training and evaluation. A quantitative evaluation on 14 real clinical cases diagnosed with low-grade gliomas demonstrates tissue class accuracy comparable with state of the art, with added benefit in terms of computational efficiency and the ability to estimate tumor cell density as a latent variable underlying the multimodal image observations. The idea of synthesizing training data to train data-driven learning algorithms can be extended to other applications where expert annotation is lacking or expensive. © 2013 Springer-Verlag.

关键词： Tumors

How to Choose a Reinforcement-learning Algorithm

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Bongratz, Fabian Golkov, Vladimir Mautner, Lukas Libera, Luca Della Heetmeyer, Frederik Czaja, Felix Rodemann, Julian Cremers, Daniel Computer Vision Group Technical University of Munich Germany Munich Center for Machine Learning Germany Department of Statistics Ludwig-Maximilians-Universität Munich Germany

The field of reinforcement learning offers a large variety of concepts and methods to tackle sequential decision-making problems. This variety has become so large that choosing an algorithm for a task at hand can be challenging. In this work, we streamline the process of choosing reinforcement-learning algorithms and action-distribution families. We provide a structured overview of existing methods and their properties, as well as guidelines for when to choose which methods. An interactive version of these guidelines is available online at https://***/.MSC Codes 62M45 © 2024, CC BY-NC-SA.

关键词： Adversarial machine learning

Reinforced imitation: Sample efficient deep reinforcement learning for map-less navigation by leveraging prior demonstrations

学校读者我要写书评

暂无评论

arXiv 2018年

作者： Pfeiffer, M. Shukla, S. Turchetta, M. Cadena, C. Krause, A. Siegwart, R. Nieto, J. Autonomous Systems Lab Zurich Switzerland Computer Vision Lab Zurich Switzerland Learning & Adaptive Systems Group Zurich Switzerland Max Planck ETH Center for Learning Systems ETH Zurich Zurich Switzerland

This work presents a case study of a learning-based approach for target driven map-less navigation. The underlying navigation model is an end-to-end neural network which is trained using a combination of expert demonstrations, imitation learning (IL) and reinforcement learning (RL). While RL and IL suffer from a large sample complexity and the distribution mismatch problem, respectively, we show that leveraging prior expert demonstrations for pre-training can reduce the training time to reach at least the same level of performance compared to plain RL by a factor of 5. We present a thorough evaluation of different combinations of expert demonstrations, different RL algorithms and reward functions, both in simulation and on a real robotic platform. Our results show that the final model outperforms both standalone approaches in the amount of successful navigation tasks. In addition, the RL reward function can be significantly simplified when using pre-training, e.g. by using a sparse reward only. The learned navigation policy is able to generalize to unseen and real-world environments. Copyright © 2018, The Authors. All rights reserved.

关键词： Deep learning

Deep deterministic uncertainty for semantic segmentation

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Mukhoti, Jishnu van Amersfoort, Joost Torr, Philip H.S. Gal, Yarin Oxford Applied & Theoretical Machine Learning Group Department of Computer Science University of Oxford Oxford United Kingdom Torr Vision Group Department of Engineering Science University of Oxford Oxford United Kingdom

We extend Deep Deterministic Uncertainty (DDU) (Mukhoti et al., 2021), a method for uncertainty estimation using feature space densities, to semantic segmentation. DDU enables quantifying and disentangling epistemic and aleatoric uncertainty in a single forward pass through the model. We study the similarity of feature representations of pixels at different locations for the same class and conclude that it is feasible to apply DDU location independently, which leads to a significant reduction in memory consumption compared to pixel dependent DDU. Using the DeepLab-v3+ architecture on Pascal VOC 2012, we show that DDU improves upon MC Dropout and Deep Ensembles while being significantly faster to compute. Copyright © 2021, The Authors. All rights reserved.

关键词： Pixels

LEDNet: Deep Network for Single Image Haze Removal 2018

学校读者我要写书评

暂无评论

LEDNet: Deep Network for Single Image Haze Removal

Proceedings of the 11th Indian Conference on computer vision, Graphics and Image Processing

作者： Akshay Dudhane Subrahmanyam Murala Abhinav Dhall Computer Vision and Pattern Recognition Lab Indian Institute of Technology Ropar India Learning Affect and Semantic Image Analysis Group Indian Institute of Technology Ropar India

ISBN: (纸本)9781450366151

Haze during the bad weather, degrades the visibility of the scene drastically. Degradation of scene visibility varies with respect to the transmission coefficient/map (Tc) of the scene. Estimation of accurate Tc is key step to reconstruct the haze free scene. Previously, local as well as global priors were proposed to estimate the Tc. We, on the other hand, propose integration of local and global approaches to learn both point level and object level Tc. The proposed local encoder decoder network (LEDNet) estimates the scene transmission map in two stages. During first stage, network estimates the point level Tc using parallel convolutional filters and spatial invariance filtering. The second stage comprises of a two level encoder-decoder architecture which anticipates the object level Tc. We also propose, local air-light estimation (LAE) algorithm, which is able to obtain the air-light component of the outdoor scene. Combination of LEDNet and LAE improves the accuracy of haze model to recover the scene radiance. Structural similarity index, mean square error and peak signal to noise ratio are used to evaluate the performance of the proposed approach for single image haze removal. Experiments on benchmark datasets show that LEDNet outperforms the existing state-of-the-art methods for single image haze removal.

关键词： Haze removal transmission map CNN

Fréchet Wavelet Distance: A Domain-Agnostic Metric for Image Generation

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Veeramacheneni, Lokesh Wolter, Moritz Kuehne, Hildegard Gall, Juergen High-Performance Computing and Analytics Lab University of Bonn Bonn53115 Germany Multimodal Learning Group University of Bonn Bonn53115 Germany Computer Vision Group University of Bonn Bonn53115 Germany

Modern metrics for generative learning like Fréchet Inception Distance (FID) demonstrate impressive performance. However, they suffer from various shortcomings, like a bias towards specific generators and datasets. To address this problem, we propose the Fréchet Wavelet Distance (FWD) as a domain-agnostic metric based on Wavelet Packet Transform (Wp). FWD provides a sight across a broad spectrum of frequencies in images with a high resolution, along with preserving both spatial and textural aspects. Specifically, we use Wp to project generated and dataset images to packet coefficient space. Further, we compute Fréchet distance with the resultant coefficients to evaluate the quality of a generator. This metric is general-purpose and dataset-domain agnostic, as it does not rely on any pre-trained network while being more interpretable because of frequency band transparency. We conclude with an extensive evaluation of a wide variety of generators across various datasets that the proposed FWD is able to generalize and improve robustness to domain shift and various corruptions compared to other metrics. © 2023, CC BY.

关键词： Quality control

Fault detection and isolation for systems defined over graphs

学校读者我要写书评

暂无评论

Fault detection and isolation for systems defined over graph...

IEEE Annual Conference on Decision and Control

作者： P. Rapisarda A.R.F. Everts M.K. Camlibel Vision Learning and Control group School of Electronics and Computer Science University of Southampton UK Johann Bernoulli Institute for Mathematics and Computer Science University of Groningen P.O. Box 407 9700 AK the Netherlands

ISBN: (纸本)9781479978878

We consider the problem of fault detection and isolation for a class of linear dynamical systems defined by a graph containing faulty vertices and observer vertices. Using a geometric approach, we provide a characterization of the smallest conditioned invariant subspaces generated by faults in terms of the underlying graph structure. Based on this characterization, we give graph-theoretic conditions guaranteeing fault detectability. In addition, we provide a condition under which fault detectability fails.

关键词： Defect detection detectability DYNAMICAL SYSTEMS vertex head BASES(STRUCTURES)

Improving tag transfer for image annotation using visual and semantic information

学校读者我要写书评

暂无评论

Improving tag transfer for image annotation using visual and...

International Workshop on Content-Based Multimedia Indexing, CBMI

作者： Sergio Rodriguez-Vaamonde Lorenzo Torresani Koldo Espinosa Estibaliz Garrote Computer Vision Area-ICT/ESI Division TECNALIA Zamudio Spain Visual-Learning Group-CS Department Dartmouth College Hanover USA Multimedia Group-Communications Engineering Department University of the Basque Country Bilbao Spain

This paper addresses the problem of image annotation using a combination of visual and semantic information. Our model involves two stages: a Nearest Neighbor computation and a tag transfer stage that collects the final annotations. For the latter stage, several algorithms have been implemented in the past using labels' information or including implicitly some visual features. In this paper we propose a novel algorithm for tag transfer that takes advantage explicitly of semantic and visual information. We also present a structured training procedure based on a concept we have called Image Networking: all the images in a training database are “connected” visually and semantically, so it is possible to exploit these connections to learn the tag transfer parameters at annotation time. This learning is local for the test image and it exploits the information obtained in the Nearest Neighbor computation stage. We demonstrate that our approach achieves state-of-the-art performance on the ImageCLEF2011 dataset.

关键词： Visualization Training Semantics Databases Image color analysis Image edge detection Vectors

A duality perspective on Loewner rational interpolation and state-space modelling of vector-exponential trajectories

学校读者我要写书评

暂无评论

A duality perspective on Loewner rational interpolation and ...

IEEE Annual Conference on Decision and Control

作者： P. Rapisarda A.C. Antoulas Vision Learning and Control Group School of Electronics and Computer Science University of Southampton SO17 1BJ Southampton UK Department of Electrical and Computer Engineering Rice University Houston TX 77005 USA

We explore some connections between the Loewner approach to interpolation and realization, and that based on bilinear differential forms arising in the behavioral framework. We show that a crucial concept underlying b... 详细信息

ISBN: (纸本)9781479978878

关键词： Models, Space trajectory rational interpolation Interpolation Perspective Modeling DUALITY bilinearity