Filters








56,226 Hits in 6.3 sec

Discovering Modes of an Image Population through Mixture Modeling [chapter]

Mert R. Sabuncu, Serdar K. Balci, Polina Golland
2008 Lecture Notes in Computer Science  
The algorithm produced three modes that mainly corresponded to a sub-population of healthy controls, a sub-population of patients with dementia and a mixture group that contained both types.  ...  These results suggest that the algorithm can be used to discover sub-populations that correspond to interesting structural or functional "modes."  ...  These results suggest that iCluster can be used to probe a population of images to discover important structural or functional "modes."  ... 
doi:10.1007/978-3-540-85990-1_46 fatcat:c2qvvhlwn5hanmkr73l6z42bmq

Discovering modes of an image population through mixture modeling

Mert R Sabuncu, Serdar K Balci, Polina Golland
2008
The algorithm produced three modes that mainly corresponded to a sub-population of healthy controls, a sub-population of patients with dementia and a mixture group that contained both types.  ...  These results suggest that the algorithm can be used to discover sub-populations that correspond to interesting structural or functional "modes".  ...  These results suggest that iCluster can be used to probe a population of images to discover important structural or functional "modes."  ... 
pmid:18982628 pmcid:PMC2671151 fatcat:5zsrhh4zabfx3mcigltzf6mxmy

Image-driven population analysis through mixture modeling

Mert R. Sabuncu, Polina Golland
2009 2009 IEEE International Symposium on Biomedical Imaging: From Nano to Macro  
We derive the algorithm based on a generative model of an image population as a mixture of deformable template images. We validate and explore our method in four experiments.  ...  The output of the algorithm is a small number of template images that represent different modes in a population.  ...  Support for this research is provided in part by the Department of Veterans Affairs Merit Awards, National Alliance for Medical Image Analysis (NIH NIBIB NAMIC U54-EB005149), the Neuroimaging Analysis  ... 
doi:10.1109/isbi.2009.5193178 dblp:conf/isbi/Sabuncu09 fatcat:ldgun3bxtfcpfjpjxfbzdekzti

Image-Driven Population Analysis Through Mixture Modeling

M.R. Sabuncu, S.K. Balci, M.E. Shenton, P. Golland
2009 IEEE Transactions on Medical Imaging  
We derive the algorithm based on a generative model of an image population as a mixture of deformable template images. We validate and explore our method in four experiments.  ...  The output of the algorithm is a small number of template images that represent different modes in a population.  ...  Support for this research is provided in part by the Department of Veterans Affairs Merit Awards, National Alliance for Medical Image Analysis (NIH NIBIB NAMIC U54-EB005149), the Neuroimaging Analysis  ... 
doi:10.1109/tmi.2009.2017942 pmid:19336293 pmcid:PMC2832589 fatcat:m42yn2u24jezrjzr46ejgqjfl4

Fashion Style Generation: Evolutionary Search with Gaussian Mixture Models in the Latent Space [article]

Imke Grabe, Jichen Zhu, Manex Agirrezabal
2022 arXiv   pre-print
Over generations, a genetic algorithm optimizes a population of designs to increase their probability of belonging to one of the Gaussian mixture components or styles.  ...  A Gaussian mixture model is applied to identify fashion styles based on the higher-layer representations of outfits in a clothing-specific attribute prediction model.  ...  Clustering models such as a Gaussian mixture model (GMM) have previously been applied to find recurring components in the attribute embedding of images [22, 1] .  ... 
arXiv:2204.00592v2 fatcat:bmoxmyzseva4jperyii3eegrve

Mixture of Probabilistic Principal Component Analyzers for Shapes from Point Sets

Ali Gooya, Karim Lekadir, Isaac Castro-Mateos, Jose Maria Pozo, Alejandro F. Frangi
2018 IEEE Transactions on Pattern Analysis and Machine Intelligence  
Statistics are often limited to the variations around a single population mean, not necessarily representing any of the shape subpopulations, with an arbitrary number of variation modes.  ...  models for each population.  ...  In 2014, he was awarded an IIF Marie-Curie Fellowship for statistical modeling of morphology and function from population in University of Sheffield, where he recently works as a Lecturer in Medical image  ... 
doi:10.1109/tpami.2017.2700276 pmid:28475045 fatcat:gdnf5gii35fjxcv2l6e2enekge

Enhanced Bayesian modelling in BAPS software for learning genetic structures of populations

Jukka Corander, Pekka Marttinen, Jukka Sirén, Jing Tang
2008 BMC Bioinformatics  
The Bayesian modelling methods introduced in this article represent an array of enhanced tools for learning the genetic structure of populations.  ...  With these methods it is possible, e.g., to fit genetic mixture models using user-specified numbers of clusters and to estimate levels of admixture under a genetic linkage model.  ...  Acknowledgements This work was supported by the Academy of Finland, grant no. 121301 and by the ComBi and ComMIT graduate schools.  ... 
doi:10.1186/1471-2105-9-539 pmid:19087322 pmcid:PMC2629778 fatcat:7s5crgixjnedth7w3w5vyq66t4

Fungicide resistance: facing the challenge – a review

D.W. Hollomon
2016 Plant Protection Science  
pathogen populations in field crops.  ...  Experience amassed over the past fifty years has emphasised the importance of diversity in modes of action in anti-resistance strategies.  ...  Both modelling and experimental evidence from many studies show that mixtures do indeed slow the evolution to an at risk partner (Brent & Hollomon 2007b; van den Bosch et al. 2014) .  ... 
doi:10.17221/42/2015-pps fatcat:ntncwxav3zgkdk3vugxw7umyji

Evolutionary Generative Adversarial Networks [article]

Chaoyue Wang, Chang Xu, Xin Yao, Dacheng Tao
2018 arXiv   pre-print
In this way, E-GAN overcomes the limitations of an individual adversarial training objective and always preserves the best offspring, contributing to progress in and the success of GANs.  ...  We also utilize an evaluation mechanism to measure the quality and diversity of generated samples, such that only well-performing generator(s) are preserved and used for further training.  ...  architectures through an evolutionary search [35, 20, 25] .  ... 
arXiv:1803.00657v1 fatcat:ngoz424hcrhtxc4yddyhw4sx2e

Evidence for Two Hot-Jupiter Formation Paths

Benjamin E. Nelson, Eric B. Ford, Frederic A. Rasio
2017 Astronomical Journal  
channels, and applying a hierarchical Bayesian mixture model of truncated power laws of the form x^γ-1 to constrain the population-level parameters of interest (e.g., location of inner edges, γ, mixture  ...  We approach this problem using data from several exoplanet surveys (radial velocity, Kepler, HAT, and WASP) allowing for either a single population or a mixture of populations associated with these formation  ...  γ 2 power law index for second mixture component in x f i ith mixture component fraction pare to the observations (e.g., through planet population synthesis models), we approach this problem from a data-driven  ... 
doi:10.3847/1538-3881/aa82b3 fatcat:ommfvclfqbhixcqlylw4xvclly

Demonstrating the Evolution of GANs through t-SNE [article]

Victor Costa, Nuno Lourenço, João Correia, Penousal Machado
2021 arXiv   pre-print
Generative Adversarial Networks (GANs) are powerful generative models that achieved strong results, mainly in the image domain.  ...  The results show both by visual inspection and metrics that the Evolutionary Algorithm gradually improves discriminators and generators through generations, avoiding problems such as mode collapse.  ...  Acknowledgments This work is partially funded by the project grant DSAIPA/DS/0022/2018 (GADgET), by national funds through the FCT -Foundation for Science and  ... 
arXiv:2102.00524v2 fatcat:zgjy5stdxnhtbnbmkjmssgyfw4

A Faint Halo Star Cluster Discovered in the Blanco Imaging of the Southern Sky Survey

S. Mau, A. Drlica-Wagner, K. Bechtol, A. B. Pace, T. Li, M. Soares-Santos, N. Kuropatkin, S. Allam, D. Tucker, L. Santana-Silva, B. Yanny, P. Jethwa (+4 others)
2019 Astrophysical Journal  
We present the discovery of a faint, resolved stellar system, BLISS J0321+0438 (BLISS 1), found in Dark Energy Camera data from the first observing run of the Blanco Imaging of the Southern Sky (BLISS)  ...  Combining the available positional and velocity information with simulations of the accreted satellite population of the Large Magellanic Cloud, we find that it is unlikely that BLISS J0321+0438 (BLISS  ...  We estimate the proper motion of BLISS J0321+0438 (BLISS 1) using the Gaussian mixture model analysis described in Section 2.2 of Pace & Li (2018) .  ... 
doi:10.3847/1538-4357/ab0bb8 fatcat:bcoj3ffvqzeixlfwje6roo2a7y

DynaMorph: learning morphodynamic states of human cells with live imaging and sc-RNAseq [article]

Zhenqin Wu, Bryant B. Chhun, Galina Schmunk, Chang Kim, Li-Hao Yeh, Tomasz J. Nowakowski, James Zou, Shalin B. Mehta
2020 bioRxiv   pre-print
Morphological states of human cells are widely imaged and analyzed to diagnose diseases and to discover biological mechanisms.  ...  We propose a computational framework, DynaMorph, that combines quantitative label-free imaging and deep learning for automated discovery of morphodynamic states.  ...  We thank Greg Huber for discussions around the physical models of cell states.  ... 
doi:10.1101/2020.07.20.213074 fatcat:yw3fdjiwdrhhpca6b6i63btshe

Bayesian Nonparametrics for Non-exhaustive Learning [article]

Yicheng Cheng, Bartek Rajwa, Murat Dundar
2019 arXiv   pre-print
problem, which is at the root of many recently discovered limitations of deep learning.  ...  The presented study which has been motivated by two important applications proposes a NEL algorithm built on a highly flexible, doubly non-parametric Bayesian Gaussian mixture model that can grow arbitrarily  ...  Experiments with Simulated Data We use a two layer Gaussian mixture model similar to I 2 GMM to generate a 2D simulated data with multi-mode class distributions.  ... 
arXiv:1908.09736v1 fatcat:kvdp2uhnknhgvj2co4qpvg6g4q

Visible and near-infrared spectroscopy of the Centaur 32532 (2001 PT$_{\mathsf {13}}$)

M. A. Barucci, H. Boehnhardt, E. Dotto, A. Doressoundiram, J. Romon, M. Lazzarin, S. Fornasier, C. de Bergh, G. P. Tozzi, A. Delsanti, O. Hainaut, L. Barrera (+8 others)
2002 Astronomy and Astrophysics  
) within the framework of an ESO large program on the Trans-Neptunian objects (TNOs) and Centaurs.  ...  In one spectrum there is the possible presence of signatures of water ice in small amounts. Two models have been proposed to interpret the surface composition of this Centaur.  ...  The aim is to provide photometric and spectroscopic data in the visible and near-infrared ranges for a large set of objects to study the physical properties and composition of this newly discovered population  ... 
doi:10.1051/0004-6361:20021186 fatcat:xykrfrsuibcxll5re4jy3w52o4
« Previous Showing results 1 — 15 out of 56,226 results