25 skills found
mstorath / PottslabUnsupervised multilabel image segmentation (color/gray/multichannel) based on the Potts model (aka piecewise constant Mumford-Shah model)
ProteinDesignLab / CalibyPotts model-based protein sequence design
sokrypton / GREMLIN CPPGREMLIN - learn MRF/potts model from input multiple sequence alignment! Implementation now available in C++ and Tensorflow/Python!
songlab-cal / Factored AttentionThis repository contains code for reproducing results in our paper Interpreting Potts and Transformer Protein Models Through the Lens of Simplified Attention
ignaciorlando / Fundus Vessel Segmentation TbmeIn this work, we present an extensive description and evaluation of our method for blood vessel segmentation in fundus images based on a discriminatively trained, fully connected conditional random field model. Standard segmentation priors such as a Potts model or total variation usually fail when dealing with thin and elongated structures. We overcome this difficulty by using a conditional random field model with more expressive potentials, taking advantage of recent results enabling inference of fully connected models almost in real-time. Parameters of the method are learned automatically using a structured output support vector machine, a supervised technique widely used for structured prediction in a number of machine learning applications. Our method, trained with state of the art features, is evaluated both quantitatively and qualitatively on four publicly available data sets: DRIVE, STARE, CHASEDB1 and HRF. Additionally, a quantitative comparison with respect to other strategies is included. The experimental results show that this approach outperforms other techniques when evaluated in terms of sensitivity, F1-score, G-mean and Matthews correlation coefficient. Additionally, it was observed that the fully connected model is able to better distinguish the desired structures than the local neighborhood based approach. Results suggest that this method is suitable for the task of segmenting elongated structures, a feature that can be exploited to contribute with other medical and biological applications.
Neelfrost / Microstructure MasMicrostructure Modeling and Simulation. Generate microstructures using site-saturation condition, and simulate grain growth using Monte Carlo Potts Model.
SubarnaTripathi / Video Inferencemean field based inference for dense semantic video segmentation with higher order clique potentials (Pn Potts model)
bdecost / Mcpmmcpm: python implementation of the modified Potts model for grain growth developed in Mason, J. K., et al. "Kinetics and anisotropy of the Monte Carlo model of grain growth." Acta Materialia 82 (2015): 155-166.
alexjli / Terminator PublicNeurally-derived Potts models for protein design, inspired by dTERMen
anna-pa-m / AdabmDCABoltzmann machine learning for Potts models of biological data
mutual-ai / Fundus Vessel Segmentation TmbeOne of the first steps in automatic fundus image analysis is the segmentation of the retinal vasculature, which provides valuable information related to several diseases. In this work, we present an extensive description and evaluation of our method for blood vessel segmentation in fundus images based on a discriminatively trained, fully connected conditional random field model. This task remains a challenge largely due to the desired structures being thin and elongated, a setting that performs particularly poorly using standard segmentation priors, such as a Potts model or total variation. We overcome this difficulty by using a conditional random field model with more expressive potentials, taking advantage of recent results enabling inference of fully connected models almost in real-time. Parameters of the method are learned automatically using a structured output support vector machine, a supervised technique widely used for structured prediction in a number of machine learning applications. The evaluation of our method is performed both quantitatively and qualitatively on DRIVE, STARE, CHASEDB1 and HRF, showing its ability to deal with different types of images and outperforming other techniques, trained using state of the art features.
jtextor / CpmImplementation of the cellular Potts model in pure javascript for fun an easy visualisation.
lyelibi / Potts Model ClusteringSuper-Paramagnetic Clustering, Maximum entropy, Maximum Likelihood Methods.
manolo-lolo / Potts Model Monte CarloSimulation of the Potts model for a university course in Monte Carlo simulations
rgjha / TensorCodesAssortment of codes for tensor network analysis of two- and three-dimensional spin models (Ising, Potts, XY) and Euclidean 2d SU(2) gauge theory. Not all codes work properly or are checked. They are to get you started. Please use at your own risk.
SunilAnandatheertha / PXOPXO (Poly-XTAL Operations). Generate, analyze and export complex 2D space partitions like metallic grain structures
BrooksResearchGroup-UM / DirectCouplingAnalysis PottsModel TensorflowA Tensorflow implementation of Direct Coupling Analysis using Potts model
salimandre / Markov Random FieldsImage denoising using Markov random fields.
davcem / Cpm CytoscapeImplementation of the Cellular Potts Model with cytoscape.js
NinelK / VCTVirtual Cardiac Tissue Model – A Cellular Potts Model for cardiac monolayers that reproduces fibrotic patterns
