Approximate Bayesian Image Interpretation using Generative Probabilistic Graphics Programs

Approximate Bayesian Image Interpretation using Generative Probabilistic Graphics Programs

The idea of computer vision as the Bayesian inverse problem to computer graphics has a long history and an appealing elegance, but it has proved difficult to directly implement. Instead, most vision tasks are approached via complex bottom-up processing pipelines. Here we show that it is possible to...

Descripció completa

Dades bibliogràfiques
Autors principals:	Mansinghka, Vikash K., Kulkarni, Tejas Dattatraya, Perov, Yura N., Tenenbaum, Joshua B.
Altres autors:	Massachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratory
Format:	Article
Idioma:	en_US
Publicat:	Neural Information Processing Systems Foundation 2015
Accés en línia:	http://hdl.handle.net/1721.1/93171 https://orcid.org/0000-0002-7077-2765 https://orcid.org/0000-0002-1925-2035

Ítems similars

Picture: A Probabilistic Programming Language for Scene Perception
per: Kulkarni, Tejas Dattatraya, et al.
Publicat: (2015)

Deep convolutional inverse graphics network
per: Kohli, Pushmeet, et al.
Publicat: (2017)

Bayesian synthesis of probabilistic programs for automatic data modeling
per: Saad, Feras A, et al.
Publicat: (2021)

Stochastic Digital Circuits for Probabilistic Inference
per: Tenenbaum, Joshua B., et al.
Publicat: (2008)

A probabilistic model of cross-categorization
per: Shafto, Patrick, et al.
Publicat: (2015)

Natively probabilistic computation
per: Mansinghka, Vikash Kumar
Publicat: (2009)

Exact and approximate sampling by systematic stochastic search
per: Tenenbaum, Joshua B., et al.
Publicat: (2011)

Probabilistic Programming with Stochastic Probabilities
per: Lew, Alexander K., et al.
Publicat: (2023)

Applications of probabilistic programming
per: Perov, Y
Publicat: (2015)

Nonparametric Bayesian methods for supervised and unsupervised learning
per: Mansinghka, Vikash Kumar
Publicat: (2010)

Probabilistic graphical models : bayesian networks
per: Chan, Xiang Yun
Publicat: (2021)

SPPL: probabilistic programming with fast exact symbolic inference
per: Saad, Feras A, et al.
Publicat: (2022)

Probabilistic programming with programmable inference
per: Mansinghka, Vikash K., et al.
Publicat: (2021)

P244: Developing Bayesian graphical models to provide continuous, probabilistic variant interpretation
per: Toby Manders, et al.
Publicat: (2023-01-01)

ADEV: Sound Automatic Differentiation of Expected Values of Probabilistic Programs
per: Lew, Alexander K., et al.
Publicat: (2023)

Self-supervised intrinsic image decomposition
per: Janner, Michael, et al.
Publicat: (2020)

Gen: A General-Purpose Probabilistic Programming System with Programmable Inference
per: Cusumano-Towner, Marco F., et al.
Publicat: (2018)

CrossCat: A fully Bayesian nonparametric method for analyzing heterogeneous, high dimensional data
per: Shafto, Patrick, et al.
Publicat: (2017)

Learning structured representations for perception and control
per: Kulkarni, Tejas Dattatraya
Publicat: (2017)

Probabilistic Programming with Programmable Variational Inference
per: Becker, McCoy R., et al.
Publicat: (2024)

Bayesian Optimization for Probabilistic Programs
per: Rainforth, T, et al.
Publicat: (2016)

GenSQL: A Probabilistic Programming System for Querying Generative Models of Database Tables
per: Huot, Mathieu, et al.
Publicat: (2024)

Particle Gibbs with ancestor sampling for probabilistic programs
per: Meent, J, et al.
Publicat: (2015)

Sampling for Bayesian program learning
per: Ellis, Kevin M., et al.
Publicat: (2017)

Particle Gibbs with Ancestor Sampling for Probabilistic Programs
per: van de Meent, J, et al.
Publicat: (2015)

ADEV: Sound Automatic Differentiation of Expected Values of probabilistic programs
per: Lew, AK, et al.
Publicat: (2023)

Bayesian optimization as a probabilistic meta-program
per: Zinberg, Ben (Ben I.)
Publicat: (2017)

Learning to Infer Graphics Programs from Hand-Drawn Images
per: Ellis, Kevin, et al.
Publicat: (2021)

Learning to Infer Graphics Programs from Hand-Drawn Images
per: Ellis, Kevin, et al.
Publicat: (2021)

Designing Perceptual Puzzles by Differentiating Probabilistic Programs
per: Chandra, Kartik, et al.
Publicat: (2022)

Optimal approximate sampling from discrete probability distributions
per: Saad, Feras A, et al.
Publicat: (2021)

Explaining human multiple object tracking as resource-constrained approximate inference in a dynamic probabilistic model
per: Alvarez, George, et al.
Publicat: (2017)

Approximate counting in SMT and value estimation for probabilistic programs
per: Chistikov, D, et al.
Publicat: (2017)

Interpreting lion behaviour with nonparametric probabilistic programs
per: Dhir, N, et al.
Publicat: (2017)

DURableVS: Data-efficient Unsupervised Recalibrating Visual Servoing via online learning in a structured generative model
per: Gothoskar, Nishad, et al.
Publicat: (2023)

Trace types and denotational semantics for sound programmable inference in probabilistic languages
per: Lew, Alexander, et al.
Publicat: (2021)

Advances in probabilistics graphical models /
per: Lucas, Peter, 1955-, et al.
Publicat: (2007)

Bayesian Active Structure Learning for Gaussian Process Probabilistic Programs
per: Lin, Gloria Z.
Publicat: (2022)

Exact Bayesian inference on discrete models via probability generating functions: a probabilistic programming approach
per: Zaiser, F, et al.
Publicat: (2024)

Language Understanding for Text-based Games using Deep Reinforcement Learning
per: Narasimhan, Karthik Rajagopal, et al.
Publicat: (2015)