Preserving Modes and Messages via Diverse Particle Selection

Jason Pacheco, Silvia Zuffi, Michael Black, Erik Sudderth
Proceedings of the 31st International Conference on Machine Learning, PMLR 32(2):1152-1160, 2014.

Abstract

In applications of graphical models arising in domains such as computer vision and signal processing, we often seek the most likely configurations of high-dimensional, continuous variables. We develop a particle-based max-product algorithm which maintains a diverse set of posterior mode hypotheses, and is robust to initialization. At each iteration, the set of hypotheses at each node is augmented via stochastic proposals, and then reduced via an efficient selection algorithm. The integer program underlying our optimization-based particle selection minimizes errors in subsequent max-product message updates. This objective automatically encourages diversity in the maintained hypotheses, without requiring tuning of application-specific distances among hypotheses. By avoiding the stochastic resampling steps underlying particle sum-product algorithms, we also avoid common degeneracies where particles collapse onto a single hypothesis. Our approach significantly outperforms previous particle-based algorithms in experiments focusing on the estimation of human pose from single images.

Cite this Paper

BibTeX
@InProceedings{pmlr-v32-pacheco14, title = {Preserving Modes and Messages via Diverse Particle Selection}, author = {Pacheco, Jason and Zuffi, Silvia and Black, Michael and Sudderth, Erik}, booktitle = {Proceedings of the 31st International Conference on Machine Learning}, pages = {1152--1160}, year = {2014}, editor = {Xing, Eric P. and Jebara, Tony}, volume = {32}, number = {2}, series = {Proceedings of Machine Learning Research}, address = {Bejing, China}, month = {22--24 Jun}, publisher = {PMLR}, pdf = {http://proceedings.mlr.press/v32/pacheco14.pdf}, url = {https://proceedings.mlr.press/v32/pacheco14.html}, abstract = {In applications of graphical models arising in domains such as computer vision and signal processing, we often seek the most likely configurations of high-dimensional, continuous variables. We develop a particle-based max-product algorithm which maintains a diverse set of posterior mode hypotheses, and is robust to initialization. At each iteration, the set of hypotheses at each node is augmented via stochastic proposals, and then reduced via an efficient selection algorithm. The integer program underlying our optimization-based particle selection minimizes errors in subsequent max-product message updates. This objective automatically encourages diversity in the maintained hypotheses, without requiring tuning of application-specific distances among hypotheses. By avoiding the stochastic resampling steps underlying particle sum-product algorithms, we also avoid common degeneracies where particles collapse onto a single hypothesis. Our approach significantly outperforms previous particle-based algorithms in experiments focusing on the estimation of human pose from single images.} }
Endnote
%0 Conference Paper %T Preserving Modes and Messages via Diverse Particle Selection %A Jason Pacheco %A Silvia Zuffi %A Michael Black %A Erik Sudderth %B Proceedings of the 31st International Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2014 %E Eric P. Xing %E Tony Jebara %F pmlr-v32-pacheco14 %I PMLR %P 1152--1160 %U https://proceedings.mlr.press/v32/pacheco14.html %V 32 %N 2 %X In applications of graphical models arising in domains such as computer vision and signal processing, we often seek the most likely configurations of high-dimensional, continuous variables. We develop a particle-based max-product algorithm which maintains a diverse set of posterior mode hypotheses, and is robust to initialization. At each iteration, the set of hypotheses at each node is augmented via stochastic proposals, and then reduced via an efficient selection algorithm. The integer program underlying our optimization-based particle selection minimizes errors in subsequent max-product message updates. This objective automatically encourages diversity in the maintained hypotheses, without requiring tuning of application-specific distances among hypotheses. By avoiding the stochastic resampling steps underlying particle sum-product algorithms, we also avoid common degeneracies where particles collapse onto a single hypothesis. Our approach significantly outperforms previous particle-based algorithms in experiments focusing on the estimation of human pose from single images.
RIS
TY - CPAPER TI - Preserving Modes and Messages via Diverse Particle Selection AU - Jason Pacheco AU - Silvia Zuffi AU - Michael Black AU - Erik Sudderth BT - Proceedings of the 31st International Conference on Machine Learning DA - 2014/06/18 ED - Eric P. Xing ED - Tony Jebara ID - pmlr-v32-pacheco14 PB - PMLR DP - Proceedings of Machine Learning Research VL - 32 IS - 2 SP - 1152 EP - 1160 L1 - http://proceedings.mlr.press/v32/pacheco14.pdf UR - https://proceedings.mlr.press/v32/pacheco14.html AB - In applications of graphical models arising in domains such as computer vision and signal processing, we often seek the most likely configurations of high-dimensional, continuous variables. We develop a particle-based max-product algorithm which maintains a diverse set of posterior mode hypotheses, and is robust to initialization. At each iteration, the set of hypotheses at each node is augmented via stochastic proposals, and then reduced via an efficient selection algorithm. The integer program underlying our optimization-based particle selection minimizes errors in subsequent max-product message updates. This objective automatically encourages diversity in the maintained hypotheses, without requiring tuning of application-specific distances among hypotheses. By avoiding the stochastic resampling steps underlying particle sum-product algorithms, we also avoid common degeneracies where particles collapse onto a single hypothesis. Our approach significantly outperforms previous particle-based algorithms in experiments focusing on the estimation of human pose from single images. ER -
APA
Pacheco, J., Zuffi, S., Black, M. & Sudderth, E.. (2014). Preserving Modes and Messages via Diverse Particle Selection. Proceedings of the 31st International Conference on Machine Learning, in Proceedings of Machine Learning Research 32(2):1152-1160 Available from https://proceedings.mlr.press/v32/pacheco14.html.

Related Material