Faster attend-infer-repeat with tractable probabilistic models

Karl Stelzner, Robert Peharz, Kristian Kersting

Research output: Chapter in Book/Report/Conference proceedingConference contributionAcademicpeer-review

11 Citations (Scopus)


The recent Attend-Infer-Repeat (AIR) framework marks a milestone in structured probabilistic modeling, as it tackles the challenging problem of unsupcrviscd scene understanding via Baycsian inference. AIR expresses the composition of visual scenes from individual objects, and uses vari-ational autoencoders to model the appearance of those objects. However, inference in the overall model is highly intractable, which hampers its learning speed and makes it prone to suboptimal solutions. In this paper, we show that the speed and robustness of learning in AIR can be considerably improved by replacing the intractable object representations with tractable probabilistic models. In particular, we opt for sum-product networks (SPNs), expressive deep probabilistic models with a rich set of tractable inference routines. The resulting model, called SuPAIR, learns an order of magnitude faster than AIR, treats object occlusions in a consistent manner, and allows for the inclusion of a background noise model, improving the robustness of Bayesian scene understanding.

Original languageEnglish
Title of host publication36th International Conference on Machine Learning, ICML 2019
Number of pages12
ISBN (Electronic)9781510886988
Publication statusPublished - 1 Jan 2019
Event36th International Conference on Machine Learning (ICML 2019) - Long Beach, United States
Duration: 9 Jun 201915 Jun 2019
Conference number: 36

Publication series

NameProceedings of Machine Learning Research


Conference36th International Conference on Machine Learning (ICML 2019)
Abbreviated titleICML 2019
Country/TerritoryUnited States
CityLong Beach


Dive into the research topics of 'Faster attend-infer-repeat with tractable probabilistic models'. Together they form a unique fingerprint.

Cite this