Can We Learn Heuristics for Graphical Model Inference Using Reinforcement Learning?

Safa Messaoud, Maghav Kumar, Alexander G. Schwing

Research output: Contribution to journalConference articlepeer-review

Abstract

Combinatorial optimization is frequently used in computer vision. For instance, in applications like semantic segmentation, human pose estimation and action recognition, programs are formulated for solving inference in Conditional Random Fields (CRFs) to produce a structured output that is consistent with visual features of the image. However, solving inference in CRFs is in general intractable, and approximation methods are computationally demanding and limited to unary, pairwise and hand-crafted forms of higher order potentials. In this paper, we show that we can learn program heuristics, i.e., policies, for solving inference in higher order CRFs for the task of semantic segmentation, using reinforcement learning. Our method solves inference tasks efficiently without imposing any constraints on the form of the potentials. We show compelling results on the Pascal VOC and MOTS datasets.

Original languageEnglish (US)
Article number9156920
Pages (from-to)7586-7596
Number of pages11
JournalProceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition
DOIs
StatePublished - 2020
Event2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2020 - Virtual, Online, United States
Duration: Jun 14 2020Jun 19 2020

ASJC Scopus subject areas

  • Software
  • Computer Vision and Pattern Recognition

Fingerprint

Dive into the research topics of 'Can We Learn Heuristics for Graphical Model Inference Using Reinforcement Learning?'. Together they form a unique fingerprint.

Cite this