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

2020-04-27 · CVPR 2020 6 · Safa Messaoud, Maghav Kumar, Alexander G. Schwing

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.

📄 PDF Abstract BibTeX arXiv:2005.01508

Code (0)

등록된 구현이 없습니다.

Tasks

Action RecognitionCombinatorial OptimizationPose Estimation reinforcement-learning Reinforcement Learning (RL)Segmentation Semantic Segmentation

Tutorial and Survey on Probabilistic Graphical Model and Variational Inference in Deep Reinforcement Learning

2019-08-25 · Xudong Sun, Bernd Bischl

Aiming at a comprehensive and concise tutorial survey, recap of variational inference and reinforcement learning with Probabilistic Graphical Models are given with detailed derivations. Reviews and comparisons on recent …

Deep Reinforcement Learning reinforcement-learning Reinforcement Learning Reinforcement Learning (RL)+2

Convex Combination Belief Propagation Algorithms

2021-05-26 · Anna Grim, Pedro Felzenszwalb

We present new message passing algorithms for performing inference with graphical models. Our methods are designed for the most difficult inference problems where loopy belief propagation and other heuristics fail to con…

Learnability of Timescale Graphical Event Models

2020-05-25 · Philipp Behrendt

This technical report tries to fill a gap in current literature on Timescale Graphical Event Models. I propose and evaluate different heuristics to determine hyper-parameters during the structure learning algorithm and r…

Introducing PetriRL: An Innovative Framework for JSSP Resolution Integrating Petri nets and Event-based Reinforcement Learning

2024-01-23 · Sofiene Lassoued, Andreas Schwung

Resource utilization and production process optimization are crucial for companies in today's competitive industrial landscape. Addressing the complexities of job shop scheduling problems (JSSP) is essential to improving…

Decision Making Deep Reinforcement Learning Job Shop Scheduling Scheduling

Learning to Guide Local Search for MPE Inference in Probabilistic Graphical Models

2026-02-01 · Brij Malhotra, Shivvrat Arya, Tahrima Rahman, Vibhav Giridhar Gogate arxiv

Most Probable Explanation (MPE) inference in Probabilistic Graphical Models (PGMs) is a fundamental yet computationally challenging problem arising in domains such as diagnosis, planning, and structured prediction. In ma…

Structured Prediction