Continuous Relaxation of MAP Inference: A Nonconvex Perspective - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Conference Papers Year : 2018

Continuous Relaxation of MAP Inference: A Nonconvex Perspective


In this paper, we study a nonconvex continuous relaxation of MAP inference in discrete Markov random fields (MRFs). We show that for arbitrary MRFs, this relaxation is tight, and a discrete stationary point of it can be easily reached by a simple block coordinate descent algorithm. In addition, we study the resolution of this relaxation using popular gradient methods, and further propose a more effective solution using a multilinear decomposition framework based on the alternating direction method of multi-pliers (ADMM). Experiments on many real-world problems demonstrate that the proposed ADMM significantly outper-forms other nonconvex relaxation based methods, and compares favorably with state of the art MRF optimization algorithms in different settings.
Fichier principal
Vignette du fichier
norelax_cvpr2018.pdf (581.62 Ko) Télécharger le fichier
Origin : Files produced by the author(s)

Dates and versions

hal-01716514 , version 1 (23-02-2018)
hal-01716514 , version 2 (26-02-2018)



Ð.Khuê Lê-Huu, Nikos Paragios. Continuous Relaxation of MAP Inference: A Nonconvex Perspective. CVPR 2018 - IEEE Conference on Computer Vision and Pattern Recognition, Jun 2018, Salt Lake City, United States. pp.1-19, ⟨10.1109/CVPR.2018.00580⟩. ⟨hal-01716514v2⟩
305 View
134 Download



Gmail Facebook X LinkedIn More