Regularized Frank-Wolfe for Dense CRFs: Generalizing Mean Field and Beyond - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Conference Papers Year : 2021

Regularized Frank-Wolfe for Dense CRFs: Generalizing Mean Field and Beyond

Abstract

We introduce regularized Frank-Wolfe, a general and effective algorithm for inference and learning of dense conditional random fields (CRFs). The algorithm optimizes a nonconvex continuous relaxation of the CRF inference problem using vanilla Frank-Wolfe with approximate updates, which are equivalent to minimizing a regularized energy function. Our proposed method is a generalization of existing algorithms such as mean field or concave-convex procedure. This perspective not only offers a unified analysis of these algorithms, but also allows an easy way of exploring different variants that potentially yield better performance. We illustrate this in our empirical results on standard semantic segmentation datasets, where several instantiations of our regularized Frank-Wolfe outperform mean field inference, both as a standalone component and as an end-to-end trainable layer in a neural network. We also show that dense CRFs, coupled with our new algorithms, produce significant improvements over strong CNN baselines.
Fichier principal
Vignette du fichier
neurips_2021_regularizedFW.pdf (622.45 Ko) Télécharger le fichier
Origin Files produced by the author(s)

Dates and versions

hal-03406107 , version 1 (27-10-2021)

Identifiers

  • HAL Id : hal-03406107 , version 1

Cite

Ð.Khuê Lê-Huu, Karteek Alahari. Regularized Frank-Wolfe for Dense CRFs: Generalizing Mean Field and Beyond. NeurIPS 2021 - 35th Annual Conference on Neural Information Processing Systems, Dec 2021, Virtual-only Conference, Australia. pp.1-35. ⟨hal-03406107⟩
81 View
94 Download

Share

Gmail Mastodon Facebook X LinkedIn More