Skip to main content

Lund University Publications

LUND UNIVERSITY LIBRARIES

Deep Learning of Graph Matching

Zanfir, Andrei and Sminchisescu, Cristian LU (2018) 31st Meeting of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2018 p.2684-2693
Abstract

The problem of graph matching under node and pairwise constraints is fundamental in areas as diverse as combinatorial optimization, machine learning or computer vision, where representing both the relations between nodes and their neighborhood structure is essential. We present an end-to-end model that makes it possible to learn all parameters of the graph matching process, including the unary and pairwise node neighborhoods, represented as deep feature extraction hierarchies. The challenge is in the formulation of the different matrix computation layers of the model in a way that enables the consistent, efficient propagation of gradients in the complete pipeline from the loss function, through the combinatorial optimization layer... (More)

The problem of graph matching under node and pairwise constraints is fundamental in areas as diverse as combinatorial optimization, machine learning or computer vision, where representing both the relations between nodes and their neighborhood structure is essential. We present an end-to-end model that makes it possible to learn all parameters of the graph matching process, including the unary and pairwise node neighborhoods, represented as deep feature extraction hierarchies. The challenge is in the formulation of the different matrix computation layers of the model in a way that enables the consistent, efficient propagation of gradients in the complete pipeline from the loss function, through the combinatorial optimization layer solving the matching problem, and the feature extraction hierarchy. Our computer vision experiments and ablation studies on challenging datasets like PASCAL VOC keypoints, Sintel and CUB show that matching models refined end-to-end are superior to counterparts based on feature hierarchies trained for other problems.

(Less)
Please use this url to cite or link to this publication:
author
and
organization
publishing date
type
Chapter in Book/Report/Conference proceeding
publication status
published
subject
host publication
Proceedings - 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2018
article number
8578382
pages
10 pages
publisher
IEEE Computer Society
conference name
31st Meeting of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2018
conference location
Salt Lake City, United States
conference dates
2018-06-18 - 2018-06-22
external identifiers
  • scopus:85062882212
ISBN
9781538664209
DOI
10.1109/CVPR.2018.00284
language
English
LU publication?
yes
id
ee9a397d-08a8-49dc-aac9-222d1eab0e17
date added to LUP
2019-04-01 09:45:28
date last changed
2022-05-11 07:07:52
@inproceedings{ee9a397d-08a8-49dc-aac9-222d1eab0e17,
  abstract     = {{<p>The problem of graph matching under node and pairwise constraints is fundamental in areas as diverse as combinatorial optimization, machine learning or computer vision, where representing both the relations between nodes and their neighborhood structure is essential. We present an end-to-end model that makes it possible to learn all parameters of the graph matching process, including the unary and pairwise node neighborhoods, represented as deep feature extraction hierarchies. The challenge is in the formulation of the different matrix computation layers of the model in a way that enables the consistent, efficient propagation of gradients in the complete pipeline from the loss function, through the combinatorial optimization layer solving the matching problem, and the feature extraction hierarchy. Our computer vision experiments and ablation studies on challenging datasets like PASCAL VOC keypoints, Sintel and CUB show that matching models refined end-to-end are superior to counterparts based on feature hierarchies trained for other problems.</p>}},
  author       = {{Zanfir, Andrei and Sminchisescu, Cristian}},
  booktitle    = {{Proceedings - 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2018}},
  isbn         = {{9781538664209}},
  language     = {{eng}},
  month        = {{12}},
  pages        = {{2684--2693}},
  publisher    = {{IEEE Computer Society}},
  title        = {{Deep Learning of Graph Matching}},
  url          = {{http://dx.doi.org/10.1109/CVPR.2018.00284}},
  doi          = {{10.1109/CVPR.2018.00284}},
  year         = {{2018}},
}