Skip to Main content Skip to Navigation
Conference papers

Finding Matches in a Haystack: A Max-Pooling Strategy for Graph Matching in the Presence of Outliers

Minsu Cho 1, 2 Jian Sun 1, 3 Olivier Duchenne 4 Jean Ponce 1, 2
1 WILLOW - Models of visual object recognition and scene understanding
CNRS - Centre National de la Recherche Scientifique : UMR8548, Inria Paris-Rocquencourt, DI-ENS - Département d'informatique de l'École normale supérieure
Abstract : A major challenge in real-world feature matching problems is to tolerate the numerous outliers arising in typical visual tasks. Variations in object appearance, shape, and structure within the same object class make it harder to distinguish inliers from outliers due to clutters. In this pa- per, we propose a max-pooling approach to graph matching, which is not only resilient to deformations but also remarkably tolerant to outliers. The proposed algorithm evaluates each candidate match using its most promising neighbors, and gradually propagates the corresponding scores to update the neighbors. As final output, it assigns a reliable score to each match together with its supporting neighbors, thus providing contextual information for further verification. We demonstrate the robustness and utility of our method with synthetic and real image experiments.
Document type :
Conference papers
Complete list of metadata

Cited literature [31 references]  Display  Hide  Download

https://hal.inria.fr/hal-01053675
Contributor : Minsu Cho <>
Submitted on : Friday, August 1, 2014 - 1:19:31 AM
Last modification on : Tuesday, May 4, 2021 - 2:06:02 PM
Long-term archiving on: : Tuesday, November 25, 2014 - 10:41:14 PM

File

cho2014.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-01053675, version 1

Collections

Citation

Minsu Cho, Jian Sun, Olivier Duchenne, Jean Ponce. Finding Matches in a Haystack: A Max-Pooling Strategy for Graph Matching in the Presence of Outliers. CVPR - IEEE Conference on Computer Vision and Pattern Recognition, Jun 2014, Columbus, Ohio, United States. ⟨hal-01053675⟩

Share

Metrics

Record views

639

Files downloads

472