Learning to Compare Image Patches via Convolutional Neural Networks

Sergey Zagoruyko 1, 2, 3 Nikos Komodakis 2, 1, 3, 4
3 IMAGINE [Marne-la-Vallée]
LIGM - Laboratoire d'Informatique Gaspard-Monge, CSTB - Centre Scientifique et Technique du Bâtiment, ENPC - École des Ponts ParisTech
Abstract : In this paper we show how to learn directly from image data (i.e., without resorting to manually-designed features) a general similarity function for comparing image patches, which is a task of fundamental importance for many computer vision problems. To encode such a function, we opt for a CNN-based model that is trained to account for a wide variety of changes in image appearance. To that end, we explore and study multiple neural network architectures, which are specifically adapted to this task. We show that such an approach can significantly outperform the state-of-the-art on several problems and benchmark datasets.
Liste complète des métadonnées

Cited literature [28 references]  Display  Hide  Download

https://hal.archives-ouvertes.fr/hal-01246261
Contributor : Sergey Zagoruyko <>
Submitted on : Friday, December 18, 2015 - 12:29:18 PM
Last modification on : Monday, July 9, 2018 - 12:39:44 PM
Document(s) archivé(s) le : Saturday, March 19, 2016 - 12:40:28 PM

File

1504.03641v1.pdf
Files produced by the author(s)

Identifiers

Citation

Sergey Zagoruyko, Nikos Komodakis. Learning to Compare Image Patches via Convolutional Neural Networks. IEEE Conference on Computer Vision and Pattern Recognition 2015, Jun 2015, Boston, United States. ⟨10.1109/CVPR.2015.7299064⟩. ⟨hal-01246261⟩

Share

Metrics

Record views

696

Files downloads

485