Rotation Equivariant Vector Field Networks

Diego Marcos*, Michele Volpi, Nikos Komodakis, Devis Tuia

*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceedingConference paperAcademicpeer-review

66 Citations (Scopus)

Abstract

In many computer vision tasks, we expect a particular behavior of the output with respect to rotations of the input image. If this relationship is explicitly encoded, instead of treated as any other variation, the complexity of the problem is decreased, leading to a reduction in the size of the required model. In this paper, we propose the Rotation Equivariant Vector Field Networks (RotEqNet), a Convolutional Neural Network (CNN) architecture encoding rotation equivariance, invariance and covariance. Each convolutional filter is applied at multiple orientations and returns a vector field representing magnitude and angle of the highest scoring orientation at every spatial location. We develop a modified convolution operator relying on this representation to obtain deep architectures. We test RotEqNet on several problems requiring different responses with respect to the inputs' rotation: image classification, biomedical image segmentation, orientation estimation and patch matching. In all cases, we show that RotEqNet offers extremely compact models in terms of number of parameters and provides results in line to those of networks orders of magnitude larger.

Original languageEnglish
Title of host publicationProceedings - 2017 IEEE International Conference on Computer Vision, ICCV 2017
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages5058-5067
Number of pages10
ISBN (Electronic)9781538610329
ISBN (Print)9781538610336
DOIs
Publication statusPublished - 22 Dec 2017
Externally publishedYes
Event16th IEEE International Conference on Computer Vision, ICCV 2017 - Venice, Italy
Duration: 22 Oct 201729 Oct 2017

Publication series

NameProceedings of the IEEE International Conference on Computer Vision
Volume2017-October
ISSN (Print)1550-5499

Conference

Conference16th IEEE International Conference on Computer Vision, ICCV 2017
Country/TerritoryItaly
CityVenice
Period22/10/1729/10/17

Fingerprint

Dive into the research topics of 'Rotation Equivariant Vector Field Networks'. Together they form a unique fingerprint.

Cite this