Worrall, DE;
Garbin, SJ;
Turmukhambetov, D;
Brostow, GJ;
(2017)
Harmonic Networks: Deep Translation and Rotation Equivariance.
In:
2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).
(pp. pp. 7168-7177).
IEEE: Honolulu, HI, USA, USA.
Preview |
Text
Brostow_1612.04642.pdf - Accepted Version Download (4MB) | Preview |
Abstract
Translating or rotating an input image should not affect the results of many computer vision tasks. Convolutional neural networks (CNNs) are already translation equivariant: input image translations produce proportionate feature map translations. This is not the case for rotations. Global rotation equivariance is typically sought through data augmentation, but patch-wise equivariance is more difficult. We present Harmonic Networks or H-Nets, a CNN exhibiting equivariance to patch-wise translation and 360-rotation. We achieve this by replacing regular CNN filters with circular harmonics, returning a maximal response and orientation for every receptive field patch. H-Nets use a rich, parameter-efficient and low computational complexity representation, and we show that deep feature maps within the network encode complicated rotational invariants. We demonstrate that our layers are general enough to be used in conjunction with the latest architectures and techniques, such as deep supervision and batch normalization. We also achieve state-of-the-art classification on rotated-MNIST, and competitive results on other benchmark challenges.
| Type: | Proceedings paper |
|---|---|
| Title: | Harmonic Networks: Deep Translation and Rotation Equivariance |
| Event: | IEEE Conference on Computer Vision and Pattern Recognition (CVPR) |
| Location: | Honolulu, Hawaii, USA |
| Dates: | 22 July 2017 - 25 July 2017 |
| ISBN-13: | 978-1-5386-0457-1 |
| Open access status: | An open access version is available from UCL Discovery |
| DOI: | 10.1109/CVPR.2017.758 |
| Publisher version: | http://dx.doi.org/10.1109/CVPR.2017.758 |
| Language: | English |
| Additional information: | This version is the author accepted manuscript. For information on re-use, please refer to the publisher’s terms and conditions. |
| Keywords: | Filtering theory, Harmonic analysis, Power harmonic filters, Maximum likelihood detection, Nonlinear filters, Detectors, Computer vision |
| UCL classification: | UCL UCL > Provost and Vice Provost Offices > UCL BEAMS UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of Engineering Science UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of Engineering Science > Dept of Computer Science |
| URI: | https://discovery.ucl.ac.uk/id/eprint/10039219 |
Loading...
Loading...Loading...Loading...Archive Staff Only
 |
View Item |
