Innamorati, C;
Ritschel, T;
Weyrich, T;
Mitra, NJ;
(2019)
Learning on the Edge: Investigating Boundary Filters in CNNs.
International Journal of Computer Vision
10.1007/s11263-019-01223-y.
(In press).
Preview |
Text
Innamorati2019_Article_LearningOnTheEdgeInvestigating.pdf - Published Version Download (1MB) | Preview |
Abstract
Convolutional neural networks (CNNs) handle the case where filters extend beyond the image boundary using several heuristics, such as zero, repeat or mean padding. These schemes are applied in an ad-hoc fashion and, being weakly related to the image content and oblivious of the target task, result in low output quality at the boundary. In this paper, we propose a simple and effective improvement that learns the boundary handling itself. At training-time, the network is provided with a separate set of explicit boundary filters. At testing-time, we use these filters which have learned to extrapolate features at the boundary in an optimal way for the specific task. Our extensive evaluation, over a wide range of architectural changes (variations of layers, feature channels, or both), shows how the explicit filters result in improved boundary handling. Furthermore, we investigate the efficacy of variations of such boundary filters with respect to convergence speed and accuracy. Finally, we demonstrate an improvement of 5–20% across the board of typical CNN applications (colorization, de-Bayering, optical flow, disparity estimation, and super-resolution). Supplementary material and code can be downloaded from the project page: http://geometry.cs.ucl.ac.uk/projects/2019/investigating-edge/.
| Type: | Article |
|---|---|
| Title: | Learning on the Edge: Investigating Boundary Filters in CNNs |
| Open access status: | An open access version is available from UCL Discovery |
| DOI: | 10.1007/s11263-019-01223-y |
| Publisher version: | https://doi.org/10.1007/s11263-019-01223-y |
| Language: | English |
| Additional information: | © The Author(s) 2019. This article is distributed under the terms of the Creative Commons Attribution 4.0 International License (http://creativecommons.org/licenses/by/4.0/), which permits unrestricted use, distribution, and reproduction in any medium, provided you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license, and indicate if changes were made. |
| Keywords: | Deep learning , Convolutional neural networks , Boundary rules , Boundary conditions |
| 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/10083777 |
Archive Staff Only
 |
View Item |
