Innamorati, C; Ritschel, T; Weyrich, T; Mitra, N; (2018) Learning on the Edge: Explicit Boundary Handling in CNNs. Proceedings of the British Machine Vision Conference (BMVC)

Preview

Text LEdge.pdf - Accepted Version Download (8MB) | 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. Consequently, we demonstrate an improvement of 5 % to 20 % across the board of typical CNN applications (colorization, de-Bayering, optical flow, and disparity estimation)

Download activity - last month

Export as JSONXMLCSV

Download activity - last 12 months

Export as CSVXMLJSON

Downloads by country - last 12 months

Export as XMLCSVJSON

Archive Staff Only

View Item