Loughborough University
Leicestershire, UK
LE11 3TU
+44 (0)1509 263171
Loughborough University

Loughborough University Institutional Repository

Please use this identifier to cite or link to this item: https://dspace.lboro.ac.uk/2134/35360

Title: A fully convolutional two-stream fusion network for interactive image segmentation
Authors: Hu, Yang
Soltoggio, Andrea
Lock, Russell
Carter, Steve
Keywords: Interactive image segmentation
Fully convolutional network
Two-stream network
Issue Date: 2018
Publisher: © Elsevier
Citation: HU, Y. ... et al, 2018. A fully convolutional two-stream fusion network for interactive image segmentation. Neural Networks, 109, pp.31-42.
Abstract: In this paper, we propose a novel fully convolutional two-stream fusion network (FCTSFN) for interactive image segmentation. The proposed network includes two sub-networks: a two-stream late fusion network (TSLFN) that predicts the foreground at a reduced resolution, and a multi-scale refining network (MSRN) that refines the foreground at full resolution. The TSLFN includes two distinct deep streams followed by a fusion network. The intuition is that, since user interactions are more direction information on foreground/background than the image itself, the two-stream structure of the TSLFN reduces the number of layers between the pure user interaction features and the network output, allowing the user interactions to have a more direct impact on the segmentation result. The MSRN fuses the features from different layers of TSLFN with different scales, in order to seek the local to global information on the foreground to refine the segmentation result at full resolution. We conduct comprehensive experiments on four benchmark datasets. The results show that the proposed network achieves competitive performance compared to current state-of-the-art interactive image segmentation methods.
Description: This paper is closed access until 21 October 2019.
Sponsor: This work was supported by Ice Communication Limited and Innovate UK (project KTP/10412).
Version: Accepted for publication
DOI: 10.1016/j.neunet.2018.10.009
URI: https://dspace.lboro.ac.uk/2134/35360
Publisher Link: https://doi.org/10.1016/j.neunet.2018.10.009
ISSN: 0893-6080
Appears in Collections:Closed Access (Computer Science)

Files associated with this item:

File Description SizeFormat
elsarticle-template.pdfAccepted version8.68 MBAdobe PDFView/Open


SFX Query

Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.