Regression of Instance Boundary by Aggregated CNN and GCN

Meng, Y ORCID: 0000-0001-7344-2174, Meng, W, Gao, D ORCID: 0000-0001-7008-0737, Zhao, Y, Yang, X, Huang, X ORCID: 0000-0001-6267-0366 and Zheng, Y ORCID: 0000-0002-7873-0922 (2020) Regression of Instance Boundary by Aggregated CNN and GCN In: ECCV, 2020-8-23 - 2020-7-28, Edinburgh, UK.

Text ECCV_2020_camera.pdf - Author Accepted Manuscript Download (2MB) | Preview

Abstract

This paper proposes a straightforward, intuitive deep learning approach for (biomedical) image segmentation tasks. Different from the existing dense pixel classification methods, we develop a novel multi-level aggregation network to directly regress the coordinates of the boundary of instances in an end-to-end manner. The network seamlessly combines standard convolution neural network (CNN) with Attention Refinement Module (ARM) and Graph Convolution Network (GCN). By iteratively and hierarchically fusing the features across different layers of the CNN, our approach gains sufficient semantic information from the input image and pays special attention to the local boundaries with the help of ARM and GCN. In particular, thanks to the proposed aggregation GCN, our network benefits from direct feature learning of the instances’ boundary locations and the spatial information propagation across the image. Experiments on several challenging datasets demonstrate that our method achieves comparable results with state-of-the-art approaches but requires less inference time on the segmentation of fetal head in ultrasound images and of optic disc and optic cup in color fundus images.

Item Type:	Conference Item (Unspecified)
Uncontrolled Keywords:	Regression, Semantic segmentation, CNN, GCN, Attention, Aggregation
Depositing User:	Symplectic Admin
Date Deposited:	04 Aug 2020 09:42
Last Modified:	28 Feb 2026 14:29
DOI:	10.1007/978-3-030-58598-3_12
Related Websites:	Author Publisher
URI:	https://livrepository.liverpool.ac.uk/id/eprint/3095903
Disclaimer:	The University of Liverpool is not responsible for content contained on other websites from links within repository metadata. Please contact us if you notice anything that appears incorrect or inappropriate.