The University of Southampton
University of Southampton Institutional Repository

Gaussian dynamic convolution for efficient single-image segmentation

Gaussian dynamic convolution for efficient single-image segmentation
Gaussian dynamic convolution for efficient single-image segmentation
Interactive single-image segmentation is ubiquitous in the scientific and commercial imaging software. Lightweight neural network is one practical and effective way to accomplish the single-image segmentation task. This work focuses on the single-image segmentation problem only with some seeds such
as scribbles. Inspired by the dynamic receptive field in the human being’s visual system, we propose the Gaussian dynamic convolution (GDC) to fast and efficiently aggregate the contextual information for neural networks. The core idea is randomly selecting the spatial sampling area according to the Gaussian
distribution offsets. Our GDC can be easily used as a module to build lightweight or complex segmentation networks. We adopt the proposed GDC to address the typical single-image segmentation tasks. Furthermore, we also build a Gaussian dynamic pyramid Pooling to show its potential and generality in common semantic segmentation. Experiments demonstrate that the GDC outperforms other existing convolutions on three benchmark segmentation datasets including Pascal-Context, Pascal-VOC 2012, and Cityscapes. Additional experiments are also conducted to illustrate that the GDC can produce richer and more vivid features compared with other convolutions. In general, our GDC is conducive to the convolutional neural networks to form an overall impression of the image.
Sun, Xin
0838ca15-5141-4bf6-8faa-7d59e508bf39
Chen, Changrui
6ea14b1f-5be0-4dd9-8603-b221cd66ad20
Wang, Xiaorui
0c9b2f71-030f-42aa-8a37-274d3883afbc
Dong, Junyu
f412ed20-b213-4c97-b0fd-f77262d6ab2f
Zhou, Huiyu
3180d70f-059b-4421-b5c5-34707b3e5504
Chen, Sheng
9310a111-f79a-48b8-98c7-383ca93cbb80
Sun, Xin
0838ca15-5141-4bf6-8faa-7d59e508bf39
Chen, Changrui
6ea14b1f-5be0-4dd9-8603-b221cd66ad20
Wang, Xiaorui
0c9b2f71-030f-42aa-8a37-274d3883afbc
Dong, Junyu
f412ed20-b213-4c97-b0fd-f77262d6ab2f
Zhou, Huiyu
3180d70f-059b-4421-b5c5-34707b3e5504
Chen, Sheng
9310a111-f79a-48b8-98c7-383ca93cbb80

Sun, Xin, Chen, Changrui, Wang, Xiaorui, Dong, Junyu, Zhou, Huiyu and Chen, Sheng (2021) Gaussian dynamic convolution for efficient single-image segmentation. IEEE Transactions on Circuits and Ssystems for Video Technology. (In Press)

Record type: Article

Abstract

Interactive single-image segmentation is ubiquitous in the scientific and commercial imaging software. Lightweight neural network is one practical and effective way to accomplish the single-image segmentation task. This work focuses on the single-image segmentation problem only with some seeds such
as scribbles. Inspired by the dynamic receptive field in the human being’s visual system, we propose the Gaussian dynamic convolution (GDC) to fast and efficiently aggregate the contextual information for neural networks. The core idea is randomly selecting the spatial sampling area according to the Gaussian
distribution offsets. Our GDC can be easily used as a module to build lightweight or complex segmentation networks. We adopt the proposed GDC to address the typical single-image segmentation tasks. Furthermore, we also build a Gaussian dynamic pyramid Pooling to show its potential and generality in common semantic segmentation. Experiments demonstrate that the GDC outperforms other existing convolutions on three benchmark segmentation datasets including Pascal-Context, Pascal-VOC 2012, and Cityscapes. Additional experiments are also conducted to illustrate that the GDC can produce richer and more vivid features compared with other convolutions. In general, our GDC is conducive to the convolutional neural networks to form an overall impression of the image.

Text
Gaussian_Dynamic_Convolution - Accepted Manuscript
Restricted to Repository staff only until 9 July 2023.
Request a copy

More information

Accepted/In Press date: 9 July 2021

Identifiers

Local EPrints ID: 451260
URI: http://eprints.soton.ac.uk/id/eprint/451260
PURE UUID: 5b5f69be-fe3d-4a55-81b4-c696ca9dddac

Catalogue record

Date deposited: 15 Sep 2021 16:31
Last modified: 21 Oct 2021 17:20

Export record

Contributors

Author: Xin Sun
Author: Changrui Chen
Author: Xiaorui Wang
Author: Junyu Dong
Author: Huiyu Zhou
Author: Sheng Chen

University divisions

Download statistics

Downloads from ePrints over the past year. Other digital versions may also be available to download e.g. from the publisher's website.

View more statistics

Atom RSS 1.0 RSS 2.0

Contact ePrints Soton: eprints@soton.ac.uk

ePrints Soton supports OAI 2.0 with a base URL of http://eprints.soton.ac.uk/cgi/oai2

This repository has been built using EPrints software, developed at the University of Southampton, but available to everyone to use.

We use cookies to ensure that we give you the best experience on our website. If you continue without changing your settings, we will assume that you are happy to receive cookies on the University of Southampton website.

×