The University of Southampton
University of Southampton Institutional Repository

OCEAN: Object-centric arranging network for self-supervised visual representations learning

OCEAN: Object-centric arranging network for self-supervised visual representations learning
OCEAN: Object-centric arranging network for self-supervised visual representations learning
Learning visual representations plays an important role in computer vision and machine learning applications. It facilitates a model to understand and perform high-level tasks intelligently. A common approach for learning visual representations is supervised one which requires a huge amount of human annotations to train the model. This paper presents a self-supervised approach which learns visual representations from input images without human annotations. We learn the correct arrangement of object proposals to represent an image using a convolutional neural network (CNN) without any manual annotations. We hypothesize that the network trained for solving this problem requires the embedding of semantic visual representations. Unlike existing approaches that use uniformly sampled patches, we relate object proposals that contain prominent objects and object parts. More specifically, we discover the representation that considers overlap, inclusion, and exclusion relationship of proposals as well as their relative position. This allows focusing on potential objects and parts rather than on clutter. We demonstrate that our model outperforms existing self-supervised learning methods and can be used as a generic feature extractor by applying it to object detection, classification, action recognition, image retrieval, and semantic matching tasks.
0957-4174
218-292
Oh, Changjae
8b3237c1-cee5-41e7-b983-1057c9c9cd3f
Ham, Beomsup
e57b8c7b-445f-438a-89fa-37a038946e6b
Kim, Hansung
2c7c135c-f00b-4409-acb2-85b3a9e8225f
Hilton, Adrian
66073dc9-2a0a-424a-b68c-4523285a4876
Sohn, Kwanghoon
15547878-23a1-4428-90b5-64842ce10dff
Oh, Changjae
8b3237c1-cee5-41e7-b983-1057c9c9cd3f
Ham, Beomsup
e57b8c7b-445f-438a-89fa-37a038946e6b
Kim, Hansung
2c7c135c-f00b-4409-acb2-85b3a9e8225f
Hilton, Adrian
66073dc9-2a0a-424a-b68c-4523285a4876
Sohn, Kwanghoon
15547878-23a1-4428-90b5-64842ce10dff

Oh, Changjae, Ham, Beomsup, Kim, Hansung, Hilton, Adrian and Sohn, Kwanghoon (2019) OCEAN: Object-centric arranging network for self-supervised visual representations learning. Expert Systems with Applications, 125, 218-292. (doi:10.1016/j.eswa.2019.01.073).

Record type: Article

Abstract

Learning visual representations plays an important role in computer vision and machine learning applications. It facilitates a model to understand and perform high-level tasks intelligently. A common approach for learning visual representations is supervised one which requires a huge amount of human annotations to train the model. This paper presents a self-supervised approach which learns visual representations from input images without human annotations. We learn the correct arrangement of object proposals to represent an image using a convolutional neural network (CNN) without any manual annotations. We hypothesize that the network trained for solving this problem requires the embedding of semantic visual representations. Unlike existing approaches that use uniformly sampled patches, we relate object proposals that contain prominent objects and object parts. More specifically, we discover the representation that considers overlap, inclusion, and exclusion relationship of proposals as well as their relative position. This allows focusing on potential objects and parts rather than on clutter. We demonstrate that our model outperforms existing self-supervised learning methods and can be used as a generic feature extractor by applying it to object detection, classification, action recognition, image retrieval, and semantic matching tasks.

Full text not available from this repository.

More information

Accepted/In Press date: 29 January 2019
e-pub ahead of print date: 6 February 2019
Published date: July 2019

Identifiers

Local EPrints ID: 439649
URI: http://eprints.soton.ac.uk/id/eprint/439649
ISSN: 0957-4174
PURE UUID: 4f9f6688-2945-49f1-8ce4-0a14c46bda2e
ORCID for Hansung Kim: ORCID iD orcid.org/0000-0003-4907-0491

Catalogue record

Date deposited: 29 Apr 2020 16:30
Last modified: 07 Oct 2020 02:27

Export record

Altmetrics

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.

×