University of Surrey

Test tubes in the lab Research in the ATI Dance Research

OCEAN: Object-Centric Arranging Network for Self-supervised Visual Representations Learning

Kim, Hansung, Hilton, Adrian, Sohn, Kwanghoon, Ham, Bumsub and Oh, Changjae (2019) OCEAN: Object-Centric Arranging Network for Self-supervised Visual Representations Learning Expert Systems with Applications, 125. pp 281-292.

ESWA-Camera-Ready-low.pdf - Accepted version Manuscript

Download (3MB) | Preview


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.

Item Type: Article
Divisions : Faculty of Engineering and Physical Sciences > Electronic Engineering > Centre for Vision Speech and Signal Processing
Authors :
Sohn, Kwanghoon
Ham, Bumsub
Oh, Changjae
Date : 1 July 2019
DOI : 10.1016/j.eswa.2019.01.073
Copyright Disclaimer : © 2019 Elsevier Ltd. All rights reserved.
Uncontrolled Keywords : Self-supervised learning, visual representations learning, object proposals, convolutional neural networks.
Depositing User : Users 6648 not found.
Date Deposited : 15 Feb 2019 15:29
Last Modified : 07 Feb 2020 02:08

Actions (login required)

View Item View Item


Downloads per month over past year

Information about this web site

© The University of Surrey, Guildford, Surrey, GU2 7XH, United Kingdom.
+44 (0)1483 300800