SAL-Net: Self-Supervised Attribute Learning for Object Recognition and Segmentation

Existing attribute learning methods rely on predefined attributes, which require manual annotations. Due to the limitation of human experience, the predefined attributes are not capable enough of providing enough description. This paper proposes a self-supervised attribute learning (SAL) method, whi...

Full description

Bibliographic Details

Published in:	Wireless communications and mobile computing Vol. 2021; no. 1
Main Authors:	Yang, Shu, JingWang, Arif, Sheeraz, Jia, Minli, Zhong, Shunan
Format:	Journal Article
Language:	English
Published:	Oxford Hindawi 2021 John Wiley & Sons, Inc
Subjects:	Algorithms Annotations Classification Datasets Dictionaries Image annotation Image classification Image segmentation Learning Neural networks Object recognition Semantic segmentation Semantics
ISSN:	1530-8669, 1530-8677
Online Access:	Get full text
Tags:	Add Tag No Tags, Be the first to tag this record!