Semantic combined network for zero-shot scene parsing

Wang, Yinduo, Zhang, Haofeng, Wang, Shidong, Long, Yang and Yang, Longzhi (2020) Semantic combined network for zero-shot scene parsing. IET Image Processing, 14 (4). pp. 757-765. ISSN 1751-9659

[img]
Preview
Text
30567.pdf - Accepted Version

Download (5MB) | Preview
Official URL: https://doi.org/10.1049/iet-ipr.2019.0870

Abstract

Recently, image-based scene parsing has attracted increasing attention due to its wide application. However, conventional models can only be valid on images with the same domain of the training set and are typically trained using discrete and meaningless labels. Inspired by the traditional zero-shot learning methods which employ auxiliary side information to bridge the source and target domains, the authors propose a novel framework called semantic combined network (SCN), which aims at learning a scene parsing model only from the images of the seen classes while targeting on the unseen ones. In addition, with the assistance of semantic embeddings of classes, the proposed SCN can further improve the performances of traditional fully supervised scene parsing methods. Extensive experiments are conducted on the data set Cityscapes, and the results show that the proposed SCN can perform well on both zero-shot scene parsing (ZSSP) and generalised ZSSP settings based on several state-of-the-art scenes parsing architectures. Furthermore, the authors test the proposed model under the traditional fully supervised setting and the results show that the proposed SCN can also significantly improve the performances of the original network models.

Item Type: Article
Uncontrolled Keywords: learning (artificial intelligence), natural language processing, object recognition, object detection, unsupervised learning
Subjects: G400 Computer Science
Department: Faculties > Engineering and Environment > Computer and Information Sciences
Depositing User: John Coen
Date Deposited: 04 Nov 2020 12:23
Last Modified: 31 Jul 2021 13:19
URI: http://nrl.northumbria.ac.uk/id/eprint/44681

Actions (login required)

View Item View Item

Downloads

Downloads per month over past year

View more statistics