Neural Architecture Search for Portrait Parsing.

Lyu, B; Yang, Y; Wen, S; Huang, T; Li, K

Neural Architecture Search for Portrait Parsing.

Lyu, B Yang, Y Wen, S

Huang, T Li, K

Permalink

Publisher:: Institute of Electrical and Electronics Engineers (IEEE)
Publication Type:: Journal Article
Citation:: IEEE Trans Neural Netw Learn Syst, 2022, PP, (99), pp. 1-10
Issue Date:: 2022-01-01

Closed Access

	Filename	Description	Size
	Neural Architecture Search for Portrait Parsing.pdf	Published version	2.15 MB	Adobe PDF	View/Open

Copyright Clearance Process

Recently Added
In Progress
Closed Access

This item is closed access and not available.

Full metadata record

Field	Value	Language
dc.contributor.author	Lyu, B
dc.contributor.author	Yang, Y
dc.contributor.author	Wen, S https://orcid.org/0000-0001-8077-7001
dc.contributor.author	Huang, T
dc.contributor.author	Li, K
dc.date.accessioned	2023-02-28T04:09:53Z
dc.date.available	2023-02-28T04:09:53Z
dc.date.issued	2022-01-01
dc.identifier.citation	IEEE Trans Neural Netw Learn Syst, 2022, PP, (99), pp. 1-10
dc.identifier.issn	2162-237X
dc.identifier.issn	2162-2388
dc.identifier.uri	http://hdl.handle.net/10453/166550
dc.description.abstract	This work proposes a neural architecture search (NAS) method for portrait parsing, which is a novel up-level task based on portrait segmentation and face labeling. Recently, NAS has become an effective method in terms of automatic machine learning. However, remarkable achievements have been made only in image classification and natural language processing (NLP) areas. Meanwhile, state-of-the-art portrait segmentation and face labeling approaches are all manually designed, but few models reach a tradeoff between efficiency and performance. Thus, we are extremely interested in improving existing NAS methods for dense-per-pixel prediction tasks on portrait datasets. To achieve that, we resort to a cell-based encoder-decoder architecture with an elaborate design of connectivity structure and searching space. As a result, we achieve state-of-the-art performance on three portrait tasks, including 96.8% MIOU on EG1800 (portrait segmentation), 91.2% overall F1-score on HELEN (face labeling), and 95.1% overall F1-score on CelebAMask-HQ (portrait parsing) with only 2.29M model parameters. That is, our approach compares favorably with all previous works on portrait datasets. More crucially, we empirically prove that even a fundamental encoder-decoder architecture may reach an outstanding result on the aforementioned tasks with the help of the innovative approach of NAS. To the best of our knowledge, our work is also the first to report the success of applying NAS on these portrait tasks.
dc.format	Print-Electronic
dc.language	eng
dc.publisher	Institute of Electrical and Electronics Engineers (IEEE)
dc.relation.ispartof	IEEE Trans Neural Netw Learn Syst
dc.relation.isbasedon	10.1109/TNNLS.2021.3104872
dc.rights	info:eu-repo/semantics/closedAccess
dc.subject.classification	Artificial Intelligence & Image Processing
dc.title	Neural Architecture Search for Portrait Parsing.
dc.type	Journal Article
utslib.citation.volume	PP
utslib.location.activity	United States
pubs.organisational-group	/University of Technology Sydney
pubs.organisational-group	/University of Technology Sydney/Faculty of Engineering and Information Technology
pubs.organisational-group	/University of Technology Sydney/Strength - AAII - Australian Artificial Intelligence Institute
utslib.copyright.status	closed_access	*
pubs.consider-herdc	false
dc.date.updated	2023-02-28T04:09:52Z
pubs.issue	99
pubs.publication-status	Published online
pubs.volume	PP
utslib.citation.issue	99

Abstract:

This work proposes a neural architecture search (NAS) method for portrait parsing, which is a novel up-level task based on portrait segmentation and face labeling. Recently, NAS has become an effective method in terms of automatic machine learning. However, remarkable achievements have been made only in image classification and natural language processing (NLP) areas. Meanwhile, state-of-the-art portrait segmentation and face labeling approaches are all manually designed, but few models reach a tradeoff between efficiency and performance. Thus, we are extremely interested in improving existing NAS methods for dense-per-pixel prediction tasks on portrait datasets. To achieve that, we resort to a cell-based encoder-decoder architecture with an elaborate design of connectivity structure and searching space. As a result, we achieve state-of-the-art performance on three portrait tasks, including 96.8% MIOU on EG1800 (portrait segmentation), 91.2% overall F1-score on HELEN (face labeling), and 95.1% overall F1-score on CelebAMask-HQ (portrait parsing) with only 2.29M model parameters. That is, our approach compares favorably with all previous works on portrait datasets. More crucially, we empirically prove that even a fundamental encoder-decoder architecture may reach an outstanding result on the aforementioned tasks with the help of the innovative approach of NAS. To the best of our knowledge, our work is also the first to report the success of applying NAS on these portrait tasks.

Please use this identifier to cite or link to this item:

http://hdl.handle.net/10453/166550