Beyond IID: Learning to combine Non-IID metrics for vision tasks

Shi, Y; Li, W; Gao, Y; Cao, L; Shen, D

Beyond IID: Learning to combine Non-IID metrics for vision tasks

Shi, Y Li, W Gao, Y Cao, L

Shen, D

Permalink

Publication Type:: Conference Proceeding
Citation:: 31st AAAI Conference on Artificial Intelligence, AAAI 2017, 2017, pp. 1524 - 1531
Issue Date:: 2017-01-01

Closed Access

	Filename	Description	Size
	14688-66430-1-PB.pdf	Published version	2.97 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	Shi, Y	en_US
dc.contributor.author	Li, W	en_US
dc.contributor.author	Gao, Y	en_US
dc.contributor.author	Cao, L https://orcid.org/0000-0003-1562-9429	en_US
dc.contributor.author	Shen, D	en_US
dc.date.issued	2017-01-01	en_US
dc.identifier.citation	31st AAAI Conference on Artificial Intelligence, AAAI 2017, 2017, pp. 1524 - 1531	en_US
dc.identifier.uri	http://hdl.handle.net/10453/125821
dc.description.abstract	Copyright © 2017, Association for the Advancement of Artificial Intelligence (www.aaai.org). All rights reserved. Metric learning has been widely employed, especially in various computer vision tasks, with the fundamental assumption that all samples (e.g., regions/superpixels in images/videos) are independent and identically distributed (IID). However, since the samples are usually spatially-connected or temporally-correlated with their physically-connected neighbours, they are not IID (non-IID for short), which cannot be directly handled by existing methods. Thus, we propose to learn and integrate non-IID metrics (NIME). To incorporate the non-IID spatial/temporal relations, instead of directly using non-IID features and metric learning as previous methods, NIME first builds several non-IID representations on original (non-IID) features by various graph kernel functions, and then automatically learns the metric under the best combination of various non-IID representations. NIME is applied to solve two typical computer vision tasks: interactive image segmentation and histology image identification. The results show that learning and integrating non-IID metrics improves the performance, compared to the IID methods. Moreover, our method achieves results comparable or better than that of the state-of-the-arts.	en_US
dc.relation.ispartof	31st AAAI Conference on Artificial Intelligence, AAAI 2017	en_US
dc.title	Beyond IID: Learning to combine Non-IID metrics for vision tasks	en_US
dc.type	Conference Proceeding
utslib.for	0801 Artificial Intelligence and Image Processing	en_US
pubs.embargo.period	Not known	en_US
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 - AAI - Advanced Analytics Institute Research Centre
utslib.copyright.status	closed_access
pubs.publication-status	Published	en_US

Abstract:

Copyright © 2017, Association for the Advancement of Artificial Intelligence (www.aaai.org). All rights reserved. Metric learning has been widely employed, especially in various computer vision tasks, with the fundamental assumption that all samples (e.g., regions/superpixels in images/videos) are independent and identically distributed (IID). However, since the samples are usually spatially-connected or temporally-correlated with their physically-connected neighbours, they are not IID (non-IID for short), which cannot be directly handled by existing methods. Thus, we propose to learn and integrate non-IID metrics (NIME). To incorporate the non-IID spatial/temporal relations, instead of directly using non-IID features and metric learning as previous methods, NIME first builds several non-IID representations on original (non-IID) features by various graph kernel functions, and then automatically learns the metric under the best combination of various non-IID representations. NIME is applied to solve two typical computer vision tasks: interactive image segmentation and histology image identification. The results show that learning and integrating non-IID metrics improves the performance, compared to the IID methods. Moreover, our method achieves results comparable or better than that of the state-of-the-arts.

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

http://hdl.handle.net/10453/125821