Learning a mixture of granularity-specific experts for fine-grained categorization

Zhang, L; Huang, S; Liu, W; Tao, D

Learning a mixture of granularity-specific experts for fine-grained categorization

Zhang, L Huang, S Liu, W Tao, D

Permalink

Publisher:: IEEE
Publication Type:: Conference Proceeding
Citation:: Proceedings of the IEEE International Conference on Computer Vision, 2020, 2019-October, pp. 8330-8339
Issue Date:: 2020

Open Access

Copyright Clearance Process

Recently Added
In Progress
Open Access

This item is open access.

Adobe PDF

Download Accepted manuscriptAdobe PDF (1.36 MB)

View on publisher's site

View statistics

Full metadata record

Field	Value	Language
dc.contributor.author	Zhang, L
dc.contributor.author	Huang, S
dc.contributor.author	Liu, W
dc.contributor.author	Tao, D https://orcid.org/0000-0001-7225-5449
dc.date	2019-10-27
dc.date.accessioned	2021-01-21T04:49:03Z
dc.date.available	2021-01-21T04:49:03Z
dc.date.issued	2020
dc.identifier.citation	Proceedings of the IEEE International Conference on Computer Vision, 2020, 2019-October, pp. 8330-8339
dc.identifier.isbn	9781728148038
dc.identifier.issn	1550-5499
dc.identifier.issn	2380-7504
dc.identifier.uri	http://hdl.handle.net/10453/145526
dc.description.abstract	© 2019 IEEE. We aim to divide the problem space of fine-grained recognition into some specific regions. To achieve this, we develop a unified framework based on a mixture of experts. Due to limited data available for the fine-grained recognition problem, it is not feasible to learn diverse experts by using a data division strategy. To tackle the problem, we promote diversity among experts by combing an expert gradually-enhanced learning strategy and a Kullback-Leibler divergence based constraint. The strategy learns new experts on the dataset with the prior knowledge from former experts and adds them to the model sequentially, while the introduced constraint forces the experts to produce diverse prediction distribution. These drive the experts to learn the task from different aspects, making them specialized in different subspace problems. Experiments show that the resulting model improves the classification performance and achieves the state-of-the-art performance on several fine-grained benchmark datasets.
dc.language	en
dc.publisher	IEEE
dc.relation	http://purl.org/au-research/grants/arc/DP180103424
dc.relation.ispartof	Proceedings of the IEEE International Conference on Computer Vision
dc.relation.ispartof	IEEE/CVF International Conference on Computer Vision
dc.relation.isbasedon	10.1109/ICCV.2019.00842
dc.rights	© 2020 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.	en_US
dc.rights	info:eu-repo/semantics/openAccess
dc.title	Learning a mixture of granularity-specific experts for fine-grained categorization
dc.type	Conference Proceeding
utslib.citation.volume	2019-October
utslib.location.activity	Seoul, Korea (South)
pubs.organisational-group	/University of Technology Sydney/Faculty of Engineering and Information Technology
pubs.organisational-group	/University of Technology Sydney
utslib.copyright.status	open_access	*
pubs.consider-herdc	false
dc.date.updated	2021-01-21T04:48:25Z
pubs.finish-date	2019-11-02
pubs.place-of-publication	Piscataway, USA
pubs.publication-status	Published
pubs.start-date	2019-10-27
pubs.volume	2019-October
dc.location	Piscataway, USA

Abstract:

© 2019 IEEE. We aim to divide the problem space of fine-grained recognition into some specific regions. To achieve this, we develop a unified framework based on a mixture of experts. Due to limited data available for the fine-grained recognition problem, it is not feasible to learn diverse experts by using a data division strategy. To tackle the problem, we promote diversity among experts by combing an expert gradually-enhanced learning strategy and a Kullback-Leibler divergence based constraint. The strategy learns new experts on the dataset with the prior knowledge from former experts and adds them to the model sequentially, while the introduced constraint forces the experts to produce diverse prediction distribution. These drive the experts to learn the task from different aspects, making them specialized in different subspace problems. Experiments show that the resulting model improves the classification performance and achieves the state-of-the-art performance on several fine-grained benchmark datasets.

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

http://hdl.handle.net/10453/145526