Web-supervised network for fine-grained visual classification

Zhang, C; Yao, Y; Zhang, J; Chen, J; Huang, P; Zhang, J; Tang, Z

Web-supervised network for fine-grained visual classification

Zhang, C Yao, Y Zhang, J

Chen, J Huang, P Zhang, J

Tang, Z

Permalink

Publisher:: IEEE
Publication Type:: Conference Proceeding
Citation:: Proceedings - IEEE International Conference on Multimedia and Expo, 2020, 2020-July, pp. 1-6
Issue Date:: 2020-07-01

Closed Access

	Filename	Description	Size
	09102790.pdf	Published version	603.6 kB	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	Zhang, C
dc.contributor.author	Yao, Y
dc.contributor.author	Zhang, J https://orcid.org/0000-0002-7240-3541
dc.contributor.author	Chen, J
dc.contributor.author	Huang, P
dc.contributor.author	Zhang, J https://orcid.org/0000-0002-7240-3541
dc.contributor.author	Tang, Z
dc.date	2020-07-06
dc.date.accessioned	2020-10-06T02:01:33Z
dc.date.available	2020-10-06T02:01:33Z
dc.date.issued	2020-07-01
dc.identifier.citation	Proceedings - IEEE International Conference on Multimedia and Expo, 2020, 2020-July, pp. 1-6
dc.identifier.isbn	9781728113319
dc.identifier.issn	1945-7871
dc.identifier.issn	1945-788X
dc.identifier.uri	http://hdl.handle.net/10453/143098
dc.description.abstract	© 2020 IEEE. Fine-grained visual classification (FGVC) is a tough task due to its high annotation cost of the fine-grained subcategories. To build a large-scale dataset at low manual cost, straightforwardly learning from web images for FGVC has attracted broad attention. However, there exist two characteristics in the need of concerning for the web dataset: 1) Noisy images; 2) A large proportion of hard examples. In this paper, we propose a simple yet effective approach to deal with noisy images and hard examples during training. Our method is a pure web-supervised method for FGVC. Extensive experiments on three commonly used fine-grained datasets demonstrate that our approach is much superior to the state-of-the-art web-supervised methods. The data and source code of this work have been posted available at: https://github.com/NUST-Machine-Intelligence-Laboratory/WSNFG.
dc.language	en
dc.publisher	IEEE
dc.relation.ispartof	Proceedings - IEEE International Conference on Multimedia and Expo
dc.relation.ispartof	2020 IEEE International Conference on Multimedia and Expo (ICME)
dc.relation.isbasedon	10.1109/ICME46284.2020.9102790
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/closedAccess
dc.title	Web-supervised network for fine-grained visual classification
dc.type	Conference Proceeding
utslib.citation.volume	2020-July
pubs.organisational-group	/University of Technology Sydney/Faculty of Engineering and Information Technology
pubs.organisational-group	/University of Technology Sydney/Strength - GBDTC - Global Big Data Technologies
pubs.organisational-group	/University of Technology Sydney/Faculty of Engineering and Information Technology/School of Electrical and Data Engineering
pubs.organisational-group	/University of Technology Sydney
utslib.copyright.status	closed_access	*
dc.date.updated	2020-10-06T02:01:28Z
pubs.finish-date	2020-07-10
pubs.publication-status	Published
pubs.start-date	2020-07-06
pubs.volume	2020-July

Abstract:

© 2020 IEEE. Fine-grained visual classification (FGVC) is a tough task due to its high annotation cost of the fine-grained subcategories. To build a large-scale dataset at low manual cost, straightforwardly learning from web images for FGVC has attracted broad attention. However, there exist two characteristics in the need of concerning for the web dataset: 1) Noisy images; 2) A large proportion of hard examples. In this paper, we propose a simple yet effective approach to deal with noisy images and hard examples during training. Our method is a pure web-supervised method for FGVC. Extensive experiments on three commonly used fine-grained datasets demonstrate that our approach is much superior to the state-of-the-art web-supervised methods. The data and source code of this work have been posted available at: https://github.com/NUST-Machine-Intelligence-Laboratory/WSNFG.

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

http://hdl.handle.net/10453/143098