Web-supervised network for fine-grained visual classification

  • Chuanyi Zhang
  • , Yazhou Yao
  • , Jiachao Zhang
  • , Jiaxin Chen
  • , Pu Huang
  • , Jian Zhang
  • , Zhenmin Tang*
  • *Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

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.

Original languageEnglish
Title of host publication2020 IEEE International Conference on Multimedia and Expo, ICME 2020
PublisherIEEE Computer Society
ISBN (Electronic)9781728113319
DOIs
StatePublished - Jul 2020
Externally publishedYes
Event2020 IEEE International Conference on Multimedia and Expo, ICME 2020 - London, United Kingdom
Duration: 6 Jul 202010 Jul 2020

Publication series

NameProceedings - IEEE International Conference on Multimedia and Expo
Volume2020-July
ISSN (Print)1945-7871
ISSN (Electronic)1945-788X

Conference

Conference2020 IEEE International Conference on Multimedia and Expo, ICME 2020
Country/TerritoryUnited Kingdom
CityLondon
Period6/07/2010/07/20

Keywords

  • Fine-grained
  • Recognition
  • Web-supervised

Fingerprint

Dive into the research topics of 'Web-supervised network for fine-grained visual classification'. Together they form a unique fingerprint.

Cite this