Coarse to Fine: Multi-label Image Classification with Global/Local Attention

Fan Lyu, Fuyuan Hu, Victor S. Sheng, Zhengtian Wu, Qiming Fu, Baochuan Fu

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

4 Scopus citations

Abstract

In our daily life, the scenes around us are always with multiple labels especially in a smart city, i.e., recognizing the information of city operation to response and control. Great efforts have been made by using Deep Neural Networks to recognize multi-label images. Since multi-label image classification is very complicated, people seek to use the attention mechanism to guide the classification process. However, conventional attention-based methods always analyzed images directly and aggressively. It is difficult for them to well understand complicated scenes. In this paper, we propose a global/local attention method that can recognize an image from coarse to fine by mimicking how human-beings observe images. Specifically, our global/local attention method first concentrates on the whole image, and then focuses on local specific objects in the image. We also propose a joint max-margin objective function, which enforces that the minimum score of positive labels should be larger than the maximum score of negative labels horizontally and vertically. This function can further improve our multi-label image classification method. We evaluate the effectiveness of our method on two popular multilabel image datasets (i.e., Pascal VOC and MS-COCO). Our experimental results show that our method outperforms state-of-The-Art methods.

Original languageEnglish
Title of host publication2018 IEEE International Smart Cities Conference, ISC2 2018
PublisherInstitute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)9781538659595
DOIs
StatePublished - Feb 28 2019
Event2018 IEEE International Smart Cities Conference, ISC2 2018 - Kansas City, United States
Duration: Sep 16 2018Sep 19 2018

Publication series

Name2018 IEEE International Smart Cities Conference, ISC2 2018

Conference

Conference2018 IEEE International Smart Cities Conference, ISC2 2018
CountryUnited States
CityKansas City
Period09/16/1809/19/18

Keywords

  • Deep learning
  • Multi-label image classification
  • Scene recognition

Fingerprint Dive into the research topics of 'Coarse to Fine: Multi-label Image Classification with Global/Local Attention'. Together they form a unique fingerprint.

Cite this