Skip to main navigation Skip to search Skip to main content

SFCM: Learn a Pooling Kernel for Weakly Supervised Object Localization

  • Zongxian Li
  • , Yemin Shi
  • , Yonghong Tian*
  • , Wei Zeng
  • , Yaowei Wang
  • *Corresponding author for this work
  • Peking University
  • Beijing Institute of Technology

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

Abstract

The weakly supervised object localization (WSOL) is to locate the objects in an image while only image-level labels are available during the training procedure. In this work, the Selective Feature Category Mapping (SFCM) method is proposed, which introduces the Feature Category Mapping (FCM) and the widely-used selective search method to solve the WSOL task. Our FCM replaces layers after the specific layer in the state-of-the-art CNNs with a set of kernels and learns the weighted pooling for previous feature maps. It is trained with only image-level labels and then map the feature maps to their corresponding categories in the test phase. Together with selective search method, the location of each object is finally obtained. Extensive experimental evaluation on ILSVRC2012 and PASCAL VOC2007 benchmarks shows that SFCM is simple but very effective, and it is able to achieve outstanding classification performance and outperform the state-of-the-art methods in the WSOL task.

Original languageEnglish
Title of host publication2018 IEEE International Conference on Multimedia and Expo, ICME 2018
PublisherIEEE Computer Society
ISBN (Electronic)9781538617373
DOIs
StatePublished - 8 Oct 2018
Externally publishedYes
Event2018 IEEE International Conference on Multimedia and Expo, ICME 2018 - San Diego, United States
Duration: 23 Jul 201827 Jul 2018

Publication series

NameProceedings - IEEE International Conference on Multimedia and Expo
Volume2018-July
ISSN (Print)1945-7871
ISSN (Electronic)1945-788X

Conference

Conference2018 IEEE International Conference on Multimedia and Expo, ICME 2018
Country/TerritoryUnited States
CitySan Diego
Period23/07/1827/07/18

Keywords

  • Global Learnable Pooling (GLP)
  • Selective Feature Category Mapping (SFCM)
  • Weakly Supervised Object Localization (WSOL)

Fingerprint

Dive into the research topics of 'SFCM: Learn a Pooling Kernel for Weakly Supervised Object Localization'. Together they form a unique fingerprint.

Cite this