Learning object categories from internet image searches

Rob Fergus, Li Fei-Fei, Pietro Perona, Andrew Zisserman

Research output: Contribution to journalArticlepeer-review

Abstract

In this paper, we describe a simple approach to learning models of visual object categories from images gathered from Internet image search engines. The images for a given keyword are typically highly variable, with a large fraction being unrelated to the query term, and thus pose a challenging environment from which to learn. By training our models directly from Internet images, we remove the need to laboriously compile training data sets, required by most other recognition approachesthis opens up the possibility of learning object category models on-the-fly. We describe two simple approaches, derived from the probabilistic latent semantic analysis (pLSA) technique for text document analysis, that can be used to automatically learn object models from these data. We show two applications of the learned model: first, to rerank the images returned by the search engine, thus improving the quality of the search engine; and second, to recognize objects in other image data sets.

Original languageEnglish (US)
Article number5483225
Pages (from-to)1453-1466
Number of pages14
JournalProceedings of the IEEE
Volume98
Issue number8
DOIs
StatePublished - Aug 2010

Keywords

  • Internet image search engines
  • Learning
  • Object categories
  • Recognition
  • Unsupervised

ASJC Scopus subject areas

  • Electrical and Electronic Engineering

Fingerprint Dive into the research topics of 'Learning object categories from internet image searches'. Together they form a unique fingerprint.

Cite this