Embedding based on function approximation for large scale image search

Thanh-Toan Do, Ngai-Man Cheung

Research output: Contribution to journalArticleResearchpeer-review

14 Citations (Scopus)

Abstract

The objective of this paper is to design an embedding method that maps local features describing an image (e.g., SIFT) to a higher dimensional representation useful for the image retrieval problem. First, motivated by the relationship between the linear approximation of a nonlinear function in high dimensional space and the state-of-The-Art feature representation used in image retrieval, i.e., VLAD, we propose a new approach for the approximation. The embedded vectors resulted by the function approximation process are then aggregated to form a single representation for image retrieval. Second, in order to make the proposed embedding method applicable to large scale problem, we further derive its fast version in which the embedded vectors can be efficiently computed, i.e., in the closed-form. We compare the proposed embedding methods with the state of the art in the context of image search under various settings: when the images are represented by medium length vectors, short vectors, or binary vectors. The experimental results show that the proposed embedding methods outperform existing the state of the art on the standard public image retrieval benchmarks.

Original languageEnglish
Pages (from-to)626-638
Number of pages13
JournalIEEE Transactions on Pattern Analysis and Machine Intelligence
Volume40
Issue number3
DOIs
Publication statusPublished - 1 Mar 2018
Externally publishedYes

Keywords

  • Feature embedding
  • Function approximation
  • Image search

Cite this