Learnable Descriptors for Visual Search - Archive ouverte HAL Access content directly
Journal Articles IEEE Transactions on Image Processing Year : 2021

Learnable Descriptors for Visual Search

Andrea Migliorati
  • Function : Author
  • PersonId : 1100600
Gianluca Francini
  • Function : Author
  • PersonId : 1100601
Riccardo Leonardi
  • Function : Author
  • PersonId : 1100602

Abstract

This work proposes LDVS, a learnable binary local descriptor devised for matching natural images within the MPEG CDVS framework. LDVS descriptors are learned so that they can be sign-quantized and compared using the Hamming distance. The underlying convolutional architecture enjoys a moderate parameters count for operations on mobile devices. Our experiments show that LDVS descriptors perform favorably over comparable learned binary descriptors at patch matching on two different datasets. A complete pair-wise image matching pipeline is then designed around LDVS descriptors, integrating them in the reference CDVS evaluation framework. Experiments show that LDVS descriptors outperform the compressed CDVS SIFT-like descriptors at pair-wise image matching over the challenging CDVS image dataset.
Fichier principal
Vignette du fichier
09238464 (1).pdf (3.06 Mo) Télécharger le fichier
Origin : Files produced by the author(s)

Dates and versions

hal-03245174 , version 1 (28-02-2022)

Identifiers

Cite

Andrea Migliorati, Attilio Fiandrotti, Gianluca Francini, Riccardo Leonardi. Learnable Descriptors for Visual Search. IEEE Transactions on Image Processing, 2021, 30, pp.80 - 91. ⟨10.1109/tip.2020.3031216⟩. ⟨hal-03245174⟩
17 View
35 Download

Altmetric

Share

Gmail Facebook Twitter LinkedIn More