Instance classification with prototype selection - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Conference Papers Year : 2014

Instance classification with prototype selection

Josip Krapac
  • Function : Author
  • PersonId : 885309
Teddy Furon
Hervé Jégou
  • Function : Author
  • PersonId : 833473


We address the problem of instance classification: our goal is to annotate images with tags corresponding to objects classes which exhibit small intra-class variations such as logos, products or landmarks. We propose a novel algorithm for the selection of class-specific prototypes which are used in a voting-based classification scheme. We show significant improvements over two state-of-the-art methods, namely the Fisher vector and Hamming Embedding, on two challenging methods of logos and vehicles.
Fichier principal
Vignette du fichier
icmr_krapac.pdf (808.89 Ko) Télécharger le fichier
Vignette du fichier
thumb.png (10.62 Ko) Télécharger le fichier
Origin : Files produced by the author(s)
Format : Figure, Image

Dates and versions

hal-00942275 , version 1 (05-02-2014)


  • HAL Id : hal-00942275 , version 1


Josip Krapac, Florent Perronnin, Teddy Furon, Hervé Jégou. Instance classification with prototype selection. ICMR - ACM International Conference on Multimedia Retrieval, Apr 2014, Glasgow, United Kingdom. ⟨hal-00942275⟩
310 View
666 Download


Gmail Facebook X LinkedIn More