Ensembles of Exemplar-SVMs have been introduced as a framework for Object Detection but have rapidly found a large interest in a wide variety of computer vision applications such as mid-level feature learning, tracking and segmentation. What makes this technique so attractive is the possibility of associating to instance specific classifiers one or more semantic labels that can be transferred at test time. To guarantee its effectiveness though, a large collection of classifiers has to be used. This directly translates in a high computational footprint, which could make the evaluation step prohibitive. To overcome this issue we organize Exemplar-SVMs into a taxonomy, exploiting the joint distribution of Exemplar scores. This permits to index the classifiers at a logarithmic cost, while maintaining the label transfer capabilities of the method almost unaffected. We propose different formulations of the taxonomy in order to maximize the speed gain. In particular we propose a highly efficient Vector Quantized Rejecting Taxonomy to discard unpromising image regions during evaluation, performing computations in a quantized domain. This allow us to obtain ramarkable speed gains, with an improvement up to more than two orders of magnitude. To verify the robustness of our indexing data structure with reference to a standard Exemplar-SVM ensemble, we experiment with the Pascal VOC 2007 benchmark on the Object Detection competition and on a simple segmentation task.

Indexing quantized ensembles of exemplar-SVMs with rejecting taxonomies / Becattini, Federico; Seidenari, Lorenzo; Del Bimbo, Alberto. - In: MULTIMEDIA TOOLS AND APPLICATIONS. - ISSN 1380-7501. - ELETTRONICO. - (2017), pp. 1-22. [10.1007/s11042-017-4794-7]

Indexing quantized ensembles of exemplar-SVMs with rejecting taxonomies

BECATTINI, FEDERICO;SEIDENARI, LORENZO;DEL BIMBO, ALBERTO
2017

Abstract

Ensembles of Exemplar-SVMs have been introduced as a framework for Object Detection but have rapidly found a large interest in a wide variety of computer vision applications such as mid-level feature learning, tracking and segmentation. What makes this technique so attractive is the possibility of associating to instance specific classifiers one or more semantic labels that can be transferred at test time. To guarantee its effectiveness though, a large collection of classifiers has to be used. This directly translates in a high computational footprint, which could make the evaluation step prohibitive. To overcome this issue we organize Exemplar-SVMs into a taxonomy, exploiting the joint distribution of Exemplar scores. This permits to index the classifiers at a logarithmic cost, while maintaining the label transfer capabilities of the method almost unaffected. We propose different formulations of the taxonomy in order to maximize the speed gain. In particular we propose a highly efficient Vector Quantized Rejecting Taxonomy to discard unpromising image regions during evaluation, performing computations in a quantized domain. This allow us to obtain ramarkable speed gains, with an improvement up to more than two orders of magnitude. To verify the robustness of our indexing data structure with reference to a standard Exemplar-SVM ensemble, we experiment with the Pascal VOC 2007 benchmark on the Object Detection competition and on a simple segmentation task.
2017
1
22
Becattini, Federico; Seidenari, Lorenzo; Del Bimbo, Alberto
File in questo prodotto:
File Dimensione Formato  
mtap17.pdf

Accesso chiuso

Tipologia: Pdf editoriale (Version of record)
Licenza: Tutti i diritti riservati
Dimensione 5.63 MB
Formato Adobe PDF
5.63 MB Adobe PDF   Richiedi una copia

I documenti in FLORE sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificatore per citare o creare un link a questa risorsa: https://hdl.handle.net/2158/1085396
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 3
  • ???jsp.display-item.citation.isi??? 3
social impact