Spatially Localized Visual Dictionary Learning - Archive ouverte HAL Access content directly
Conference Papers Year : 2016

Spatially Localized Visual Dictionary Learning

(1, 2) , (1) , (2) , (1)


This paper addresses the challenge of devising new representation learning algorithms that overcome the lack of interpretability of classical visual models. Therefore, it introduces a new recursive visual patch selection technique built on top of a Shared Nearest Neighbors embedding method. The main contribution of the paper is to drastically reduce the high-dimensionality of such over-complete representation thanks to a recursive feature elimination method. We show that the number of spatial atoms of the representation can be reduced by up to two orders of magnitude without much degrading the encoded information. The resulting representations are shown to provide competitive image classification performance with the state-of-the-art while enabling to learn highly interpretable visual models.
Fichier principal
Vignette du fichier
LeveauICMR2016.pdf (9.03 Mo) Télécharger le fichier
Origin : Files produced by the author(s)

Dates and versions

hal-01373778 , version 1 (05-10-2016)



Valentin Leveau, Alexis Joly, Olivier Buisson, Patrick Valduriez. Spatially Localized Visual Dictionary Learning. ICMR: International Conference on Multimedia Retrieval, Jun 2016, New York, United States. pp.367-370, ⟨10.1145/2911996.2912070⟩. ⟨hal-01373778⟩
277 View
96 Download



Gmail Facebook Twitter LinkedIn More